CN104933700A - Method and apparatus for image content recognition - Google Patents

Method and apparatus for image content recognition Download PDF

Info

Publication number
CN104933700A
CN104933700A CN201510232787.9A CN201510232787A CN104933700A CN 104933700 A CN104933700 A CN 104933700A CN 201510232787 A CN201510232787 A CN 201510232787A CN 104933700 A CN104933700 A CN 104933700A
Authority
CN
China
Prior art keywords
value
gradient
gray
image
pixel
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201510232787.9A
Other languages
Chinese (zh)
Other versions
CN104933700B (en
Inventor
龙飞
侯文迪
汪平仄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Xiaomi Technology Co Ltd
Xiaomi Inc
Original Assignee
Xiaomi Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xiaomi Inc filed Critical Xiaomi Inc
Priority to CN201510232787.9A priority Critical patent/CN104933700B/en
Publication of CN104933700A publication Critical patent/CN104933700A/en
Application granted granted Critical
Publication of CN104933700B publication Critical patent/CN104933700B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/22—Character recognition characterised by the type of writing
    • G06V30/224—Character recognition characterised by the type of writing of printed characters having additional code marks or containing code marks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20068—Projection on vertical or horizontal image axis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/469—Contour-based spatial representations, e.g. vector-coding
    • G06V10/473—Contour-based spatial representations, e.g. vector-coding using gradient analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)

Abstract

The present disclosure, belonging to the field of computer technologies, relates to a method and apparatus for image content recognition. The method comprises: performing gradient detection on an image to be identified, to obtain a gradient value of each pixel of the image to be identified; according to a first value range of each gradient value obtained via the gradient detection, and a second value range of a predetermined gray value, determining a mapping relationship between the gradient values in the first value range and the gray values in the second value range; respectively determining a gray value corresponding to the gradient value of each pixel according to the mapping relationship; determining a pixel value of each pixel in the gradient image according to the determined grey value corresponding to each pixel, to obtain a gradient image corresponding to the image to be identified, and identifying the content of the image according to the gradient image. According to the present disclosure, accuracy in boarder detection can be improved.

Description

A kind of method and apparatus carrying out picture material identification
Technical field
The disclosure is directed to field of computer technology, especially about a kind of method and apparatus carrying out picture material identification.
Background technology
Along with the development of computer technology, the purposes of computing machine is more and more extensive, and also from strength to strength, people can carry out picture material identification, as Boundary Detection, character recognition etc. by computing machine to function.Wherein, gradient image carries out image conventional in picture material identification.
VG (vertical gradient) operator and horizontal gradient operator can be prestored in computing machine, after computing machine gets image to be identified, the gray scale of pixel each in image to be identified and VG (vertical gradient) operator and horizontal gradient operator are carried out convolution algorithm respectively, obtain vertical gradient value and the horizontal gradient value of each pixel in image to be identified, Grad can the diversity factor of reflected image vegetarian refreshments and neighbor pixel.Computing machine using vertical gradient value or horizontal gradient value as the pixel value of pixel, can obtain the gradient image of image to be identified, and then treats recognition image according to gradient image and carry out picture material identification.
Realizing in process of the present disclosure, inventor finds at least there is following problem:
But, the pixel value range of the pixel that computing machine is given tacit consent to when carrying out image procossing is 0 ~ 255, if find that the pixel value of pixel is less than 0, then it can be used as 0 process, if find that the pixel value of pixel is greater than 255, then it can be used as 255 process, like this, when carrying out image procossing, different Grad may be considered as identical, thus, cause the accuracy carrying out picture material identification lower.
Summary of the invention
In order to overcome Problems existing in correlation technique, present disclose provides a kind of method and apparatus carrying out picture material identification.Described technical scheme is as follows:
According to the first aspect of disclosure embodiment, provide one to carry out picture material and know method for distinguishing, described method comprises:
Treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of described image to be identified;
According to the first numerical range of each Grad that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
The gray-scale value that the Grad of described each pixel is corresponding is determined respectively according to described mapping relations;
The gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carries out picture material identification.
Optionally, first numerical range of the described each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, comprising:
First numerical range of the absolute value of each Grad obtained according to described gradient check processing, determines the maximum value in described first numerical range and least absolute value;
According to the ratio shared by the maximum value of maximal value in described first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value;
Describedly determine respectively to comprise the gray-scale value that the Grad of described each pixel is corresponding according to described mapping relations:
The gray-scale value that the absolute value of the Grad of described each pixel is corresponding is determined respectively according to described mapping relations.
Optionally, described recognition image for the treatment of carries out gradient check processing, obtain the Grad of each pixel of described image to be identified, comprise: according to the VG (vertical gradient) operator prestored and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of described image to be identified;
First numerical range of the described each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, comprise: according to the first numerical range of each vertical gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in described first numerical range and the gray-scale value within the scope of described second value; According to the third value scope of each horizontal gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of described third value and the gray-scale value within the scope of described second value;
Describedly determine according to described mapping relations the gray-scale value that the Grad of described each pixel is corresponding respectively, comprise: determine the gray-scale value that the vertical gradient value of described each pixel is corresponding and the gray-scale value that the horizontal gradient value of described each pixel is corresponding respectively according to described mapping relations.
Optionally, described Grad is horizontal gradient value or vertical gradient value.
Optionally, described based on described gradient image, carry out picture material identification, comprising:
Based on described gradient image, carry out Image Edge-Detection, obtain the border of the target object in described image to be identified, in the border of described target object, carry out picture material identification.
According to the second aspect of disclosure embodiment, provide a kind of device carrying out picture material identification, described device comprises:
Detection module, carrying out gradient check processing for treating recognition image, obtaining the Grad of each pixel of described image to be identified;
First determination module, for the first numerical range of each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
Second determination module, for determining the gray-scale value that the Grad of described each pixel is corresponding respectively according to described mapping relations;
Identification module, for the gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carry out picture material identification.
Optionally, described first determination module, for:
First numerical range of the absolute value of each Grad obtained according to described gradient check processing, determines the maximum value in described first numerical range and least absolute value;
According to the ratio shared by the maximum value of maximal value in described first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value;
Described second determination module, for:
The gray-scale value that the absolute value of the Grad of described each pixel is corresponding is determined respectively according to described mapping relations.
Optionally, described detection module, for: according to the VG (vertical gradient) operator prestored and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of described image to be identified;
Described first determination module, for: according to the first numerical range of each vertical gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in described first numerical range and the gray-scale value within the scope of described second value; According to the third value scope of each horizontal gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of described third value and the gray-scale value within the scope of described second value;
Described second determination module, for: determine the gray-scale value that the vertical gradient value of described each pixel is corresponding and the gray-scale value that the horizontal gradient value of described each pixel is corresponding respectively according to described mapping relations.
Optionally, described Grad is horizontal gradient value or vertical gradient value.
Optionally, institute's identification module, for:
Based on described gradient image, carry out Image Edge-Detection, obtain the border of the target object in described image to be identified, in the border of described target object, carry out picture material identification.
According to the third aspect of disclosure embodiment, a kind of device carrying out picture material identification is provided, comprises:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of described image to be identified;
According to the first numerical range of each Grad that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
The gray-scale value that the Grad of described each pixel is corresponding is determined respectively according to described mapping relations;
The gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carries out picture material identification.
The technical scheme that embodiment of the present disclosure provides can comprise following beneficial effect:
In disclosure embodiment, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in these mapping relations, the gray-scale value that different Grad is corresponding is different, the gray-scale value that the Grad of each pixel is corresponding is determined respectively according to mapping relations, the gray-scale value corresponding according to each pixel determined, determine the pixel value of each pixel in gradient image, obtain the gradient image that image to be identified is corresponding, and based on gradient image, carry out picture material identification, like this, the gray-scale value corresponding due to different Grad is different, thus when image procossing, there will not be and different Grad is considered as identical situation, thus the accuracy carrying out picture material identification can be improved.
Should be understood that, it is only exemplary and explanatory that above general description and details hereinafter describe, and can not limit the disclosure.
Accompanying drawing explanation
Accompanying drawing to be herein merged in instructions and to form the part of this instructions, shows and meets embodiment of the present disclosure, and is used from instructions one and explains principle of the present disclosure.In the accompanying drawings:
Fig. 1 is a kind of process flow diagram carrying out picture material knowledge method for distinguishing according to an exemplary embodiment;
Fig. 2 is a kind of mapping schematic diagram carrying out picture material identification according to an exemplary embodiment;
Fig. 3 is a kind of schematic diagram carrying out the device of picture material identification according to an exemplary embodiment;
Fig. 4 is the structural representation of a kind of terminal according to an exemplary embodiment.
By above-mentioned accompanying drawing, illustrate the embodiment that the disclosure is clear and definite more detailed description will be had hereinafter.These accompanying drawings and text description be not in order to limited by any mode the disclosure design scope, but by reference to specific embodiment for those skilled in the art illustrate concept of the present disclosure.
Embodiment
Here will be described exemplary embodiment in detail, its sample table shows in the accompanying drawings.When description below relates to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawing represents same or analogous key element.Embodiment described in following exemplary embodiment does not represent all embodiments consistent with the disclosure.On the contrary, they only with as in appended claims describe in detail, the example of apparatus and method that aspects more of the present disclosure are consistent.
The disclosure one exemplary embodiment provides one and carries out picture material knowledge method for distinguishing, and as shown in Figure 1, the treatment scheme of the method can comprise following step:
In a step 101, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified.
In a step 102, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in these mapping relations, the gray-scale value that different Grad is corresponding is different.
In step 103, determine according to mapping relations the gray-scale value that the Grad of each pixel is corresponding respectively.
At step 104, the gray-scale value corresponding according to each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that image to be identified is corresponding, and based on gradient image, carries out picture material identification.
In disclosure embodiment, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in these mapping relations, the gray-scale value that different Grad is corresponding is different, the gray-scale value that the Grad of each pixel is corresponding is determined respectively according to mapping relations, the gray-scale value corresponding according to each pixel determined, determine the pixel value of each pixel in gradient image, obtain the gradient image that image to be identified is corresponding, and based on gradient image, carry out picture material identification, like this, the gray-scale value corresponding due to different Grad is different, thus when image procossing, there will not be and different Grad is considered as identical situation, thus the accuracy carrying out picture material identification can be improved.
Another exemplary embodiment of the disclosure provides one and carries out picture material knowledge method for distinguishing, and the method may be used in terminal, and wherein, terminal can be the terminal with image identification function, as the mobile terminal such as mobile phone or panel computer.Described terminal can be provided with the application program with picture material recognition function, described terminal can comprise input block, and described input block can be camera, also can be scanner etc., and terminal can obtain image to be identified by input block; Described terminal can comprise processor, and described processor according to the image to be identified got, can carry out identifying processing, as rim detection, or character recognition etc.; Described terminal can also comprise display unit, and described display unit can liquid crystal display, and display unit can the information that obtained by identifying processing of video-stream processor.In addition, described terminal can also comprise the parts such as storer, sensor, voicefrequency circuit and power supply.
Below in conjunction with embodiment, be described in detail the treatment scheme shown in Fig. 1, content can be as follows:
In a step 101, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified.
In force, user can install in terminal have the application program of picture material recognition function, and user can by the information of object (i.e. target object) comprised in this application identification image, as the bank's card number on identification bank card.When user wishes recognition target object, user can open this application program in terminal, terminal can open input equipment (as camera), and surveyed area is shown in screen, user can the position of mobile terminal, can obtain the image (i.e. image to be identified) including target object to make terminal.After terminal obtains image to be identified, can sobel border detection algorithm be passed through, treat recognition image and carry out gradient check processing.Terminal can determine the gray-scale value of each pixel in image to be identified, then the operator in the gray-scale value of each pixel and sobel algorithm can be carried out convolution algorithm, obtain the Grad of each pixel of image to be identified.Sobel algorithm comprises VG (vertical gradient) operator and horizontal gradient operator, terminal can determine vertical gradient value or the horizontal gradient value of each pixel in image to be identified, also can determine vertical gradient value and the horizontal gradient value of each pixel in image to be identified, corresponding processing mode can have following two kinds:
The VG (vertical gradient) operator that mode one, basis prestore and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of image to be identified.
In force, the VG (vertical gradient) operator in sobel algorithm and horizontal gradient operator can be prestored in terminal, for the arbitrary pixel (x treated in recognition image, y), terminal can use VG (vertical gradient) operator and horizontal gradient operator to pixel (x respectively, y) carry out convolution algorithm, obtain vertical gradient value and the horizontal gradient value of pixel (x, y).
VG (vertical gradient) operator in sobel algorithm and horizontal gradient operator as shown in the table:
For the arbitrary pixel (x, y) in image to be identified, (x, y) can be adjacent pixel and be expressed as:
(x-1，y+1) (x，y+1) (x+1，y+1)
(x-1，y) (x，y) (x+1，y)
(x-1，y-1) (x，y-1) (x+1，y-1)
The gray-scale value that pixel (x, y) is corresponding in image to be identified can be expressed as f (x, y), terminal can pass through convolutional calculation, obtain vertical gradient value and the horizontal gradient value of pixel (x, y), concrete computation process can be as follows:
Vertical gradient value:
G y＝1*f(x-1,y+1)+2*f(x,y+1)+1*f(x+1,y+1)+0*f(x-1,y)+0*f(x,y)+0*f(x+1,y)+(-1)*f(x-1,y-1)+(-2)*f(x,y-1)+(-1)*f(x+1,y-1)＝[f(x-1,y+1)+2f(x,y+1)+f(x+1,y+1)]-[f(x-1,y-1)+2*f(x,y-1)+f(x+1,y-1)]
Horizontal vertical ladder angle value:
G x＝(-1)*f(x-1,y+1)+0*f(x,y+1)+1*f(x+1,y+1)+(-2)*f(x-1,y)+0*f(x,y)+2*f(x+1,y)+(-1)*f(x-1,y-1)+0*f(x,y-1)+1*f(x+1,y-1)＝[f(x+1,y+1)+2*f(x+1,y)+f(x+1,y-1)]-[f(x-1,y+1)+2*f(x-1,y)+f(x-1,y-1)]
The VG (vertical gradient) operator that mode two, basis prestore or horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value or the horizontal gradient value of each pixel of image to be identified.
In force, based on above-mentioned calculating vertical gradient value with or the identical computing method of horizontal gradient value, terminal only can calculate the vertical gradient value of each pixel of image to be identified, or only calculates the horizontal gradient value of each pixel of image to be identified, repeats no more.
In a step 102, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different.
In force, after terminal obtains the Grad of each pixel in image to be identified, the numerical range (i.e. the first numerical range) of each Grad obtained can be determined, and the scope (i.e. second value scope) of default gray-scale value can be stored, second value scope can be 0 ~ 255, and then terminal can determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value.
Such as, terminal determines that the first numerical range is-100 ~ 1000, and the mapping relations of the arbitrary Grad a in the first numerical range and the gray-scale value within the scope of second value can be:
Gray-scale value a ＇ after mapping=[a-(-100)] * 255/ [1000-(-100)]=(a+100) * 255/1100
Optionally, first can determine the absolute value of each Grad, determine mapping relations again, accordingly, the processing procedure of step 102 can be as follows: the first numerical range of the absolute value of each Grad obtained according to gradient check processing, determines the maximum value in the first numerical range and least absolute value; According to the ratio shared by the maximum value of maximal value in the first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value.
In force, after terminal obtains the Grad of each pixel in image to be identified, the absolute value of the Grad of each pixel can be determined, and then determine the maximum value in these absolute values and least absolute value, thus obtain the first numerical range, the scope (i.e. second value scope) of default gray-scale value can be stored in terminal, second value scope can be 0 ~ 255, for 0 ~ 255, terminal can determine ratio shared in the difference of 255 maximum values in the first numerical range and least absolute value, and then terminal can determine the mapping relations of the Grad in the first numerical range and the gray-scale value in 0 ~ 255 scope.
Such as, terminal can be determined in the absolute value of the Grad of each pixel, and maximum value is 1000, and least absolute value is 100, namely to be the mapping relations of the arbitrary Grad a in the 100 ~ 1000, first numerical range and the gray-scale value in 0 ~ 255 scope can be the first numerical range:
Gray-scale value a ＇=(a-100) * 255/ (1000-100) after mapping
Optionally, for the above-mentioned vertical gradient value of each pixel and the situation of horizontal gradient value that obtain image to be identified, accordingly, the processing procedure of step 102 can be as follows: according to the first numerical range of each vertical gradient value that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in the first numerical range and the gray-scale value within the scope of second value; According to the third value scope of each horizontal gradient value that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of third value and the gray-scale value within the scope of second value.
In force, after the vertical gradient value that terminal obtains each pixel of image to be identified and horizontal gradient value, in the vertical gradient value obtained, the maximal value in vertical gradient value and minimum value can be determined, thus obtain the numerical range (i.e. the first numerical range) of vertical gradient value.Terminal can store the scope (i.e. second value scope) of default gray-scale value, and second value scope can be 0 ~ 255, and then terminal can determine the mapping relations of the vertical gradient value in the first numerical range and the gray-scale value within the scope of second value.In addition, terminal also first can determine the absolute value of vertical gradient value, then the first numerical range of the absolute value of vertical gradient value is determined, and first maximum value in numerical range and least absolute value, according to the ratio shared by the maximum value of maximal value in the first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the vertical gradient value in the first numerical range and the gray-scale value within the scope of second value, concrete processing procedure and above-mentioned processing procedure similar, repeat no more.
Terminal in the horizontal gradient value obtained, can also determine the maximal value in horizontal gradient value and minimum value, thus obtains the numerical range (i.e. third value scope) of horizontal gradient value.Terminal can store the scope (i.e. second value scope) of default gray-scale value, and second value scope can be 0 ~ 255, and then terminal can determine the mapping relations of the horizontal gradient value within the scope of third value and the gray-scale value within the scope of second value.In addition, terminal also first can determine the absolute value of horizontal gradient value, then the third value scope of the absolute value of horizontal gradient value is determined, determine the maximum value in third value scope and least absolute value, according to the ratio shared by the maximum value of maximal value in third value scope in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the horizontal gradient value within the scope of third value and the gray-scale value within the scope of second value, concrete processing procedure and above-mentioned processing procedure similar, repeat no more.
In step 103, determine according to mapping relations the gray-scale value that the Grad of each pixel is corresponding respectively.
In force, after terminal determines the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, the Grad of each pixel can be brought in the mapping relations determined, obtain the gray-scale value that the Grad of each pixel is corresponding.Such as, terminal determines that the first numerical range is-100 ~ 1000, the mapping relations of the arbitrary Grad a in the first numerical range and the gray-scale value within the scope of second value can be: the gray-scale value a ＇ after mapping=[a-(-100)] * 255/ [1000-(-100)]=(a+100) * 255/1100, pixel (x 1, y 1) Grad be 500, then pixel (x 1, y 1) gray-scale value corresponding to Grad be (500+100) * 255/1100=139.The gray-scale value that the Grad of each pixel is corresponding is generally integer, for calculating non-integral situation, can adopt modes such as rounding up or round, obtaining the gray-scale value that the Grad of each pixel is corresponding.
Optionally, for the above-mentioned situation determining the absolute value of the Grad of each pixel, accordingly, the processing procedure of step 103 can be as follows: determine the gray-scale value that the absolute value of the Grad of each pixel is corresponding respectively according to mapping relations.
In force, after terminal determines the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, the absolute value of the Grad of each pixel can be brought in the formula of the mapping relations determined, obtain the gray-scale value that the Grad of each pixel is corresponding.Such as, terminal determines that the first numerical range is 100 ~ 1000, the mapping relations of the arbitrary Grad a in the first numerical range and the gray-scale value within the scope of second value can be: gray-scale value a ＇=(a-100) * 255/ (1000-100) after mapping, pixel (x 1, y 1) Grad be-150, then pixel (x 1, y 1) gray-scale value corresponding to the absolute value of Grad be (150-100) * 255/ (1000-100)=14, as shown in Figure 2.The gray-scale value that the Grad of each pixel is corresponding is generally integer, for calculating non-integral situation, can adopt modes such as rounding up or round, obtaining the gray-scale value that the Grad of each pixel is corresponding.
Optionally, for the above-mentioned mapping relations determining the vertical gradient value in the first numerical range and the gray-scale value within the scope of second value, and determine the situation of mapping relations of the horizontal gradient value within the scope of third value and the gray-scale value within the scope of second value, accordingly, the processing procedure of step 103 can be as follows: determine the gray-scale value that the vertical gradient value of each pixel is corresponding and the gray-scale value that the horizontal gradient value of each pixel is corresponding respectively according to mapping relations.
In force, after terminal determines the mapping relations of the vertical gradient value in the first numerical range and the gray-scale value within the scope of second value, the vertical gradient value of each pixel can be brought in the formula of the mapping relations determined, obtain the gray-scale value that the vertical gradient value of each pixel is corresponding.Terminal can also after the mapping relations determining the horizontal gradient value within the scope of third value and the gray-scale value within the scope of second value, the horizontal gradient value of each pixel can be brought in the formula of the mapping relations determined, obtain the gray-scale value that the horizontal gradient value of each pixel is corresponding.
At step 104, the gray-scale value corresponding according to each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that image to be identified is corresponding, and based on gradient image, carries out picture material identification.
In force, after terminal determines the gray-scale value that the Grad of each pixel is corresponding, the pixel value of each pixel in gradient image can be determined, thus obtain gradient image corresponding to image to be identified, and then terminal based on gradient image, can carry out picture material identification, such as, terminal can based on gradient image, and the object comprised in recognition image determines the outline line of object.
For the situation of the vertical gradient value or horizontal gradient value of determining each pixel, terminal can by gray-scale value corresponding for the vertical gradient value of each pixel, as the pixel value of pixel each in gradient image, or, terminal can by gray-scale value corresponding for the horizontal gradient value of each pixel, as the pixel value of pixel each in gradient image.Terminal according to the pixel value of pixel each in gradient image, can obtain the gradient image that image to be identified is corresponding.
For the situation of the vertical gradient value and horizontal gradient value of determining each pixel, for the arbitrary pixel in image to be identified, terminal can obtain gray-scale value corresponding to the vertical gradient value of this pixel and gray-scale value corresponding to horizontal gradient value, then can calculate square gray-scale value corresponding with horizontal gradient value of gray-scale value corresponding to vertical gradient value square and value, again extracting operation is carried out to this and value, obtain the pixel value that this pixel is corresponding, and then obtain gradient image corresponding to image to be identified.
Optionally, can also carry out Image Edge-Detection based on gradient image, corresponding processing procedure can be as follows: based on gradient image, carry out Image Edge-Detection, obtain the border of the target object in image to be identified, in the border of target object, carry out picture material identification.
In force, after terminal obtains gradient image corresponding to image to be identified, can carry out Image Edge-Detection, obtain the border of the target object in image to be identified in gradient image, terminal in the border of target object, can carry out picture material identification.Such as, target object can be bank card, then terminal can pass through Image Edge-Detection, obtains the border of bank card, then in the border of bank card, carries out picture material identification, thus identifies the card number on bank card.
In disclosure embodiment, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in these mapping relations, the gray-scale value that different Grad is corresponding is different, the gray-scale value that the Grad of each pixel is corresponding is determined respectively according to mapping relations, the gray-scale value corresponding according to each pixel determined, determine the pixel value of each pixel in gradient image, obtain the gradient image that image to be identified is corresponding, and based on gradient image, carry out picture material identification, like this, the gray-scale value corresponding due to different Grad is different, thus when image procossing, there will not be and different Grad is considered as identical situation, thus the accuracy carrying out picture material identification can be improved.
The another exemplary embodiment of the disclosure provides a kind of device carrying out picture material identification, and as shown in Figure 3, this device comprises: detection module 310, the first determination module 320, second determination module 330 and identification module 340.
Detection module 310, carrying out gradient check processing for treating recognition image, obtaining the Grad of each pixel of described image to be identified;
First determination module 320, for the first numerical range of each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
Second determination module 330, for determining the gray-scale value that the Grad of described each pixel is corresponding respectively according to described mapping relations;
Identification module 340, for the gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carry out picture material identification.
Optionally, described first determination module 320, for:
First numerical range of the absolute value of each Grad obtained according to described gradient check processing, determines the maximum value in described first numerical range and least absolute value;
According to the ratio shared by the maximum value of maximal value in described first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value;
Described second determination module 330, for:
The gray-scale value that the absolute value of the Grad of described each pixel is corresponding is determined respectively according to described mapping relations.
Optionally, described detection module 310, for: according to the VG (vertical gradient) operator prestored and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of described image to be identified;
Described first determination module 320, for: according to the first numerical range of each vertical gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in described first numerical range and the gray-scale value within the scope of described second value; According to the third value scope of each horizontal gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of described third value and the gray-scale value within the scope of described second value;
Described second determination module 330, for: determine the gray-scale value that the vertical gradient value of described each pixel is corresponding and the gray-scale value that the horizontal gradient value of described each pixel is corresponding respectively according to described mapping relations.
Optionally, described Grad is horizontal gradient value or vertical gradient value.
Optionally, institute's identification module 340, for:
Based on described gradient image, carry out Image Edge-Detection, obtain the border of the target object in described image to be identified, in the border of described target object, carry out picture material identification.
About the device in above-described embodiment, wherein the concrete mode of modules executable operations has been described in detail in about the embodiment of the method, will not elaborate explanation herein.
In disclosure embodiment, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in these mapping relations, the gray-scale value that different Grad is corresponding is different, the gray-scale value that the Grad of each pixel is corresponding is determined respectively according to mapping relations, the gray-scale value corresponding according to each pixel determined, determine the pixel value of each pixel in gradient image, obtain the gradient image that image to be identified is corresponding, and based on gradient image, carry out picture material identification, like this, the gray-scale value corresponding due to different Grad is different, thus when image procossing, there will not be and different Grad is considered as identical situation, thus the accuracy carrying out picture material identification can be improved.
It should be noted that: the device carrying out picture material identification that above-described embodiment provides is when carrying out picture material identification, only be illustrated with the division of above-mentioned each functional module, in practical application, can distribute as required and by above-mentioned functions and be completed by different functional modules, inner structure by equipment is divided into different functional modules, to complete all or part of function described above.In addition, the device carrying out picture material identification that above-described embodiment provides belongs to same design with the embodiment of the method for carrying out picture material identification, and its specific implementation process refers to embodiment of the method, repeats no more here.
A disclosure again exemplary embodiment provides a kind of structural representation of terminal.This terminal can be mobile phone etc.
With reference to Fig. 4, terminal 800 can comprise following one or more assembly: processing components 802, storer 804, power supply module 806, multimedia groupware 808, audio-frequency assembly 810, the interface 812 of I/O (I/O), sensor module 814, and communications component 816.
The integrated operation of the usual control terminal 800 of processing components 802, such as with display, call, data communication, camera operation and record operate the operation be associated.Treatment element 802 can comprise one or more processor 820 to perform instruction, to complete all or part of step of above-mentioned method.In addition, processing components 802 can comprise one or more module, and what be convenient between processing components 802 and other assemblies is mutual.Such as, processing element 802 can comprise multi-media module, mutual with what facilitate between multimedia groupware 808 and processing components 802.
Storer 804 is configured to store various types of data to be supported in the operation of terminal 800.The example of these data comprises for any application program of operation in terminal 800 or the instruction of method, contact data, telephone book data, message, picture, video etc.Storer 804 can be realized by the volatibility of any type or non-volatile memory device or their combination, as static RAM (SRAM), Electrically Erasable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory EPROM (EPROM), programmable read only memory (PROM), ROM (read-only memory) (ROM), magnetic store, flash memory, disk or CD.
The various assemblies that electric power assembly 806 is terminal 800 provide electric power.Electric power assembly 806 can comprise power-supply management system, one or more power supply, and other and the assembly generating, manage and distribute electric power for audio output apparatus 800 and be associated.
Multimedia groupware 808 is included in the screen providing an output interface between described terminal 800 and user.In certain embodiments, screen can comprise liquid crystal display (LCD) and touch panel (TP).If screen comprises touch panel, screen may be implemented as touch-screen, to receive the input signal from user.Touch panel comprises one or more touch sensor with the gesture on sensing touch, slip and touch panel.Described touch sensor can the border of not only sensing touch or sliding action, but also detects the duration relevant to described touch or slide and pressure.In certain embodiments, multimedia groupware 808 comprises a front-facing camera and/or post-positioned pick-up head.When terminal 800 is in operator scheme, during as screening-mode or video mode, front-facing camera and/or post-positioned pick-up head can receive outside multi-medium data.Each front-facing camera and post-positioned pick-up head can be fixing optical lens systems or have focal length and optical zoom ability.
Audio-frequency assembly 810 is configured to export and/or input audio signal.Such as, audio-frequency assembly 810 comprises a microphone (MIC), and when audio output apparatus 800 is in operator scheme, during as call model, logging mode and speech recognition mode, microphone is configured to receive external audio signal.The sound signal received can be stored in storer 804 further or be sent via communications component 816.
I/O interface 812 is for providing interface between processing components 802 and peripheral interface module, and above-mentioned peripheral interface module can be keyboard, some striking wheel, button etc.These buttons can include but not limited to: home button, volume button, start button and locking press button.
Sensor module 814 comprises one or more sensor, for providing the state estimation of various aspects for terminal 800.Such as, sensor module 814 can detect the opening/closing state of terminal 800, the relative positioning of assembly, such as described assembly is display and the keypad of terminal 800, the position of all right sense terminals 800 of sensor module 814 or terminal 800 1 assemblies changes, the presence or absence that user contacts with terminal 800, the temperature variation of terminal 800 orientation or acceleration/deceleration and terminal 800.Sensor module 814 can comprise proximity transducer, be configured to without any physical contact time detect near the existence of object.Sensor module 814 can also comprise optical sensor, as CMOS or ccd image sensor, for using in imaging applications.In certain embodiments, this sensor module 814 can also comprise acceleration transducer, gyro sensor, Magnetic Sensor, pressure transducer or temperature sensor.
Communications component 816 is configured to the communication being convenient to wired or wireless mode between terminal 800 and other equipment.Terminal 800 can access the wireless network based on communication standard, as WiFi, 2G or 3G, or their combination.In one exemplary embodiment, communication component 816 receives from the broadcast singal of external broadcasting management system or broadcast related information via broadcast channel.In one exemplary embodiment, described communication component 816 also comprises near-field communication (NFC) module, to promote junction service.Such as, can based on radio-frequency (RF) identification (RFID) technology in NFC module, Infrared Data Association (IrDA) technology, ultra broadband (UWB) technology, bluetooth (BT) technology and other technologies realize.
In the exemplary embodiment, terminal 800 can be realized, for performing said method by one or more application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD) (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components.
In the exemplary embodiment, additionally provide a kind of non-transitory computer-readable recording medium comprising instruction, such as, comprise the storer 804 of instruction, above-mentioned instruction can perform said method by the processor 820 of terminal 800.Such as, described non-transitory computer-readable recording medium can be ROM, random access memory (RAM), CD-ROM, tape, floppy disk and optical data storage devices etc.
A kind of non-transitory computer-readable recording medium, when the instruction in described storage medium is performed by the processor of terminal, make terminal can perform one and carry out picture material knowledge method for distinguishing, the method comprises:
Treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of described image to be identified;
According to the first numerical range of each Grad that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
The gray-scale value that the Grad of described each pixel is corresponding is determined respectively according to described mapping relations;
The gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carries out picture material identification.
Optionally, first numerical range of the described each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, comprising:
First numerical range of the absolute value of each Grad obtained according to described gradient check processing, determines the maximum value in described first numerical range and least absolute value;
According to the ratio shared by the maximum value of maximal value in described first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value;
Describedly determine respectively to comprise the gray-scale value that the Grad of described each pixel is corresponding according to described mapping relations:
The gray-scale value that the absolute value of the Grad of described each pixel is corresponding is determined respectively according to described mapping relations.
Optionally, described recognition image for the treatment of carries out gradient check processing, obtain the Grad of each pixel of described image to be identified, comprise: according to the VG (vertical gradient) operator prestored and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of described image to be identified;
First numerical range of the described each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, comprise: according to the first numerical range of each vertical gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in described first numerical range and the gray-scale value within the scope of described second value; According to the third value scope of each horizontal gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of described third value and the gray-scale value within the scope of described second value;
Describedly determine according to described mapping relations the gray-scale value that the Grad of described each pixel is corresponding respectively, comprise: determine the gray-scale value that the vertical gradient value of described each pixel is corresponding and the gray-scale value that the horizontal gradient value of described each pixel is corresponding respectively according to described mapping relations.
Optionally, described Grad is horizontal gradient value or vertical gradient value.
Optionally, described based on described gradient image, carry out picture material identification, comprising:
Based on described gradient image, carry out Image Edge-Detection, obtain the border of the target object in described image to be identified, in the border of described target object, carry out picture material identification.
In disclosure embodiment, treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of image to be identified, according to the first numerical range of each Grad that gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in the first numerical range and the gray-scale value within the scope of second value, in these mapping relations, the gray-scale value that different Grad is corresponding is different, the gray-scale value that the Grad of each pixel is corresponding is determined respectively according to mapping relations, the gray-scale value corresponding according to each pixel determined, determine the pixel value of each pixel in gradient image, obtain the gradient image that image to be identified is corresponding, and based on gradient image, carry out picture material identification, like this, the gray-scale value corresponding due to different Grad is different, thus when image procossing, there will not be and different Grad is considered as identical situation, thus the accuracy carrying out picture material identification can be improved.
Those skilled in the art, at consideration instructions and after putting into practice disclosed herein disclosing, will easily expect other embodiment of the present disclosure.The application is intended to contain any modification of the present disclosure, purposes or adaptations, and these modification, purposes or adaptations are followed general principle of the present disclosure and comprised the undocumented common practise in the art of the disclosure or conventional techniques means.Instructions and embodiment are only regarded as exemplary, and true scope of the present disclosure and spirit are pointed out by claim below.
Should be understood that, the disclosure is not limited to precision architecture described above and illustrated in the accompanying drawings, and can carry out various amendment and change not departing from its scope.The scope of the present disclosure is only limited by appended claim.

Claims (11)

1. carry out picture material and know a method for distinguishing, it is characterized in that, described method comprises:
Treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of described image to be identified;
According to the first numerical range of each Grad that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
The gray-scale value that the Grad of described each pixel is corresponding is determined respectively according to described mapping relations;
The gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carries out picture material identification.
2. method according to claim 1, it is characterized in that, first numerical range of the described each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, comprising:
First numerical range of the absolute value of each Grad obtained according to described gradient check processing, determines the maximum value in described first numerical range and least absolute value;
According to the ratio shared by the maximum value of maximal value in described first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value;
Describedly determine respectively to comprise the gray-scale value that the Grad of described each pixel is corresponding according to described mapping relations:
The gray-scale value that the absolute value of the Grad of described each pixel is corresponding is determined respectively according to described mapping relations.
3. method according to claim 1, it is characterized in that, described recognition image for the treatment of carries out gradient check processing, obtain the Grad of each pixel of described image to be identified, comprise: according to the VG (vertical gradient) operator prestored and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of described image to be identified;
First numerical range of the described each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, comprise: according to the first numerical range of each vertical gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in described first numerical range and the gray-scale value within the scope of described second value; According to the third value scope of each horizontal gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of described third value and the gray-scale value within the scope of described second value;
Describedly determine according to described mapping relations the gray-scale value that the Grad of described each pixel is corresponding respectively, comprise: determine the gray-scale value that the vertical gradient value of described each pixel is corresponding and the gray-scale value that the horizontal gradient value of described each pixel is corresponding respectively according to described mapping relations.
4. method according to claim 1, is characterized in that, described Grad is horizontal gradient value or vertical gradient value.
5. method according to claim 1, is characterized in that, described based on described gradient image, carries out picture material identification, comprising:
Based on described gradient image, carry out Image Edge-Detection, obtain the border of the target object in described image to be identified, in the border of described target object, carry out picture material identification.
6. carry out a device for picture material identification, it is characterized in that, described device comprises:
Detection module, carrying out gradient check processing for treating recognition image, obtaining the Grad of each pixel of described image to be identified;
First determination module, for the first numerical range of each Grad obtained according to described gradient check processing, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
Second determination module, for determining the gray-scale value that the Grad of described each pixel is corresponding respectively according to described mapping relations;
Identification module, for the gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carry out picture material identification.
7. device according to claim 6, is characterized in that, described first determination module, for:
First numerical range of the absolute value of each Grad obtained according to described gradient check processing, determines the maximum value in described first numerical range and least absolute value;
According to the ratio shared by the maximum value of maximal value in described first numerical range in the second value scope of the gray-scale value preset and the difference of least absolute value, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value;
Described second determination module, for:
The gray-scale value that the absolute value of the Grad of described each pixel is corresponding is determined respectively according to described mapping relations.
8. device according to claim 6, it is characterized in that, described detection module, for: according to the VG (vertical gradient) operator prestored and horizontal gradient operator, treat recognition image and carry out gradient check processing, obtain vertical gradient value and the horizontal gradient value of each pixel of described image to be identified;
Described first determination module, for: according to the first numerical range of each vertical gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the vertical gradient value in described first numerical range and the gray-scale value within the scope of described second value; According to the third value scope of each horizontal gradient value that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the horizontal gradient value within the scope of described third value and the gray-scale value within the scope of described second value;
Described second determination module, for: determine the gray-scale value that the vertical gradient value of described each pixel is corresponding and the gray-scale value that the horizontal gradient value of described each pixel is corresponding respectively according to described mapping relations.
9. device according to claim 6, is characterized in that, described Grad is horizontal gradient value or vertical gradient value.
10. device according to claim 6, is characterized in that, institute's identification module, for:
Based on described gradient image, carry out Image Edge-Detection, obtain the border of the target object in described image to be identified, in the border of described target object, carry out picture material identification.
11. 1 kinds of devices carrying out picture material identification, is characterized in that, comprising:
Processor;
For the storer of storage of processor executable instruction;
Wherein, described processor is configured to:
Treat recognition image and carry out gradient check processing, obtain the Grad of each pixel of described image to be identified;
According to the first numerical range of each Grad that described gradient check processing obtains, and the second value scope of the gray-scale value preset, determine the mapping relations of the Grad in described first numerical range and the gray-scale value within the scope of described second value, in described mapping relations, the gray-scale value that different Grad is corresponding is different;
The gray-scale value that the Grad of described each pixel is corresponding is determined respectively according to described mapping relations;
The gray-scale value corresponding according to the described each pixel determined, determines the pixel value of each pixel in gradient image, obtains the gradient image that described image to be identified is corresponding, and based on described gradient image, carries out picture material identification.
CN201510232787.9A 2015-05-08 2015-05-08 A kind of method and apparatus carrying out picture material identification Active CN104933700B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510232787.9A CN104933700B (en) 2015-05-08 2015-05-08 A kind of method and apparatus carrying out picture material identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510232787.9A CN104933700B (en) 2015-05-08 2015-05-08 A kind of method and apparatus carrying out picture material identification

Publications (2)

Publication Number Publication Date
CN104933700A true CN104933700A (en) 2015-09-23
CN104933700B CN104933700B (en) 2019-02-22

Family

ID=54120854

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510232787.9A Active CN104933700B (en) 2015-05-08 2015-05-08 A kind of method and apparatus carrying out picture material identification

Country Status (1)

Country Link
CN (1) CN104933700B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106530286A (en) * 2016-10-24 2017-03-22 乐视控股（北京）有限公司 Method and device for determining definition level
CN107371001A (en) * 2017-08-25 2017-11-21 无锡北斗星通信息科技有限公司 A kind of method of the heavy truck of monitoring in real time
CN107392942A (en) * 2017-08-28 2017-11-24 无锡北斗星通信息科技有限公司 Human body target real-time analyzer
CN107396061A (en) * 2017-08-25 2017-11-24 无锡北斗星通信息科技有限公司 Heavy truck real-time monitoring system
CN107563321A (en) * 2017-08-28 2018-01-09 无锡北斗星通信息科技有限公司 A kind of human body target real-time analysis method
CN108024010A (en) * 2017-11-07 2018-05-11 秦广民 Cellphone monitoring system based on electrical measurement

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004302581A (en) * 2003-03-28 2004-10-28 Matsushita Electric Works Ltd Image processing method and device
CN101064011A (en) * 2006-04-26 2007-10-31 电子科技大学 Vehicle registration extract method in complicated background based on wavelet transforming
US20080199074A1 (en) * 2007-02-19 2008-08-21 Tomoo Mitsunaga Image Processing Device and Method, Recording Medium, and Program
CN101710425A (en) * 2009-12-25 2010-05-19 南京航空航天大学 Self-adaptive pre-segmentation method based on gray scale and gradient of image and gray scale statistic histogram
CN101908207A (en) * 2010-07-26 2010-12-08 北京理工大学 Brightness stratification-based quick trilateral filter tone mapping method
CN103593847A (en) * 2013-11-25 2014-02-19 中国航天科工集团第三研究院第八三五七研究所 Raindrop detection analysis method based on machine vision

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004302581A (en) * 2003-03-28 2004-10-28 Matsushita Electric Works Ltd Image processing method and device
CN101064011A (en) * 2006-04-26 2007-10-31 电子科技大学 Vehicle registration extract method in complicated background based on wavelet transforming
US20080199074A1 (en) * 2007-02-19 2008-08-21 Tomoo Mitsunaga Image Processing Device and Method, Recording Medium, and Program
CN101710425A (en) * 2009-12-25 2010-05-19 南京航空航天大学 Self-adaptive pre-segmentation method based on gray scale and gradient of image and gray scale statistic histogram
CN101908207A (en) * 2010-07-26 2010-12-08 北京理工大学 Brightness stratification-based quick trilateral filter tone mapping method
CN103593847A (en) * 2013-11-25 2014-02-19 中国航天科工集团第三研究院第八三五七研究所 Raindrop detection analysis method based on machine vision

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
李学广 等: "基于灰度梯度映射函数的红外图像分割", 《红外技术》 *
黄庆华: "红外图像处理算法的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106530286A (en) * 2016-10-24 2017-03-22 乐视控股（北京）有限公司 Method and device for determining definition level
CN107371001A (en) * 2017-08-25 2017-11-21 无锡北斗星通信息科技有限公司 A kind of method of the heavy truck of monitoring in real time
CN107396061A (en) * 2017-08-25 2017-11-24 无锡北斗星通信息科技有限公司 Heavy truck real-time monitoring system
CN107392942A (en) * 2017-08-28 2017-11-24 无锡北斗星通信息科技有限公司 Human body target real-time analyzer
CN107563321A (en) * 2017-08-28 2018-01-09 无锡北斗星通信息科技有限公司 A kind of human body target real-time analysis method
CN107392942B (en) * 2017-08-28 2018-06-05 广州文冠信息科技有限公司 Human body target real-time analyzer
CN107563321B (en) * 2017-08-28 2018-07-13 深圳市奥丝卡生物科技有限公司 A kind of human body target real-time analysis method
CN108024010A (en) * 2017-11-07 2018-05-11 秦广民 Cellphone monitoring system based on electrical measurement
CN108024010B (en) * 2017-11-07 2018-09-14 赵敏 Cellphone monitoring system based on electrical measurement

Also Published As

Publication number Publication date
CN104933700B (en) 2019-02-22

Similar Documents

Publication Publication Date Title
CN105069786B (en) Line detection method and device
CN104158946B (en) A kind of method and device controlling terminal
CN104021350B (en) Privacy information hidden method and device
CN104933700A (en) Method and apparatus for image content recognition
CN103885588B (en) Automatic switching method and device
CN105528606A (en) Region identification method and device
CN104991789A (en) Method and apparatus for starting application
CN104615920A (en) Notification message display method and device
CN106355573A (en) Target object positioning method and device in pictures
CN105139378A (en) Card boundary detection method and apparatus
CN105095881A (en) Method, apparatus and terminal for face identification
CN105426741A (en) Screen unlocking method, device and terminal
CN105512685A (en) Object identification method and apparatus
CN107688781A (en) Face identification method and device
CN106250831A (en) Image detecting method, device and the device for image detection
CN104238912A (en) Application control method and application control device
CN105488511A (en) Image identification method and device
CN104899610A (en) Picture classification method and device
CN105069426A (en) Similar picture determining method and apparatus
CN106127751A (en) image detecting method, device and system
CN105069089A (en) Picture detection method and device
CN107742120A (en) The recognition methods of bank card number and device
CN106339695A (en) Face similarity detection method, device and terminal
CN104239879A (en) Character segmentation method and device
CN105046260A (en) Image pre-processing method and apparatus

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant