CN109977734A - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN109977734A CN109977734A CN201711454207.6A CN201711454207A CN109977734A CN 109977734 A CN109977734 A CN 109977734A CN 201711454207 A CN201711454207 A CN 201711454207A CN 109977734 A CN109977734 A CN 109977734A
- Authority
- CN
- China
- Prior art keywords
- image
- case
- processed
- texture complication
- hand shape
- 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
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
This application provides a kind of image processing method and devices, different skin color detection algorithms is selected to detect hand shape based on brightness and Texture complication, it is avoided that the limitation of single skin color detection algorithm, better choice is suitble to the skin color detection algorithm of current background, guarantee the effect of hand shape detection, reduces the probability of missing inspection and erroneous detection.
Description
Technical field
The application field of image processing more particularly to a kind of image processing method and device.
Background technique
Long-range AR (augmented reality, augmented reality) guidance is a kind of practical application of AR technology, in the application
It include director's terminal and tutee's terminal in scene, tutee's terminal is whole to director by the transmission of video images of acquisition
End, director's terminal acquire the hand shape image of director, collected hand shape are added to what tutee's terminal transmission came
On video image.In the application scenarios, the identification and segmentation of hand shape are a key technologies, in the prior art, hand shape
Identification process is: select a color space, binary conversion treatment carried out to image to be processed according to threshold value, using clustering or
The methods of template matching carries out the identification and segmentation of hand shape to bianry image.It has been found that current hand identification scheme is deposited
The problem of be: hand shape can only be identified and extract in stable and simple background, for identifying in background complicated and changeable
It is larger with probability of false detection when extracting hand shape.
Summary of the invention
The accurate of hand shape is identified and extracted under complex background the technical problem to be solved by the embodiment of the invention is that improving
Property provides a kind of image processing method and device.
The application first aspect provides a kind of image processing method, comprising: determines the average brightness of image to be processed；?
In the case that average brightness is located at luminance threshold section, the Texture complication of image to be processed is calculated；In the line of image to be processed
Complexity is managed less than in the case where Texture complication threshold value, image to be processed is carried out according to the skin color detection algorithm of fixed threshold
Processing obtains including bianry image.
Wherein, two endpoints in luminance threshold section are the first luminance threshold and the second luminance threshold, the first luminance threshold
Less than the second scheduling thresholds, the value in luminance threshold section may include two endpoints；Optionally, the first luminance threshold and second
Luminance threshold can be obtained by learning training or a large amount of test sample.The view of homogeneity phenomenon in the texture representation image of image
Feel feature, that embodies body surface has slowly varying or periodically variable surface textural alignment attribute.Face Detection
Algorithm in certain colour of skin space for having the characteristics that cluster property according to the colour of skin, by carrying out the detection to the colour of skin and dividing
It cuts, detects hand shape region.
In this embodiment, different skin color detection algorithms is selected to detect hand shape, energy based on brightness and Texture complication
The limitation of single skin color detection algorithm is avoided, better choice is suitble to the skin color detection algorithm of current background, guarantees hand shape
The effect of detection reduces the probability of missing inspection and erroneous detection.
In a kind of possible design, further includes: in the case where average brightness is not located at luminance threshold section, according to dynamic
The skin color detection algorithm of state threshold value is handled to obtain bianry image to image to be processed.
In a kind of possible design, in the case where the Texture complication is not less than Texture complication threshold value, according to
The skin color detection algorithm of dynamic threshold is handled to obtain bianry image to image to be processed.
In a kind of possible design, further includes:
Bianry image is divided into M × N number of rectangular area of M row N column；M and N is the integer greater than 1；According to hand in M × N
The distributing position in shape region carries out erroneous detection analysis and missing inspection analysis.
In a kind of possible design, M × N number of rectangular area number is
In the case where detecting that number is 11,4 rectangular areas of 1N, M1 and MN are hand shape region, determine currently
There are erroneous detections for testing result；Or
In the case where detecting that number is 11 and 2 rectangular areas of MN are hand shape region, current detection knot is determined
There are erroneous detections for fruit；Or
In the case where detecting that number is 1N and 2 rectangular areas of M1 are hand shape region, current detection knot is determined
There are erroneous detections for fruit；Or
In the case where outermost one layer of 2M+2N-4 rectangular area is hand shape region, current testing result is determined
There are erroneous detections.
In a kind of possible design, before the average brightness for determining image to be processed, further includes:
Multiple background images are acquired, determine the Texture complication of multiple background images；
Determine the average value of the Texture complication of multiple background images and the Texture complication of the multiple background image
In maximum value；Wherein, the Texture complication threshold value is between the average value and the maximum value.
Second aspect, this application provides a kind of image processing apparatus, the device is with the above-mentioned first aspect of realization and respectively
The function of behavior in a possible embodiment.The function can also be executed corresponding by hardware realization by hardware
Software realization.The hardware or software include one or more modules corresponding with above-mentioned function.
Described image processing unit comprises determining that unit, for determining the average brightness of image to be processed；
Computing unit, user calculate the figure to be processed in the case where the average brightness is located at luminance threshold section
The Texture complication of picture；
Detection unit is used in the case where the Texture complication is less than Texture complication threshold value, according to fixed threshold
Skin color detection algorithm the image to be processed is handled to obtain bianry image.
In a kind of possible design, the detection unit is also used to not be located at luminance threshold area in the average brightness
Between in the case where, the image to be processed is handled to obtain bianry image according to the skin color detection algorithm of dynamic threshold.
In a kind of possible design, the detection unit is also used to complicated not less than texture in the Texture complication
In the case where spending threshold value, the image to be processed is handled to obtain binary map according to the skin color detection algorithm of dynamic threshold
Picture.
In a kind of possible design, erroneous detection analytical unit, for the bianry image to be divided into M × N of M row N column
A rectangular area；M and N is the integer greater than 1；
Erroneous detection analysis is carried out according to the distributing position in hand shape region in the M × N number of rectangular area.
In a kind of possible design, the M × N number of rectangular area number is；
In the case where detecting that number is 11,4 rectangular areas of 1N, M1 and MN are hand shape region, determine current
Testing result there are erroneous detections；Or
In the case where detecting that number is 11 and 2 regions of MN are hand shape region, current testing result is determined
There are erroneous detections；Or；
In the case where detecting that number is 1N and 2 rectangular areas of M1 are hand shape region, current detection is determined
As a result there is erroneous detection；Or
In the case where outermost one layer of 2M+2N-4 rectangular area is hand shape region, current testing result is determined
There are erroneous detections.
In a kind of possible design, further includes:
Threshold setting unit, for determining the Texture complication of multiple background images；
Determine the average value of the Texture complication of multiple background images and the Texture complication of the multiple background image
In maximum value；Wherein, the Texture complication threshold value is between the average value and the maximum value.
The third aspect, this application provides a kind of image processing apparatus, described image processing unit includes: memory and place
Manage device；Wherein, batch processing code is stored in the memory, and the processor is used to call to store in the memory
Program code executes the image processing method in first aspect and each embodiment of first aspect.
The another aspect of the application has been mentioned for a kind of computer readable storage medium, in the computer readable storage medium
It is stored with instruction, when run on a computer, so that computer executes method described in above-mentioned various aspects.
The another aspect of the application provides a kind of computer program product comprising instruction, when it runs on computers
When, so that computer executes method described in above-mentioned various aspects.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to required in the embodiment of the present invention
The attached drawing used is illustrated.
Fig. 1 be the present embodiments relate to a kind of image processing method flow diagram；
Fig. 2 a is a kind of another flow diagram of image processing method provided in an embodiment of the present invention；
Fig. 2 b is a kind of schematic diagram of bianry image provided in an embodiment of the present invention；
Fig. 2 c is the number schematic diagram of the rectangular area after a kind of segmentation of bianry image provided in an embodiment of the present invention；
Fig. 3 is a kind of structural schematic diagram of image processing apparatus provided in an embodiment of the present invention；
Fig. 4 is a kind of another structural schematic diagram of image processing apparatus provided in an embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described with reference to the attached drawing in the embodiment of the present invention.
Image processing apparatus in application can be terminal device, can be handheld device with wireless communication function,
Mobile unit, calculates equipment or the other processing equipments for being connected to radio modem etc. at wearable device.In different nets
Terminal device can be called different titles in network, such as: user equipment, access terminal, subscriber unit, subscriber station, movement station,
Mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless telecom equipment, user agent or user's dress
It sets, cellular phone, wireless phone, session initiation protocol (Session Initiation Protocol, SIP) phone, wireless sheet
Ground loop (Wireless Local Loop, WLL) stands, personal digital assistant (Personal Digital Assistant,
PDA), the terminal device etc. in 5G network or future evolution network.
Referring to Fig. 1, Fig. 1 is a kind of flow diagram of image processing method provided in an embodiment of the present invention.This method
The following steps are included:
S101, the average brightness for determining image to be processed.
Specifically, image to be processed is digital picture, image to be processed includes multiple pixels.Determine the flat of image to be processed
It is YCrCb (also referred to as YUV) that the method for equal brightness, which includes: by the color space conversion of image to be processed, and each pixel is using bright
Degree (Y), tone (Cr or U) and saturation degree (Cb or V) indicate, obtain the brightness of each pixel in image to be processed, will acquire
To the brightness of each pixel be averaged (such as: arithmetic mean of instantaneous value) and obtain the average brightness of image to be processed.
S102, in the case where average brightness is located at luminance threshold section, calculate the Texture complication of image to be processed.
Specifically, image processing apparatus it is pre-stored or it is prewired be set to luminance threshold section, luminance threshold section is a Duan Lian
Continuous luminance threshold, the luminance threshold section may include two value endpoints: the first luminance threshold and the second luminance threshold, the
One luminance threshold is less than the second luminance threshold.In the case where the average brightness that S101 is calculated is in luminance threshold section,
I.e. average brightness be greater than or equal to the first luminance threshold, and be less than or equal to the second luminance threshold, image processing apparatus calculate to
The Texture complication of image is handled, the visual signature of homogeneity phenomenon, embodies the tool of body surface in the texture representation image of image
There is slowly varying or periodically variable surface textural alignment attribute.Optionally, image processing apparatus can use as follows
Formula 1 calculate the Texture complication of image to be processed:
Wherein, | | indicate signed magnitude arithmetic(al) symbol, f is Texture complication, and N indicates the quantity of pixel in image to be processed, n
Indicate the number of pixel in image to be processed, PixnIndicate the gray value for the pixel that number is n in image to be processed.
S103, Texture complication be less than Texture complication threshold value in the case where, according to the Face Detection of fixed threshold calculate
Method is handled to obtain bianry image to image to be processed.
Specifically, image processing apparatus is pre-stored or is pre-configured with Texture complication threshold value, compare the texture of S102 calculating
Whether complexity is less than Texture complication threshold value, if it is, according to the skin color detection algorithm of fixed threshold to image to be processed into
Row processing obtains bianry image.The skin color detection algorithm of fixed threshold carries out at binaryzation image to be processed using fixed threshold
Reason obtains bianry image after processing, include testing result in bianry image, such as: the region that white pixel is constituted is detection
The hand shape region arrived.
In this embodiment, different skin color detection algorithms is selected to detect hand shape, energy based on brightness and Texture complication
The limitation of single skin color detection algorithm is avoided, better choice is suitble to the skin color detection algorithm of current background, guarantees hand shape
The effect of detection reduces the probability of missing inspection and erroneous detection.
A referring to fig. 2 is a kind of another flow diagram of image processing method provided in an embodiment of the present invention, in this hair
In bright embodiment, which comprises
S201, the average brightness for determining image to be processed.
Specifically, image to be processed is digital picture, image to be processed includes multiple pixels, and the color of image to be processed is empty
Between include but is not limited to the color space of any one or other forms in RGB, HSV, YCrCb, the embodiment of the present invention do not limit
System.The method for determining the average brightness of image to be processed includes: to be averaged the average brightness of pixel each in image to be processed
Value (such as: arithmetic mean of instantaneous value) obtain the average brightness of image to be processed.It should be noted that determining being averaged for image to be processed
When brightness, need the image of other color spaces being converted to the space YCrCb.
Whether S202, average brightness are located at luminance threshold section.
Specifically, luminance threshold section includes two value endpoints: the first luminance threshold and the second luminance threshold, first is bright
Threshold value is spent less than the second luminance threshold, wherein the first luminance threshold and the second luminance threshold can be by learning trainings or a large amount of
Test sample obtain.Whether the average brightness that image processing apparatus judges that S201 is determined is located in luminance threshold section, if
It is to execute S203, no is no, execution S206.
S203, the Texture complication for calculating image to be processed.
Specifically, in the texture representation image of image homogeneity phenomenon visual signature, it is slow to embody having for physical surface
Variation periodically variable shows structure organization alignment attribute.Optional image processing apparatus can be using the formula in S102
1 calculates the Texture complication of image to be processed, and the Texture complication of image to be processed can also be calculated using other methods,
Such as: (GLCM), Tamura textural characteristics, autoregression texture model, wavelet transformation etc. are put to the proof in gray scale symbiosis.
Whether S204, Texture complication are less than Texture complication threshold value.
Specifically, image processing apparatus is pre-stored or is pre-configured with Texture complication threshold value, image processing apparatus compares
Whether the Texture complication that S203 is calculated is less than Texture complication threshold value, if yes executes S205, if NO executes S206.
Optionally, the method that image processing apparatus determines Texture complication threshold value may is that image processing apparatus using more
A background image, background image do not include hand shape, and image processing apparatus calculates the Texture complication of multiple background images, and determination is more
The Texture complication of a background image；Determine the Texture complication of multiple background images average value and the multiple background
Maximum value in the Texture complication of image；Wherein, the Texture complication threshold value the average value and the maximum value it
Between (such as: arithmetic mean of instantaneous value) it is used as Texture complication threshold value.
S205, image to be processed is handled according to the skin color detection algorithm of fixed threshold.
Specifically, the skin color detection algorithm of fixed threshold is carried out image to be processed at binaryzation using fixed threshold value
Reason, binary conversion treatment, which refers to, is converted to the only image there are two gray level for the image of multi-grey level.If image F to be processed (x,
Y) intensity value ranges are at [a, b], and the threshold value of binary conversion treatment is set as t, a≤t≤b, then the expression formula of binary conversion treatment are as follows: F
In the case where (x, y) >=t, G (x, y)=1；In the case where F (x, y) < t, G (x, y)=0.G (x, y) is bianry image.Solid
Determine in the skin color detection algorithm of threshold value, threshold value t immobilizes.
Such as: the skin color detection algorithm of fixed threshold is Cr+Cb algorithm, at the pixel of each image to be processed
Reason: in the Cr (tone) between [a, b] and when Cb (saturation degree) is between [c, d] of pixel, the gray value of the pixel is arranged
It is 1；Otherwise, the gray value of the part pixel is set as 0.Wherein, a, b, c and d are pre-set value.
S206, image to be processed is handled according to the skin color detection algorithm of dynamic threshold.
Specifically, threshold value t is dynamic change in the skin color detection algorithm of dynamic threshold, and such as: image to be processed point
It is segmented into different regions, the threshold value t in different regions is different.Such as: the skin color detection algorithm of dynamic threshold be Cr+OSTU (most
Big inter-class variance) algorithm.
S207, bianry image.
Specifically, according to the skin color detection algorithm of the skin color detection algorithm of fixed threshold or dynamic threshold to image to be processed
Bianry image is obtained after being handled, such as: the bianry image that b is referring to fig. 2, the picture that gray value is 1 in bianry image
Element is shown as white, and it is hand shape region that the pixel that gray value is 0, which is shown as the white area in black and bianry image,.
Optionally, after S207, further includes: bianry image is divided into M × N number of rectangular area, M and N of M row N column
For the integer greater than 1, erroneous detection analysis is carried out according to the distributing position in hand shape region in M × N number of rectangular area and missing inspection is analyzed.
Specifically, hand shape region indicates the pixel region including hand shape, such as the bianry image in Fig. 2 b, work as rectangular area
In include gray value be 0 pixel when, which is hand shape region.Erroneous detection analysis indicates to judge whether
The non-analytic process for hand shape, missing inspection analysis indicate to judge whether the analytic process by hand identification for non-hand shape.Image procossing
Whether device meets preset Distribution Strategy to determine whether there are erroneous detection or leakages according to the distributing position in hand shape region in M × N
Inspection.
Such as: the resolution ratio of bianry image is 1024 × 768, and the resolution ratio of rectangular area is 128 × 96, image procossing dress
It sets and bianry image is divided into 128 × 96 rectangular areas that 128 rows 96 arrange.
Wherein, for M × N number of region, if V={ Vi, i=1,2,3 ..., M × N, ViIt indicates in M × N number of rectangular area
Any one rectangular area；BjIt is a subset of V, P (Bj) indicate BjInterior all rectangular areas are simultaneously the general of hand shape region
Rate, P (Bj|Bk) indicate BkInterior all rectangular areas are B in the case where hand shape regionjInterior all areas are the probability in hand shape region.
According to constraint and feature pre-stored or be pre-configured, P (B is determinedj) and P (Bj|Bk) regularity, and according to P (Bj) and P (Bj|
Bk) value carry out erroneous detection analysis and missing inspection analysis.Such as:
In P (BjIn the case where)≤T4, i.e. BjInterior all areas are that the probability in hand shape region is less than or equal to the feelings of threshold value T4
Under condition, determine that there are erroneous detections for current testing result；
In P (BjIn the case where) >=T5, i.e. BjInterior all areas are that the probability in hand shape region is greater than or equal to the feelings of threshold value T5
Under condition, determine that there are missing inspections for current testing result；
In P (Bj|BkIn the case where)≤T6, i.e. BkB when interior all rectangular areas are hand shape regionjInterior all rectangular areas
For hand shape region probability be less than or equal to threshold value T6 in the case where, determine that there are erroneous detections for current testing result；
In P (Bj|BkIn the case where) >=T7, i.e. BkB when interior all rectangular areas are hand shape regionjInterior all rectangular areas
For hand shape region probability be greater than or equal to threshold value T7 in the case where, determine that there are missing inspections for current testing result.
It should be noted that threshold value T4, T5, T6 and T7 can according to need and be configured, specific value the present embodiment
With no restriction, such as: the value that the value of T4 and T6 is 0, T5 and T7 is 1.
Wherein, M × N number of rectangular area number is
In the case where detecting that number is 11,4 rectangular areas of 1N, M1 and MN are hand shape region, determine currently
There are erroneous detections for testing result；Or
In the case where detecting that number is 11 and 2 rectangular areas of MN are hand shape region, current detection knot is determined
There are erroneous detections for fruit；Or
In the case where detecting that number is 1N and 2 rectangular areas of M1 are hand shape region, current detection knot is determined
There are erroneous detections for fruit；Or
In the case where outermost one layer of 2M+2N-4 rectangular area is hand shape region, current testing result is determined
There are erroneous detections.
For example: bianry image is divided into 81 rectangular areas that 9 rows 9 arrange by c referring to fig. 2,81 rectangular areas
Number is as illustrated in fig. 2 c.
In the case where 4 rectangular areas for detecting that number is 11,19,91 and 99 are hand shape region, determine current
Testing result there are erroneous detections.
In the case where the two diagonal rectangular areas for detecting that number is 11 and 99 are hand shape region, determine current
Testing result there are erroneous detections.
In the case where the two diagonal rectangular areas for detecting that number is 91 and 19 are hand shape region, determine current
Testing result there are erroneous detections.
Detect an outermost circle 32 rectangular areas (number 11,12,13,14,15,16,17,18,19,29,
39,49,59,69,79,89,99,98,97,96,95,94,93,92,91,81,71,67,51,41,31,21 rectangular area)
In the case where being hand shape region, determine that there are erroneous detections for current testing result.
In this embodiment, different skin color detection algorithms is selected to detect hand shape, energy based on brightness and Texture complication
The limitation of single skin color detection algorithm is avoided, better choice is suitble to the skin color detection algorithm of current background, guarantees hand shape
The effect of detection reduces the probability of missing inspection and erroneous detection.
Referring to Fig. 3, a kind of Fig. 3 structural schematic diagram of image processing apparatus provided in an embodiment of the present invention.At the image
Managing device 3 (hereinafter referred to as device 3) may include: determination unit 301, computing unit 302 and detection unit 303, wherein each
Unit is described in detail as follows:
Determination unit 301, for determining the average brightness of image to be processed.
Computing unit 302, user calculate described to be processed in the case where the average brightness is located at luminance threshold section
The Texture complication of image.
Detection unit 303 is used in the case where the Texture complication is less than Texture complication threshold value, according to fixed threshold
The skin color detection algorithm of value is handled to obtain bianry image to the image to be processed.
In a kind of possible embodiment, detection unit 303 is also used to not be located at luminance threshold in the average brightness
In the case where section, the image to be processed is handled to obtain bianry image according to the skin color detection algorithm of dynamic threshold.
In a kind of possible embodiment, detection unit 303 is also used to multiple not less than texture in the Texture complication
In the case where miscellaneous degree threshold value, the image to be processed is handled to obtain binary map according to the skin color detection algorithm of dynamic threshold
Picture.
In a kind of possible embodiment, device 3 further include: analytical unit (is not drawn into) in figure.
Analytical unit, for the bianry image to be divided into M × N number of rectangular area of M row N column；M and N is greater than 1
Integer；
Erroneous detection analysis and missing inspection analysis are carried out according to the distributing position in hand shape region in the M × N number of rectangular area.
In a kind of possible embodiment, the M × N number of rectangular area number is
In the case where detecting that number is 11,4 rectangular areas of 1N, M1 and MN are hand shape region, determine current
Testing result there are erroneous detections；Or
In the case where detecting that number is 11 and 2 regions of MN are hand shape region, current testing result is determined
There are erroneous detections；Or；
In the case where detecting that number is 1N and 2 rectangular areas of M1 are hand shape region, current detection is determined
As a result there is erroneous detection；Or
In the case where outermost one layer of 2M+2N-4 rectangular area is hand shape region, current testing result is determined
There are erroneous detections.
In a kind of possible embodiment, device 3 further include: threshold setting unit (is not drawn into) in figure.
Threshold setting unit, for determining the Texture complication of multiple background images；Determine the texture of multiple background images
Maximum value in the Texture complication of the average value of complexity and the multiple background image；Wherein, the Texture complication
Threshold value is between the average value and the maximum value.
Reality described device 4 of the present invention or the field programmable gate array (field- for realizing correlation function
Programmable gate array, FPGA), special integrated chip, System on Chip/SoC (system on chip, SoC), center
Processor (central processor unit, CPU), network processing unit (network processor, NP), digital signal
Processing circuit, microcontroller (micro controller unit, MCU), can also use programmable controller
(programmable logic device, PLD) or other integrated chips.
Originally the embodiment of the method for applying example and Fig. 2 a is based on same design, and bring technical effect is also identical, detailed process
It can refer to the description of the embodiment of the method for Fig. 2 a, details are not described herein again.
Fig. 4 is referred to, Fig. 4 is another image processing apparatus 4 (hereinafter referred to as device 4) provided in an embodiment of the present invention,
The device 4 may include processor 401 and memory 402.
Memory 402 can be independent physical unit, can be connect by bus with processor 401.Memory 402,
Processor 401 also can integrate together, pass through hardware realization etc..
Memory 402 is used to store the program for realizing above method embodiment or Installation practice modules, processing
Device 401 calls the program, executes the operation of above method embodiment.
Optionally, when passing through software realization some or all of in the image processing method of above-described embodiment, device
Processor can be only included.Memory for storing program is located at except device, and processor passes through circuit/electric wire and memory
Connection, for reading and executing the program stored in memory.
Processor 401 can be central processing unit (central processing unit, CPU), network processing unit
The combination of (network processor, NP) or CPU and NP.
Processor 402 can further include hardware chip.Above-mentioned hardware chip can be specific integrated circuit
(application-specific integrated circuit, ASIC), programmable logic device (programmable
Logic device, PLD) or combinations thereof.Above-mentioned PLD can be Complex Programmable Logic Devices (complex
Programmable logic device, CPLD), field programmable gate array (field-programmable gate
Array, FPGA), Universal Array Logic (generic array logic, GAL) or any combination thereof.
Memory may include volatile memory (volatile memory), such as random access memory
(random-access memory, RAM)；Memory also may include nonvolatile memory (non-volatile
), such as flash memory (flash memory), hard disk (hard disk drive, HDD) or solid state hard disk memory
(solid-state drive, SSD)；Memory can also include the combination of the memory of mentioned kind.
The embodiment of the present application also provides a kind of computer storage mediums, are stored with computer program, the computer program
For executing image processing method provided by the above embodiment.
The embodiment of the present application also provides a kind of computer program products comprising instruction, when it runs on computers
When, so that computer executes image processing method provided by the above embodiment.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When implemented in software, it can entirely or partly realize in the form of a computer program product.The computer program
Product includes one or more computer instructions.When loading on computers and executing the computer program instructions, all or
It partly generates according to process or function described in the embodiment of the present invention.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or transmitted by the computer readable storage medium.The computer instruction can be from a web-site, meter
Calculation machine, server or data center are (such as red by wired (such as coaxial cable, optical fiber, Digital Subscriber Line (DSL)) or wireless
Outside, wirelessly, microwave etc.) mode transmitted to another web-site, computer, server or data center.The calculating
Machine readable storage medium storing program for executing can be any usable medium or include one or more usable mediums that computer can access
The data storage devices such as integrated server, data center.The usable medium can be magnetic medium, (for example, floppy disk, hard
Disk, tape), optical medium (for example, DVD) or semiconductor medium (such as solid state hard disk Solid State Disk (SSD))
Deng ".
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, the process
Relevant hardware can be instructed to complete by computer program, which can be stored in computer-readable storage medium, should
Program is when being executed, it may include such as the process of above-mentioned each method embodiment.And storage medium above-mentioned includes: ROM or deposits at random
Store up the medium of the various program storage codes such as memory body RAM, magnetic or disk.
Claims (12)
1. a kind of image processing method characterized by comprising
Determine the average brightness of image to be processed；
In the case where the average brightness is located at luminance threshold section, the Texture complication of the image to be processed is calculated；
In the case where the Texture complication is less than Texture complication threshold value, according to the skin color detection algorithm of fixed threshold to institute
Image to be processed is stated to be handled to obtain bianry image.
2. the method according to claim 1, wherein further include:
In the case where the average brightness is not located at luminance threshold section, according to the skin color detection algorithm of dynamic threshold to described
Image to be processed is handled to obtain bianry image.
3. the method according to claim 1, wherein further include:
In the case where the Texture complication is not less than Texture complication threshold value, according to the skin color detection algorithm pair of dynamic threshold
The image to be processed is handled to obtain bianry image.
4. according to claim 1 to method described in 3 any one, which is characterized in that further include:
The bianry image is divided into M × N number of rectangular area of M row N column；M and N is the integer greater than 1；
Erroneous detection analysis and missing inspection analysis are carried out according to the distributing position in hand shape region in the M × N number of rectangular area.
5. according to the method described in claim 4, it is characterized in that,
The M × N number of rectangular area number is
In the case where detecting that number is 11,4 rectangular areas of 1N, M1 and MN are hand shape region, current inspection is determined
Surveying result, there are erroneous detections；Or
In the case where detecting that number is 11 and 2 regions of MN are hand shape region, determine that current testing result exists
Erroneous detection；Or；
In the case where detecting that number is 1N and 2 rectangular areas of M1 are hand shape region, current testing result is determined
There are erroneous detections；Or
In the case where outermost one layer of 2M+2N-4 rectangular area is hand shape region, determine that current testing result exists
Erroneous detection.
6. method described in -5 any one according to claim 1, which is characterized in that being averaged for the determination image to be processed is bright
Before degree, further includes:
Determine the Texture complication of multiple background images；
It determines in the average value of the Texture complication of multiple background images and the Texture complication of the multiple background image
Maximum value；Wherein, the Texture complication threshold value is between the average value and the maximum value.
7. a kind of image processing apparatus characterized by comprising
Determination unit, for determining the average brightness of image to be processed；
Computing unit, user calculate the image to be processed in the case where the average brightness is located at luminance threshold section
Texture complication；
Detection unit is used in the case where the Texture complication is less than Texture complication threshold value, according to the skin of fixed threshold
Color detection algorithm is handled to obtain bianry image to the image to be processed.
8. device according to claim 7, which is characterized in that
The detection unit is also used in the case where the average brightness is not located at luminance threshold section, according to dynamic threshold
Skin color detection algorithm the image to be processed is handled to obtain bianry image.
9. device according to claim 7, which is characterized in that
The detection unit is also used in the case where the Texture complication is not less than Texture complication threshold value, according to dynamic
The skin color detection algorithm of threshold value is handled to obtain bianry image to the image to be processed.
10. according to device described in claim 7 to 9 any one, which is characterized in that further include:
Analytical unit, for the bianry image to be divided into M × N number of rectangular area of M row N column；M and N is whole greater than 1
Number；
Erroneous detection analysis and missing inspection analysis are carried out according to the distributing position in hand shape region in the M × N number of rectangular area.
11. according to the method described in claim 10, it is characterized in that,
The M × N number of rectangular area number is
In the case where detecting that number is 11,4 rectangular areas of 1N, M1 and MN are hand shape region, current inspection is determined
Surveying result, there are erroneous detections；Or
In the case where detecting that number is 11 and 2 regions of MN are hand shape region, determine that current testing result exists
Erroneous detection；Or；
In the case where detecting that number is 1N and 2 rectangular areas of M1 are hand shape region, current testing result is determined
There are erroneous detections；Or
In the case where outermost one layer of 2M+2N-4 rectangular area is hand shape region, determine that current testing result exists
Erroneous detection.
12. according to device described in claim 7-11 any one, which is characterized in that further include:
Threshold setting unit, for determining the Texture complication of multiple background images；Determine that the texture of multiple background images is complicated
Maximum value in the Texture complication of the average value of degree and the multiple background image；Wherein, the Texture complication threshold value
Between the average value and the maximum value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711454207.6A CN109977734B (en) | 2017-12-28 | 2017-12-28 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711454207.6A CN109977734B (en) | 2017-12-28 | 2017-12-28 | Image processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109977734A true CN109977734A (en) | 2019-07-05 |
| CN109977734B CN109977734B (en) | 2023-06-06 |
Family
ID=67074083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711454207.6A Active CN109977734B (en) | 2017-12-28 | 2017-12-28 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109977734B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7265873B1 (en) * | 1999-04-13 | 2007-09-04 | Conexant Systems, Inc. | Image processor that performs edge enhancement using a dynamic threshold |
| CN103106386A (en) * | 2011-11-10 | 2013-05-15 | 华为技术有限公司 | Dynamic self-adaption skin color segmentation method and device |
| CN103745193A (en) * | 2013-12-17 | 2014-04-23 | 小米科技有限责任公司 | Skin color detection method and skin color detection device |
| CN104167006A (en) * | 2014-07-10 | 2014-11-26 | 华南理工大学 | Gesture tracking method of any hand shape |
| CN106485222A (en) * | 2016-10-10 | 2017-03-08 | 上海电机学院 | A kind of method for detecting human face being layered based on the colour of skin |
| WO2017092431A1 (en) * | 2015-12-01 | 2017-06-08 | 乐视控股（北京）有限公司 | Human hand detection method and device based on skin colour |
| CN107491718A (en) * | 2016-06-13 | 2017-12-19 | 南京亿猫信息技术有限公司 | The method that human hand Face Detection is carried out under different lightness environment |
-
2017
- 2017-12-28 CN CN201711454207.6A patent/CN109977734B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7265873B1 (en) * | 1999-04-13 | 2007-09-04 | Conexant Systems, Inc. | Image processor that performs edge enhancement using a dynamic threshold |
| CN103106386A (en) * | 2011-11-10 | 2013-05-15 | 华为技术有限公司 | Dynamic self-adaption skin color segmentation method and device |
| CN103745193A (en) * | 2013-12-17 | 2014-04-23 | 小米科技有限责任公司 | Skin color detection method and skin color detection device |
| CN104167006A (en) * | 2014-07-10 | 2014-11-26 | 华南理工大学 | Gesture tracking method of any hand shape |
| WO2017092431A1 (en) * | 2015-12-01 | 2017-06-08 | 乐视控股（北京）有限公司 | Human hand detection method and device based on skin colour |
| CN107491718A (en) * | 2016-06-13 | 2017-12-19 | 南京亿猫信息技术有限公司 | The method that human hand Face Detection is carried out under different lightness environment |
| CN106485222A (en) * | 2016-10-10 | 2017-03-08 | 上海电机学院 | A kind of method for detecting human face being layered based on the colour of skin |
Non-Patent Citations (1)
| Title |
|---|
| 朱金秀等: "基于纹理复杂度的快速帧内预测算法" * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109977734B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110544258B (en) | Image segmentation method and device, electronic equipment and storage medium | |
| WO2017092431A1 (en) | Human hand detection method and device based on skin colour | |
| CN106067177B (en) | HDR scene detection method and device | |
| CN112241714B (en) | Method and device for identifying designated area in image, readable medium and electronic equipment | |
| JP2012243313A (en) | Image processing method and image processing device | |
| CN109409377B (en) | Method and device for detecting characters in image | |
| CN116188808B (en) | Image feature extraction method and system, storage medium and electronic device | |
| CN111144337B (en) | Fire detection method and device and terminal equipment | |
| CN109753945B (en) | Target subject identification method and device, storage medium and electronic equipment | |
| CN111935479B (en) | Target image determination method and device, computer equipment and storage medium | |
| CN110930296A (en) | Image processing method, device, equipment and storage medium | |
| EP2709063A1 (en) | Image processing device, computer-readable recording medium, and image processing method | |
| CN109190617A (en) | A kind of rectangle detection method of image, device and storage medium | |
| JP7429756B2 (en) | Image processing method, device, electronic device, storage medium and computer program | |
| CN111783803A (en) | Image processing method and device for realizing privacy protection | |
| Vogt | Quantifying landscape fragmentation | |
| KR20130052418A (en) | Display analyzing apparatus using dominant color and method for controlling thereof | |
| CN106599889A (en) | Method and apparatus for recognizing characters | |
| CN109977734A (en) | Image processing method and device | |
| JP2012003358A (en) | Background determination device, method, and program | |
| CN111292247A (en) | Image processing method and device | |
| CN109598276A (en) | Image processing apparatus and method and monitoring system | |
| CN114359166A (en) | Screen color detection method, device, equipment and storage medium | |
| CN112967321A (en) | Moving object detection method and device, terminal equipment and storage medium | |
| CN109117035B (en) | Method for hiding floating icon, terminal recovery system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |