CN111723804A - Image-text separation device, image-text separation method, and computer-readable recording medium - Google Patents
Image-text separation device, image-text separation method, and computer-readable recording medium Download PDFInfo
- Publication number
- CN111723804A CN111723804A CN201910202937.XA CN201910202937A CN111723804A CN 111723804 A CN111723804 A CN 111723804A CN 201910202937 A CN201910202937 A CN 201910202937A CN 111723804 A CN111723804 A CN 111723804A
- Authority
- CN
- China
- Prior art keywords
- image
- complexity
- block
- image block
- picture
- 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
- 238000000926 separation method Methods 0.000 title claims abstract description 64
- 238000000605 extraction Methods 0.000 claims abstract description 38
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 19
- 230000000903 blocking effect Effects 0.000 claims abstract description 14
- 238000001914 filtration Methods 0.000 claims description 17
- 238000007781 pre-processing Methods 0.000 claims description 15
- 239000000284 extract Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000000638 solvent extraction Methods 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 10
- 238000000034 method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 239000000470 constituent Substances 0.000 description 1
Images
Classifications
-
- 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
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a picture-text separation device, a picture-text separation method and a computer readable recording medium, which are used for separating picture and text by taking a halftone image as an image to be separated, and the picture-text separation device comprises: a blocking part for dividing the image to be separated into a plurality of image blocks; a gray complexity analyzing part which analyzes each image block in sequence based on a mean difference algorithm to obtain the gray complexity of each image block; a first determination unit that determines an image block corresponding to a gradation complexity greater than a complexity threshold as a picture block constituting a picture area, and determines an image block corresponding to a gradation complexity not greater than the complexity threshold as a character block constituting a character area; an overall contour extraction unit for obtaining an image contour of an image to be separated; and a second determination unit which sequentially determines whether or not the image blocks through which the respective image profiles pass include a picture block, and determines all the image blocks through which the image profiles pass as picture blocks when the image blocks through which the image profiles pass include a picture block.
Description
Technical Field
The invention belongs to the technical field of image-text separation, and particularly relates to an image-text separation device, an image-text separation method and a computer readable recording medium.
Background
Halftone images are used to simulate the color and shade variation of continuous tone images by changing the size or density of multiple pixels. When performing image-text separation on a halftone image, different halftone generation algorithms may generate different pixel distribution patterns because the distribution of pixel points of the halftone image is related to the halftone generation algorithm, and therefore, the halftone image cannot be image-text separated only by extracting the color and shape features of the pixels of the halftone image.
Generally, the separation of the image and text of the halftone image is performed based on cross algorithm, which specifically includes: dividing the halftone image into a plurality of image blocks, then carrying out binarization on each image block, then comparing the gray change quantity of each image block in the horizontal and vertical directions, and judging the image block with large gray change quantity as an image block, and using the image block with small gray change quantity as a character block. However, when the halftone image contains the character-shaped pattern, the character-shaped pattern is also low in grayscale variation and is easily mistakenly determined as a character region, which causes inaccurate image-text separation, thereby affecting subsequent image processing and analysis processes.
Disclosure of Invention
The present invention has been made to solve the above-described problems, and an object of the present invention is to provide an image-text separation device, an image-text separation method, and a computer-readable recording medium that can perform image-text separation on a relatively complex halftone image subjected to image-text mixed layout.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a picture-text separation device, which is used for separating picture and text of a halftone image containing picture content and text content as an image to be separated so as to obtain a picture area corresponding to the picture content and a text area corresponding to the text content in the halftone image, and is characterized by comprising the following steps: a blocking part for dividing the image to be separated into a plurality of image blocks; a gray complexity analyzing part which analyzes each image block in sequence based on a mean difference algorithm to obtain the gray complexity of each image block; a first determination unit that determines, based on the gradation complexity of the image block and a predetermined complexity threshold, an image block corresponding to a gradation complexity greater than the complexity threshold as a picture block constituting a picture region, and determines an image block corresponding to a gradation complexity not greater than the complexity threshold as a character block constituting a character region; the overall contour extraction part is used for extracting the overall contour of the image to be separated to obtain the image contour of the image to be separated; and a second determination unit which sequentially determines whether or not the image blocks through which the respective image profiles pass include a picture block, and determines all the image blocks through which the image profiles pass as picture blocks when the image blocks through which the image profiles pass include a picture block.
The invention also provides an image-text separation method, which is used for performing image-text separation on a halftone image containing image contents and text contents as an image to be separated so as to obtain an image area corresponding to the image contents and a text area corresponding to the text contents in the halftone image, and is characterized by comprising the following steps of: a blocking step, namely dividing an image to be separated into a plurality of image blocks; a gray level complexity analyzing step, namely analyzing each image block in sequence based on a mean difference algorithm to obtain the gray level complexity of each image block; a first determination step of determining, based on the grayscale complexity of the image block and a predetermined complexity threshold, an image block corresponding to the grayscale complexity greater than the complexity threshold as a picture block constituting a picture region, and determining an image block corresponding to the grayscale complexity not greater than the complexity threshold as a character block constituting a character region; an overall contour extraction step, namely performing overall contour extraction on the image to be separated to obtain the image contour of the image to be separated; and a second determination step of sequentially determining whether the image blocks through which the image profiles pass contain image blocks, and determining all the image blocks through which the image profiles pass as image blocks once the image blocks through which the image profiles pass contain image blocks.
The invention also provides a computer-readable recording medium for recording a computer program, which is characterized in that the computer program is used for separating the image and text of a halftone image containing picture content and text content as an image to be separated, so as to obtain a picture area corresponding to the picture content and a text area corresponding to the text content in the halftone image. The image-text separation device executes the following steps: a blocking step, namely dividing an image to be separated into a plurality of image blocks; a gray level complexity analyzing step, namely analyzing each image block in sequence based on a mean difference algorithm to obtain the gray level complexity of each image block; a first determination step of determining, based on the grayscale complexity of the image block and a predetermined complexity threshold, an image block corresponding to the grayscale complexity greater than the complexity threshold as a picture block constituting a picture region, and determining an image block corresponding to the grayscale complexity not greater than the complexity threshold as a character block constituting a character region; an overall contour extraction step, namely performing overall contour extraction on the image to be separated to obtain the image contour of the image to be separated; and a second determination step of sequentially determining whether the image blocks through which the image profiles pass contain image blocks, and determining all the image blocks through which the image profiles pass as image blocks once the image blocks through which the image profiles pass contain image blocks.
Action and Effect of the invention
According to the image-text separation device, the image-text separation method, and the computer-readable recording medium of the present invention, since the blocking section divides the halftone image into a plurality of image blocks, the grayscale complexity analysis section sequentially analyzes each image block based on the mean difference algorithm to obtain the grayscale complexity of each image block, the first determination section determines an image block corresponding to a grayscale complexity greater than the complexity threshold as an image block, and determines an image block corresponding to a grayscale complexity not greater than the complexity threshold as a text block, thereby preliminarily determining the attribute of each image block. Further, the whole contour extraction unit extracts the image contour of the obtained halftone image, the second determination unit sequentially determines whether or not image blocks through which the respective image contours pass include a picture block, and determines all image blocks through which the image contours pass as picture blocks when the image blocks through which the image contours pass include a picture block, so that the first determination unit erroneously determines an image block (for example, an image block constituting a character-shaped figure) as a character block, and thus the determination result can be more accurate, and the subsequent image processing and analysis processes can be smoothly performed.
Drawings
Fig. 1 is a block diagram showing the structure of an image-text separating apparatus according to an embodiment of the present invention;
FIG. 2 is an exemplary diagram of a halftone image in an embodiment of the invention;
FIG. 3 is an exemplary diagram of all image blocks constituting an image to be separated after binarization processing in the embodiment of the present invention;
FIG. 4 is a diagram illustrating an example of a determination result after a halftone image is determined by a first determination section according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating an example of a determination result of a halftone image determined by the second determination unit according to an embodiment of the present invention; and
fig. 6 is a flowchart of the teletext separation operation of the teletext separator arrangement in an embodiment of the invention.
Detailed Description
In order to make the technical means, the creation features, the achievement objects and the effects of the invention easy to understand, the text separation device of the invention is specifically described below with reference to the embodiments and the accompanying drawings.
As a first aspect, the present invention provides a text-text separation apparatus for performing text-text separation on a halftone image including picture content and text content as an image to be separated to obtain a picture region corresponding to the picture content and a text region corresponding to the text content in the halftone image, the apparatus comprising: a blocking part for dividing the image to be separated into a plurality of image blocks; a gray complexity analyzing part for sequentially analyzing each image block to obtain the gray complexity of each image block; a first determination unit that determines, based on the gradation complexity of the image block and a predetermined complexity threshold, an image block corresponding to a gradation complexity greater than the complexity threshold as a picture block constituting a picture region, and determines an image block corresponding to a gradation complexity not greater than the complexity threshold as a character block constituting a character region; the overall contour extraction part is used for extracting the overall contour of the image to be separated to obtain the image contour of the image to be separated; and a second determination unit which sequentially determines whether or not the image blocks through which the respective image profiles pass include a picture block, and determines all the image blocks through which the image profiles pass as picture blocks when the image blocks through which the image profiles pass include a picture block.
In addition, the separation device for teletext according to the first embodiment may further have the following features: further comprising: and the preprocessing part is used for preprocessing the halftone image and taking the preprocessed halftone image as an image to be separated, wherein the preprocessing is mean filtering processing.
In addition, the separation device for teletext according to the first embodiment may further have the following features: and an output unit and a control unit, wherein the control unit controls the output unit to output, as a result of the separation, region information of a picture region formed by the plurality of picture blocks and region information of a character region formed by the plurality of character blocks.
In addition, the separation device for teletext according to the first embodiment may further have the following features: the overall contour extraction unit comprises an overall binarization unit and an overall contour identification unit, the overall binarization unit conducts binarization processing on the image to be separated to obtain a binarized image, and the overall contour identification unit conducts overall contour identification on the binarized image to obtain the image contour of the image to be separated.
In addition, the separation device for teletext according to the first embodiment may further have the following features: wherein the gray complexity analyzing section has an image block binarizing unit, an image block contour extracting unit, an image block mean filtering unit, and a gray complexity calculating unit, the image block binarization unit sequentially performs binarization processing on each image block to obtain a plurality of binarized image blocks, the image block outline extraction unit sequentially extracts the image block outlines of the binarization image blocks to obtain a plurality of binarization image block outlines, the image block mean filtering unit sequentially performs mean filtering processing on each binarized image block to obtain a plurality of processed image blocks, the image block contour extraction unit sequentially extracts image block contours of the processed image blocks to obtain a plurality of processed image block contours, and the gray complexity calculation unit calculates gray levels of the image blocks according to gray values of pixel points on the binarized image block contours of the image blocks and gray values of pixel points on the processed image block contours.
In addition, the separation device for teletext according to the first embodiment may further have the following features: the gray complexity calculating unit calculates the gray complexity of each image block based on a mean difference algorithm, wherein the mean difference algorithm is as follows: and sequentially calculating the absolute value of the difference between the gray value of each pixel point on the binary image block outline of the image block and the gray value of the pixel point on the processed image block outline, and then calculating to obtain the sum of the absolute values of the differences to serve as the gray complexity of the image block.
As a second embodiment, the present invention further provides an image-text separation method for performing image-text separation on a halftone image containing picture content and text content as an image to be separated, so as to obtain a picture region corresponding to the picture content and a text region corresponding to the text content in the halftone image, the method comprising: a blocking step, namely dividing an image to be separated into a plurality of image blocks; a gray complexity analyzing step, namely analyzing each image block in sequence to obtain the gray complexity of each image block; a first determination step of determining, based on the grayscale complexity of the image block and a predetermined complexity threshold, an image block corresponding to the grayscale complexity greater than the complexity threshold as a picture block constituting a picture region, and determining an image block corresponding to the grayscale complexity not greater than the complexity threshold as a character block constituting a character region; an overall contour extraction step, namely performing overall contour extraction on the image to be separated to obtain the image contour of the image to be separated; and a second determination step of sequentially determining whether the image blocks through which the image profiles pass contain image blocks, and determining all the image blocks through which the image profiles pass as image blocks once the image blocks through which the image profiles pass contain image blocks.
As a third aspect, the present invention provides a computer-readable recording medium for recording a computer program, wherein the computer program is configured to perform text-text separation on a halftone image including picture content and text content as an image to be separated, thereby obtaining a picture area corresponding to the picture content and a text area corresponding to the text content in the halftone image. The image-text separation device executes the following steps: a blocking step, namely dividing an image to be separated into a plurality of image blocks; a gray complexity analyzing step, namely analyzing each image block in sequence to obtain the gray complexity of each image block; a first determination step of determining, based on the grayscale complexity of the image block and a predetermined complexity threshold, an image block corresponding to the grayscale complexity greater than the complexity threshold as a picture block constituting a picture region, and determining an image block corresponding to the grayscale complexity not greater than the complexity threshold as a character block constituting a character region; an overall contour extraction step, namely performing overall contour extraction on the image to be separated to obtain the image contour of the image to be separated; and a second determination step of sequentially determining whether the image blocks through which the image profiles pass contain image blocks, and determining all the image blocks through which the image profiles pass as image blocks once the image blocks through which the image profiles pass contain image blocks.
< example >
Fig. 1 is a block diagram of a separation apparatus for separating text and graphics in an embodiment of the present invention.
As shown in fig. 1, the teletext separator 100 according to the present embodiment is a computer on which a computer program for executing a teletext separation method is installed, and is configured to perform teletext separation on a halftone image to obtain a picture region corresponding to picture content and a character region corresponding to character content, and includes a preprocessing unit 10, a blocking unit 20, a grayscale complexity analysis unit 30, a first determination unit 40, an overall contour extraction unit 50, a second determination unit 60, an output unit 70, a communication unit 80, and a control unit 90.
FIG. 2 is an exemplary diagram of a halftone image in an embodiment of the invention.
As shown in fig. 2, the halftone image is generated from a continuous tone image by a halftone generation algorithm, and includes a text region and a picture region. In fig. 2, the left part is a text area and the right part is a picture area. In the text area, the text content is superposed on the picture background; the picture area has a background and a pattern, and the pattern contains a figure in the shape of a character.
The preprocessing section 10 is for preprocessing the halftone image and treating the preprocessed halftone image as an image to be separated. The preprocessing is mean filtering processing and is used for making up holes in character areas in the halftone image and reducing particle noise of the halftone image.
The blocking section 20 is used to divide the image to be separated into a plurality of fixed-size image blocks.
The gray complexity analyzing unit 30 is configured to sequentially analyze each image block based on a mean difference algorithm to obtain the gray complexity of each image block, and includes an image block binarizing unit 31, an image block mean filtering unit 32, an image block contour extracting unit 33, and a gray complexity calculating unit 34.
The image block binarization unit 31 is configured to sequentially perform binarization processing on each image block to obtain a plurality of binarized image blocks. The specific process of obtaining the binary image block comprises the following steps: and calculating the average value of the gray values of the image block, taking the average value as a binarization threshold value of the image block, and performing binarization processing on the image block according to the binarization threshold value to obtain a binarization image block.
The image block mean filtering unit 32 is configured to perform mean filtering processing on each binarized image block in sequence to obtain a plurality of processed image blocks.
The image block contour extraction unit 33 is configured to perform image block contour extraction on the binarized image block or the processed image block to obtain a corresponding binarized image block contour or a processed image block contour, and specifically includes: sequentially extracting the image block outline of each binarization image block to obtain a plurality of binarization image block outlines; and sequentially extracting the image block contour of each processed image block to obtain a plurality of processed image block contours. Each processed image block outline is formed by pixel points at the boundary of the black and white pixels of the processed image block outline.
The gray level complexity calculating unit 34 is configured to calculate, based on a mean difference algorithm, according to the gray level values of the pixels on the binarized image block contour of each image block and the gray level values of the pixels on the processed image block contour, so as to obtain the gray level complexity of each image block.
Wherein, the mean difference algorithm is as follows: and sequentially calculating the absolute value of the difference between the gray value of each pixel point on the binary image block outline of the image block and the gray value of the pixel point on the processed image block outline, and then calculating to obtain the sum of the absolute values of the differences to serve as the gray complexity of the image block.
Fig. 3 is an exemplary diagram of all image blocks constituting an image to be separated after binarization processing in the embodiment of the present invention.
In fig. 3, (a) part represents each binarized image block, (b) part represents a plurality of binarized image blocks in a character area, and (c) part represents a plurality of binarized image blocks in a character-shaped figure. As can be seen from fig. 3, the gray scale complexity of the binarized image block in the text area is obviously inconsistent with the gray scale complexity of the binarized image block in the background; meanwhile, the gray scale complexity of the binary image block in the character-shaped graph is closer to that of the binary image block in the character area.
The first determination unit 40 is configured to determine each image block as a picture block or a character block based on the grayscale complexity of the image block and a predetermined complexity threshold.
The picture block is an image block having an attribute of a picture (corresponding to a picture area), and the character block is an image block having an attribute of a character (corresponding to a character area). The first determination unit 40 has the following determination principle: the image block outline of the image block constituting the picture area is less smooth and longer than the image block outline of the image block constituting the character area, and thus the gradation complexity is greater. Based on this principle, the first determination unit 40 determines an image block corresponding to a gradation complexity greater than the complexity threshold as a picture block constituting a picture area, and determines an image block corresponding to a gradation complexity not greater than the complexity threshold as a character block constituting a character area.
Fig. 4 is an exemplary diagram of a determination result after the halftone image is determined by the first determination section in the embodiment of the present invention. In fig. 4, (a) is a schematic view of the entire result of the halftone image determined by the first determination section 40 in the present embodiment, (b) is a partial enlarged view of a character region in the halftone image, and (c) is a partial enlarged view of a figure of a character shape in the halftone image.
As shown in fig. 4, the image block determined as the text block by the first determination unit 40 and the image block determined as the picture block are shown in different colors. As can be seen from fig. 4, after each image block is determined by the first determination unit, the image block constituting the character area is determined as a character block. Meanwhile, since the grayscale complexity of the binarized image block in the character-shaped figure is closer to the grayscale complexity of the binarized image block in the character region, a part of the image blocks constituting the character-shaped figure is erroneously determined as a character block.
The overall contour extraction section 50 is used for performing overall contour extraction on an image to be separated to obtain an image contour of the image to be separated, and includes an overall binarization unit 51 and an overall contour identification unit 52.
The overall binarization unit 51 is configured to perform binarization processing on the image to be separated by using an average value of the gray values of the image to be separated as a binarization threshold, so as to obtain a binarized image.
The overall contour identification unit 52 is configured to perform overall contour identification on the binarized image to obtain an image contour of the image to be separated, where the image contour is formed by pixel points at the boundary of black and white pixel points of the binarized image (i.e., a white line in fig. 4).
The second determination unit 60 is configured to sequentially determine whether or not each image block having an image contour includes a picture block, and determine, when a picture block is included in an image block having an image contour, all image blocks having the image contour, so as to obtain a picture area including the image blocks and a character area including the character blocks.
Fig. 5 is an exemplary diagram of a determination result of the halftone image determined by the second determination unit according to the embodiment of the present invention. In fig. 5, (a) is a schematic view of the entire result of the halftone image determined by the second determination unit in the present embodiment, (b) is a partial enlarged view of a character region of the halftone image, and (c) is a partial enlarged view of a figure of a character shape of the halftone image. In fig. 5, the white line is the image contour extracted by the entire contour extraction unit 50.
As can be seen from fig. 4(c), the image block determined as the image block by the first determination unit 40 is included in the image block where the image contour in the character-shaped figure passes.
As can be seen from fig. 5(c), the second determination unit 60 determines all image blocks through which the image contour in the character-shaped figure passes as image blocks.
The output unit 70 is configured to output, after the second determination unit 60 completes the determination operation, the area information (e.g., information such as corresponding area position coordinates and size) of the picture area formed by the plurality of picture blocks and the area information of the character area formed by the plurality of character blocks as a result of image-text separation to a subsequent image processing program, so that the image processing program performs further processing, such as character recognition and image-text comparison of the halftone image.
The communication unit 80 exchanges data information between the respective components of the teletext separator 100.
The control section 90 controls the operations of the respective constituent parts of the teletext separator arrangement 100.
The operation of the separation device 100 of the present embodiment will be described with reference to the drawings.
The image-text separation apparatus 100 of this embodiment, after preprocessing a halftone image and taking the preprocessed halftone image as an image to be separated, divides the image to be separated into a plurality of image blocks, sequentially calculates the grayscale complexity of each image block, first determines the attribute of each image block by determining whether the grayscale complexity of each image block is greater than a complexity threshold, determines whether each image block having a passing image contour contains an image block according to the image contour of the image to be separated, and determines all the image blocks having the passing image contour as image blocks when the image blocks having the passing image contour contain image blocks.
Fig. 6 is a flowchart of the teletext separation operation of the teletext separator arrangement in an embodiment of the invention.
As shown in fig. 6, in the present embodiment, the flow of the teletext separation operation of teletext separation arrangement 100 includes the following steps:
in step S1, the preprocessing section 10 preprocesses the halftone image and regards the preprocessed halftone image as an image to be separated, and then proceeds to step S2.
In step S2, the blocking section 20 divides the image to be separated into a plurality of image blocks, and then proceeds to step S3.
In step S3, the image block binarizing unit 31 sequentially performs binarization processing on each image block to obtain a plurality of binarized image blocks, and then proceeds to step S4.
In step S4, the image block contour extraction unit 33 sequentially performs image block contour extraction on each binarized image block to obtain a plurality of binarized image block contours, and then proceeds to step S5.
In step S5, the image block mean value filtering unit 32 sequentially performs mean value filtering on each binarized image block to obtain a plurality of processed image blocks, and then proceeds to step S6.
In step S6, the image block contour extraction unit 33 sequentially performs image block contour extraction on each processed image block to obtain a plurality of processed image block contours, and then proceeds to step S7.
In step S7, the gray complexity calculating unit 34 calculates the gray complexity of each image block according to the gray value of the pixel point on the binarized image block contour of each image block and the gray value of the pixel point on the processed image block contour based on the mean difference algorithm, and then proceeds to step S8.
In step S8, the first determination unit 40 determines an image block corresponding to a gradation complexity greater than the complexity threshold as a picture block constituting a picture region and determines an image block corresponding to a gradation complexity not greater than the complexity threshold as a character block constituting a character region based on the gradation complexity of the image block and a predetermined complexity threshold, and then proceeds to step S9.
In step S9, the entire binarization unit 51 performs binarization processing on the image to be separated to obtain a binarized image, and then proceeds to step S10.
In step S10, the entire contour recognition unit 52 performs entire contour recognition on the binarized image to obtain an image contour of the image to be separated, and then proceeds to step S11.
In step S11, the second determination unit 60 sequentially determines whether or not each image block through which the image contour passes includes a picture block, determines all image blocks through which the image contour passes as picture blocks when the image block through which the image contour passes includes a picture block, and then proceeds to step S12.
In step S12, the output unit 70 outputs the area information of the picture area formed by the plurality of picture blocks and the area information of the character area formed by the plurality of character blocks as the result of the separation of the text and the text, and enters the end state.
Effects and effects of the embodiments
According to the image-text separation device, the image-text separation method, and the computer-readable recording medium of the present embodiment, since the blocking section divides the halftone image into a plurality of image blocks, the grayscale complexity analysis section sequentially analyzes each image block based on the mean difference algorithm to obtain the grayscale complexity of each image block, the first determination section determines an image block corresponding to a grayscale complexity greater than the complexity threshold as an image block, and determines an image block corresponding to a grayscale complexity not greater than the complexity threshold as a text block, thereby preliminarily determining the attribute of each image block. Further, the whole contour extraction unit extracts the image contour of the obtained halftone image, the second determination unit sequentially determines whether or not image blocks through which the respective image contours pass include a picture block, and determines all image blocks through which the image contours pass as picture blocks when the image blocks through which the image contours pass include a picture block, so that the first determination unit erroneously determines an image block (for example, an image block constituting a character-shaped figure) as a character block, and thus the determination result can be more accurate, and the subsequent image processing and analysis processes can be smoothly performed.
In addition, the preprocessing part can carry out mean value filtering preprocessing on the halftone image and take the preprocessed halftone image as an image to be separated, so that the holes of a character area in the halftone image are made up, the particle noise of the halftone image is reduced, and the image-text separation result of the embodiment is more accurate.
Further, the output unit outputs the area information of the picture area formed by the plurality of picture blocks, the area information of the character area formed by the plurality of character blocks, and the halftone image, so that the subsequent teletext processing program can receive and perform the teletext processing operation.
In addition, the integral binarization unit is used for carrying out binarization processing on the image to be separated to obtain a binarized image, the integral contour identification unit is used for carrying out integral contour identification on the binarized image to obtain the image contour of the image to be separated, and then the second judgment part is used for judging whether the image block through which each image contour passes contains a picture block or not according to the image contour and finishing the judgment action.
Further, since the image block binarizing unit sequentially binarizes each image block to obtain a plurality of binarized image blocks, the image block outline extraction unit sequentially extracts the image block outlines of the binarization image blocks to obtain a plurality of binarization image block outlines, the image block mean filtering unit sequentially performs mean filtering processing on each binarized image block to obtain a plurality of processed image blocks, the image block outline extraction unit sequentially extracts the image block outlines of the processed image blocks to obtain a plurality of processed image block outlines, the gray level complexity calculation unit is based on a mean difference algorithm, the gray level complexity of each image block can be obtained by calculating according to the gray level value of the pixel point on the binarization image block outline of each image block and the gray level value of the pixel point on the processed image block outline, thereby, the attribute of each image block can be judged by comparing the gray scale complexity of each image block with the complexity threshold.
The above embodiments are preferred examples of the present invention, and are not intended to limit the scope of the present invention.
For example, in the above-described embodiment, the image separating apparatus performs the preprocessing of the halftone image and performs the image-text separation of the preprocessed halftone image as the image to be separated. In other embodiments, if the grain noise of the halftone image is small, the image separation apparatus may directly take the halftone image as the image to be processed and perform image-text separation on the image to be separated.
For example, in the present invention, the output section has a display unit, such as a display, for displaying a halftone image and displaying a text region and a picture region in different colors on the halftone image. In addition, the image outline may also be displayed in a color different from the color in which the two regions are displayed, so as to more clearly display the text content and the picture background in the text region.
Claims (8)
1. An image-text separation device for performing image-text separation on a halftone image containing picture content and text content as an image to be separated so as to obtain a picture area corresponding to the picture content and a text area corresponding to the text content in the halftone image, the device comprising:
the partitioning part is used for partitioning the image to be separated into a plurality of image blocks;
a gray complexity analyzing part which analyzes each image block in sequence to obtain the gray complexity of each image block;
a first determination unit configured to determine, based on a grayscale complexity of the image block and a predetermined complexity threshold, the image block corresponding to the grayscale complexity that is greater than the complexity threshold as a picture block constituting the picture region, and determine the image block corresponding to the grayscale complexity that is not greater than the complexity threshold as a character block constituting the character region;
the overall contour extraction part is used for carrying out overall contour extraction on the image to be separated to obtain the image contour of the image to be separated; and
and a second determination unit configured to sequentially determine whether or not the image block through which the image contour passes includes the image block, and determine, as the image block, all the image blocks through which the image contour passes, once the image block through which the image contour passes includes the image block.
2. The separation apparatus of claim 1, further comprising:
a preprocessing section for preprocessing the halftone image and taking the preprocessed halftone image as the image to be separated,
wherein the preprocessing is mean filtering processing.
3. The separation apparatus of claim 1, further comprising:
an output unit and a control unit, wherein,
wherein, when the second determination unit completes the determination operation, the control unit controls the output unit to output, as a result of the separation, area information of the picture area formed by the plurality of picture blocks and area information of the character area formed by the plurality of character blocks.
4. The separation device of claim 1, wherein:
wherein the whole contour extraction section includes a whole binarization unit and a whole contour identification unit,
the integral binarization unit carries out binarization processing on the image to be separated to obtain a binarized image,
and the overall contour identification unit carries out overall contour identification on the binary image to obtain the image contour of the image to be separated.
5. The separation device of claim 1, wherein:
wherein the gray complexity analyzing section has an image block binarization unit, an image block contour extraction unit, an image block mean value filtering unit, and a gray complexity calculating unit,
the image block binarization unit sequentially performs binarization processing on each image block to obtain a plurality of binarized image blocks,
the image block outline extraction unit sequentially extracts the image block outlines of the binaryzation image blocks to obtain a plurality of binaryzation image block outlines,
the image block mean filtering unit sequentially performs mean filtering processing on each binarized image block to obtain a plurality of processed image blocks,
the image block outline extraction unit sequentially extracts the image block outlines of the processed image blocks to obtain a plurality of processed image block outlines,
and the gray complexity calculating unit calculates to obtain the gray complexity of each image block according to the gray value of the pixel point on the binarization image block outline of each image block and the gray value of the pixel point on the processed image block outline.
6. Teletext separation arrangement according to claim 5, characterized in that:
the gray complexity calculating unit calculates the gray complexity of each image block based on a mean difference algorithm, wherein the mean difference algorithm is as follows: and sequentially calculating the absolute value of the difference between the gray value of each pixel point on the binarized image block outline of the image block and the gray value of the pixel point on the processed image block outline, and then calculating to obtain the sum of the absolute values of the differences as the gray complexity of the image block.
7. An image-text separation method is used for performing image-text separation on a halftone image containing picture contents and text contents as an image to be separated so as to obtain a picture area corresponding to the picture contents and a text area corresponding to the text contents in the halftone image, and is characterized by comprising the following steps of:
a blocking step, namely dividing the image to be separated into a plurality of image blocks;
a gray complexity analyzing step, namely analyzing each image block in sequence to obtain the gray complexity of each image block;
a first determination step of determining, based on a grayscale complexity of the image block and a predetermined complexity threshold, the image block corresponding to the grayscale complexity that is greater than the complexity threshold as a picture block constituting the picture region, and determining the image block corresponding to the grayscale complexity that is not greater than the complexity threshold as a character block constituting the character region;
an overall contour extraction step, namely performing overall contour extraction on the image to be separated to obtain an image contour of the image to be separated; and
and a second determining step of sequentially determining whether the image blocks through which the image profiles pass contain the image blocks, and determining all the image blocks through which the image profiles pass as the image blocks once the image blocks through which the image profiles pass contain the image blocks.
8. A computer-readable recording medium for recording a computer program, wherein the computer program is for causing a text-text separation apparatus that subjects a halftone image including picture content and text content as an image to be separated to text-text separation to obtain a picture region corresponding to the picture content and a text region corresponding to the text content in the halftone image to perform the steps of:
a blocking step, namely dividing the image to be separated into a plurality of image blocks;
a gray complexity analyzing step, namely analyzing each image block in sequence to obtain the gray complexity of each image block;
a first determination step of determining, based on a grayscale complexity of the image block and a predetermined complexity threshold, the image block corresponding to the grayscale complexity that is greater than the complexity threshold as a picture block constituting the picture region, and determining the image block corresponding to the grayscale complexity that is not greater than the complexity threshold as a character block constituting the character region;
an overall contour extraction step, namely performing overall contour extraction on the image to be separated to obtain an image contour of the image to be separated; and
and a second determining step of sequentially determining whether the image blocks through which the image profiles pass contain the image blocks, and determining all the image blocks through which the image profiles pass as the image blocks once the image blocks through which the image profiles pass contain the image blocks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910202937.XA CN111723804B (en) | 2019-03-18 | 2019-03-18 | Image-text separation device, image-text separation method and computer readable recording medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910202937.XA CN111723804B (en) | 2019-03-18 | 2019-03-18 | Image-text separation device, image-text separation method and computer readable recording medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111723804A true CN111723804A (en) | 2020-09-29 |
| CN111723804B CN111723804B (en) | 2024-05-17 |
Family
ID=72562837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910202937.XA Active CN111723804B (en) | 2019-03-18 | 2019-03-18 | Image-text separation device, image-text separation method and computer readable recording medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723804B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63316566A (en) * | 1987-06-19 | 1988-12-23 | Hitachi Ltd | Image input device |
| CN101751121A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | OCR-based wireless scanning input device and method |
| CN101887520A (en) * | 2009-05-12 | 2010-11-17 | 华为终端有限公司 | Method and device for positioning characters in image |
| CN102663337A (en) * | 2012-03-16 | 2012-09-12 | 江南大学 | Method for quick Data Matrix two-dimensional barcode identifying under simple condition background |
| US20140369617A1 (en) * | 2013-06-13 | 2014-12-18 | Canon Kabushiki Kaisha | Image encoding apparatus, image encoding method, and program |
| CN106407919A (en) * | 2016-09-05 | 2017-02-15 | 珠海赛纳打印科技股份有限公司 | Image processing-based text separation method, device and image forming device |
| CN109064479A (en) * | 2018-07-19 | 2018-12-21 | 中国石油大学(华东) | A kind of sea horizon detection method based on neighbouring video frame gray scale behavioral characteristics |
-
2019
- 2019-03-18 CN CN201910202937.XA patent/CN111723804B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS63316566A (en) * | 1987-06-19 | 1988-12-23 | Hitachi Ltd | Image input device |
| CN101751121A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | OCR-based wireless scanning input device and method |
| CN101887520A (en) * | 2009-05-12 | 2010-11-17 | 华为终端有限公司 | Method and device for positioning characters in image |
| CN102663337A (en) * | 2012-03-16 | 2012-09-12 | 江南大学 | Method for quick Data Matrix two-dimensional barcode identifying under simple condition background |
| US20140369617A1 (en) * | 2013-06-13 | 2014-12-18 | Canon Kabushiki Kaisha | Image encoding apparatus, image encoding method, and program |
| CN106407919A (en) * | 2016-09-05 | 2017-02-15 | 珠海赛纳打印科技股份有限公司 | Image processing-based text separation method, device and image forming device |
| CN109064479A (en) * | 2018-07-19 | 2018-12-21 | 中国石油大学(华东) | A kind of sea horizon detection method based on neighbouring video frame gray scale behavioral characteristics |
Non-Patent Citations (2)
| Title |
|---|
| ZHERU CHI ET.AL: "Hierarchical content classi cation and script determination for automatic document image processing", 《PATTERN RECOGNITION》, pages 2484 - 2500 * |
| 朱庆生 等: "彩色扫描文档图像中图文分割算法", 《计算机辅助设计与图形学学报》, vol. 16, no. 4, pages 476 - 480 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111723804B (en) | 2024-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961049B (en) | Cigarette brand identification method under complex scene | |
| US11282185B2 (en) | Information processing device, information processing method, and storage medium | |
| Babu et al. | Vehicle number plate detection and recognition using bounding box method | |
| CN107784301A (en) | Method and apparatus for identifying character area in image | |
| CN115082683A (en) | Injection molding defect detection method based on image processing | |
| CN106650553A (en) | License plate recognition method and system | |
| CN107066972B (en) | Natural scene Method for text detection based on multichannel extremal region | |
| CN110717896A (en) | Plate strip steel surface defect detection method based on saliency label information propagation model | |
| CN104156941A (en) | Method and system for determining geometric outline area on image | |
| CN111461126A (en) | Space recognition method and device in text line, electronic equipment and storage medium | |
| CN114863493A (en) | Detection method and detection device for low-quality fingerprint image and non-fingerprint image | |
| CN114863492A (en) | Method and device for repairing low-quality fingerprint image | |
| Han et al. | An enhanced image binarization method incorporating with Monte-Carlo simulation | |
| CN106780535A (en) | A kind of gray level image processing method | |
| CN114419006A (en) | Method and system for removing watermark of gray level video characters changing along with background | |
| Lin et al. | License plate location method based on edge detection and mathematical morphology | |
| JPH05166002A (en) | Method for analyzing source image | |
| KR101571681B1 (en) | Method for analysing structure of document using homogeneous region | |
| Islami | Implementation of HSV-based Thresholding Method for Iris Detection | |
| CN114399617B (en) | Method, device, equipment and medium for identifying shielding pattern | |
| CN111723804B (en) | Image-text separation device, image-text separation method and computer readable recording medium | |
| CN115393589A (en) | Universal DCS process flow chart identification conversion method, system and medium | |
| CN115359003A (en) | Two-step tunnel gray image crack identification method, system, medium and equipment | |
| CN116563659A (en) | Optical smoke detection method combining priori knowledge and feature classification | |
| CN112801963A (en) | Video image occlusion detection method and system |
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 |