CN105761219B - Text image Slant Rectify method and system - Google Patents
Text image Slant Rectify method and system Download PDFInfo
- Publication number
- CN105761219B CN105761219B CN201610076128.5A CN201610076128A CN105761219B CN 105761219 B CN105761219 B CN 105761219B CN 201610076128 A CN201610076128 A CN 201610076128A CN 105761219 B CN105761219 B CN 105761219B
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- line segment
- corrected
- binary
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012545 processing Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 73
- 238000001914 filtration Methods 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012217 deletion Methods 0.000 claims description 6
- 230000037430 deletion Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 2
- 230000002265 prevention Effects 0.000 claims 2
- 230000009466 transformation Effects 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 abstract description 2
- 238000012937 correction Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 125000000205 L-threonino group Chemical group [H]OC(=O)[C@@]([H])(N([H])[*])[C@](C([H])([H])[H])([H])O[H] 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000003702 image correction Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10008—Still image; Photographic image from scanner, fax or copier
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30176—Document
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
Abstract
The invention discloses a kind of text image Slant Rectify method and systems.Wherein, this method includes obtaining text image to be corrected；Gray processing processing is carried out to the text image to be corrected, obtains gray level image；Binary conversion treatment is carried out to the gray level image, obtains bianry image；By Hough transformation, the straight line in the bianry image is extracted；According to the length and tilt angle of the straight line, the straight line is filtered；For filtered straight line, determine that the median of the tilt angle is the tilt angle of the text image to be corrected；According to the tilt angle of the text image to be corrected, the text image to be corrected is rotated.Solves the technical issues of how being effectively corrected to inclined text image through the embodiment of the present invention.
Description
Technical Field
The embodiment of the invention relates to the technical field of text image processing, in particular to a method and a system for correcting the inclination of a text image.
Background
In the age of digital information, people rely more on the medium of images. Text image analysis is an important branch in image processing, and has important significance in the field of Optical Character Recognition (OCR). The relatively common problem of text image tilting is undoubtedly a great obstacle to image application. The inclination correction of the text image is an important ring of text image analysis, and is an important guarantee step of layout analysis, line cutting, character positioning, sequencing and the like of the text image.
In view of the above, the present invention is particularly proposed.
Disclosure of Invention
A primary object of embodiments of the present invention is to provide a method for correcting a text image tilt, which at least partially solves a technical problem of how to effectively correct a tilted text image. In addition, a text image inclination correction system is also provided.
In order to achieve the above object, according to one aspect of the present invention, the following technical solutions are provided:
a method for correcting a tilt of a text image, the method comprising at least:
acquiring a text image to be corrected;
carrying out graying processing on the text image to be corrected to obtain a grayscale image;
carrying out binarization processing on the gray level image to obtain a binary image;
extracting straight lines in the binary image through Hough transform;
filtering the straight line according to the length and the inclination angle of the straight line;
determining the median of the inclination angles as the inclination angle of the text image to be corrected according to the filtered straight line;
and rotating the text image to be corrected according to the inclination angle of the text image to be corrected.
According to another aspect of the present invention, there is also provided a system for correcting a tilt of a text image, the system including at least:
an acquisition unit configured to acquire a text image to be corrected;
the graying unit is configured to perform graying processing on the text image to be corrected to obtain a grayscale image;
a binarization unit configured to perform binarization processing on the grayscale image to obtain a binary image;
an extraction unit configured to extract a straight line in the binary image by hough transform;
a filtering unit configured to filter the straight line according to a length and an inclination angle of the straight line;
a determining unit configured to determine, for the filtered straight line, a median of the inclination angles as an inclination angle of the text image to be corrected;
a rotation unit configured to rotate the text image to be corrected according to an inclination angle of the text image to be corrected.
Compared with the prior art, the technical scheme at least has the following beneficial effects:
the embodiment of the invention obtains the text image to be corrected. And then carrying out gray processing on the text image to be corrected to obtain a gray image. Then, binarization processing is carried out on the gray level image to obtain a binary image. And then extracting straight lines in the binary image through Hough transform. And filtering the straight line according to the length and the inclination angle of the straight line. And determining the median of the inclination angles as the inclination angles of the text images to be corrected according to the filtered straight lines. And finally, rotating the text image to be corrected according to the inclination angle of the text image to be corrected. Therefore, the text image correction method and device can effectively correct the text images with various inclination angles.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the means particularly pointed out in the written description and claims hereof as well as the appended drawings.
It should be noted that this summary is not intended to identify essential features of the claimed subject matter, nor is it intended to be used to determine the scope of the claimed subject matter. The claimed subject matter is not limited to addressing any or all of the disadvantages noted in the background.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention, are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention without limiting the invention to the right. It is obvious that the drawings in the following description are only some embodiments, and that for a person skilled in the art, other drawings can be derived from them without inventive effort. In the drawings:
FIG. 1 is a flow diagram illustrating a method for text image tilt correction according to an exemplary embodiment;
fig. 2 is a schematic structural diagram illustrating a text image tilt correction system according to an exemplary embodiment.
These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
The technical problems solved, the technical solutions adopted and the technical effects achieved by the embodiments of the present invention are clearly and completely described below with reference to the accompanying drawings and the specific embodiments. It is to be understood that the described embodiments are merely a few, and not all, of the embodiments of the present application. All other equivalent or obviously modified embodiments obtained by the person skilled in the art based on the embodiments in this application fall within the scope of protection of the invention without inventive step. The embodiments of the invention can be embodied in many different ways as defined and covered by the claims.
It should be noted that in the following description, numerous specific details are set forth in order to provide an understanding. It may be evident, however, that the subject invention may be practiced without these specific details.
It should be noted that, unless explicitly defined or conflicting, the embodiments and technical features in the present invention may be combined with each other to form a technical solution.
In order to effectively correct a tilted text image, an embodiment of the present invention provides a text image tilt correction method. As shown in fig. 1, the method may include at least:
s100: and acquiring a text image to be corrected.
S110: and carrying out gray processing on the text image to be corrected to obtain a gray image.
S120: and carrying out binarization processing on the gray level image to obtain a binary image.
S130: and extracting straight lines in the binary image through Hough transform.
S140: and filtering the straight line according to the length and the inclination angle of the straight line.
S150: and determining the median of the inclination angles as the inclination angles of the text images to be corrected according to the filtered straight lines.
S160: and rotating the text image to be corrected according to the inclination angle of the text image to be corrected.
The embodiment of the invention extracts the straight line in the binary image by carrying out graying, binarization processing and Hough transformation on the text image to be corrected. Then, the extracted straight line is filtered according to the length and the inclination angle of the straight line, the median of the inclination of the filtered straight line in the image is used as the estimation of the image inclination, and the image is subjected to rotation correction, so that the text images with various inclinations can be effectively corrected.
Specifically, step S120 may further include:
s122: and extracting an image gray matrix according to the gray image.
S124: and calculating an image local contrast matrix according to the image gray matrix.
S126: and (4) performing binary division on the image local contrast matrix by using the Otsu method to obtain a binary image.
The local contrast of the text image can be calculated according to the following formula:
Con(i,j)＝αC(i,j)+(1-α)(Imax(i,j)-Imin(i,j))
wherein Con (i, j) represents the local contrast value at (i, j); i represents the abscissa of the pixel point; j represents the ordinate of the pixel; i (I, j) represents the gray value at position (I, j), Imax(I, j) and Imin(i, j) respectively representing the maximum and minimum grey values in a local neighborhood centered around (i, j), α e (0,1), which is an adjustable parameter, and e is an infinitesimal quantity, which has the effect of preventing the denominator from being 0.
In the local contrast calculation formula, the parameter α can be calculated according to the following formula:
wherein, pow (x)1,x2) Representing an exponential function, x1Denotes the base number, x2Represents an index; var represents the standard deviation of the whole image; the gamma value is 1.
Illustratively, the local filter window width size may be chosen to be 5 when computing the image local contrast matrix.
The local contrast matrix of the image is obtained by filtering the gray matrix of the image, so that the influence caused by uneven illumination can be effectively eliminated, and the contrast and the binary separability of the image are improved.
In an optional embodiment, when the step S126 is specifically implemented, the method may specifically include:
s1261: and acquiring the maximum value and the minimum value of the contrast value in the local contrast matrix of the image.
S1262: and setting the number of histogram groups, equally dividing the interval between the maximum value and the minimum value of the contrast value according to the number of the histogram groups, so that the local contrast value of each pixel point falls into the corresponding interval, and constructing a histogram.
S1263: selecting any point in the histogram, dividing the histogram into two parts according to the point, and calculating the intra-class variance and the inter-class variance of the two parts.
S1264: and selecting the point with the maximum value of the inter-class variance divided by the intra-class variance in the histogram as the optimal binary segmentation threshold point.
S1265: and dividing the image local contrast matrix into a first binary matrix according to the optimal binary segmentation threshold point.
S1266: and performing edge detection on the gray level image by using a Canny operator to determine an edge matrix.
S1267: and taking the intersection of the first binary matrix and the edge matrix to determine a third binary matrix.
S1268: and determining a binary image according to the third binary matrix.
In the first binary matrix, 0 represents a background point, and 1 represents a character point.
When the Canny operator is used for detecting the edge on the original gray level image, the parameter threshold value of the Canny operator can be reduced, so that the detected edge is more than the real edge. The edge matrix is also a binary matrix. Where 0 denotes a background point and 1 denotes a character edge point.
Taking the intersection of the first binary matrix and the edge matrix is to set the point of the position where both binary matrices are 1 as 1, and set the points of the rest positions as 0, thereby obtaining a third binary matrix.
The process of obtaining the optimal binary split threshold points is described below by way of a preferred embodiment.
Setting the histogram group number bin to 1000, and obtaining the maximum value Con in the image local contrast matrixmaxAnd minimum value Conmin。
Then, Con is mixedmaxAnd ConminThe interval in between is equally divided by the number of histogram bins, so that each point in the image local contrast matrix falls into a corresponding bin by its size.
All alternative thresholds can be derived according to the following formula:
wherein, i is 1, 2.
After selecting a threshold thres (i), the histogram can be divided into two parts, and the intra-class variance of the two parts can be calculated respectivelyAnd between-class variance
Finally, the optimal binary segmentation threshold point thres is determined according to the following formula*：
The process of obtaining the third binary matrix is described below in a preferred embodiment.
Let B1Representing a first binary matrix, B2An edge matrix is represented.
Wherein, B2Can be obtained by the following steps: on the gray matrix of the text image, Canny operator is used for edge extraction, the low threshold is set to 50, and the high threshold is set to 150, and the two thresholds ensure that most true edges are extracted. Extracted B2Still a binary matrix.
Then, carry out B ═ B1∩B2I.e. B1And B2The same 1-centered dot is represented as 1 (character edge point), and the remaining dots are represented as 0 (background point).
It will be appreciated by persons skilled in the art that the above description is made only by way of example and not as a limitation on the scope of the invention.
It should be noted that the above-mentioned method for acquiring a binary image is only an example, and any other existing or hereafter-appearing method for acquiring a binary image may be applied to the present invention, and should be included in the scope of the present invention and incorporated herein by reference.
According to the embodiment of the invention, the local contrast matrix is divided into two values by using the Otsu method, so that the accuracy of binarization can be effectively improved.
In step S130, a straight line in the binary image is extracted by hough transform.
In a binary image, a background point is represented by 0, and a character point is represented by 1. Therefore, only the polar coordinate conversion is required for the character points. Setting a threshold value (for example, 10), taking a point in the Hough space larger than the threshold value as a straight line in the image space, and reversing the point to a corresponding position in the image space, thereby completing the Hough transformation.
Converting each character point in the binary matrix into a straight line in a polar coordinate system, wherein all the character points at the position of the straight line in the image space coordinate system intersect at one point in the polar coordinate system; then marking the point of which the numerical value exceeds a certain threshold value in the polar coordinate system as a straight line at the corresponding position in the image space coordinate system; finally, for each straight line in the image space coordinate system, the corresponding line segment can be obtained according to the information of the character points on the straight line.
Specifically, the equation of a straight line in the rectangular plane coordinate system, y ═ kx + b, can be expressed as r ═ x · cos θ + y · sin θ through hough transform, where r represents the distance between the straight line and the origin, and θ represents the angle between the straight line and the x axis. Thus, for any point having coordinates (x0, y0), all straight lines passing through the point satisfy r (θ) ═ x0 · cos θ + y0 · sin θ. When detecting a straight line by hough transform, a set of straight lines in the form of r, θ passing through the point is determined for each point in the image (i.e., a corresponding r value is calculated for each θ angle sampled at angular intervals in the range of 0 ° to 360 °), and coordinates of the set of straight lines passing through each point may constitute one curve in hough space, and intersections of the plurality of curves in hough space represent straight lines formed by the respective points. In general, the intersection formed by the intersection of the most curves represents the detected straight line.
The process of extracting the straight lines in the binary image is described in detail below by way of a preferred embodiment.
Suppose there is an edge point B in B1The coordinate in the space coordinate system (x-y coordinate system) is (x)1,y1) The straight line passing through the point is expressed by a parametric equation as p ═ x1·cosθ+y1·sinθ。
Point b in space coordinate system1Is mapped to a straight line p ═ x in a polar coordinate system (p to theta coordinate system)1·cosθ+y1·sinθ。
Similarly, a point (p) in the polar coordinate system1,θ1) Is mapped into a straight line p under a space coordinate system1＝x·cosθ1+y·sinθ1。
All edge points B in Bi(i ═ 1, 2.. n) are all mapped to straight lines in the polar coordinate system, and the values of the corresponding positions in the polar coordinate system are accumulatedAnd (4) adding. I.e. the values of all points that are straight through are accumulated, the unit of accumulation may be 1.
And mapping the edge points on the same straight line to corresponding straight lines in the polar coordinate system, wherein the corresponding straight lines are intersected at one point. Therefore, if a certain point (p) in the polar coordinate system1,θ1) If m is the size of (b), the straight line p is indicated in the space coordinate system1＝x·cosθ1+y·sinθ1The number of edge points of (2) is m.
Setting the threshold value to 50, if m > 50, p1＝x·cosθ1+y·sinθ1As a straight line in image space.
All lines in the image are counted in the above manner.
According to the embodiment of the invention, when Hough transform is performed on the binary image, only character points are counted, so that the accuracy of line detection can be effectively improved, and the time complexity of an algorithm is reduced.
On the basis of obtaining the straight line through hough transform, step S140 may specifically include:
and S142, determining a line segment by counting the character points on each straight line, wherein the coordinate of the character point with the minimum abscissa is taken as the initial coordinate of the line segment, and the coordinate of the character point with the maximum abscissa is taken as the final coordinate of the line segment.
S144: and judging whether the distance between adjacent character points on the line segment is greater than a preset threshold value.
S146: and if the distance between the adjacent character points on the line segment is greater than a preset distance threshold, dividing the line segment into two line segments from the two character points.
Wherein, the character point is also the pixel point. The distance preset threshold may be 10.
After the line segments are obtained, the line segments are also screened. In particular, the screening may be performed in the following manner.
In a first implementation, it is determined whether the length of the line segment is less than a first threshold. If so, the line segment is deleted.
In a second implementation, it is determined whether the number of character points included in the line segment is less than a second threshold. If so, the line segment is deleted.
In a third implementation, the tilt angle of each line segment is calculated. A neighborhood of the slope angles of the line segments is determined. And judging whether the inclination angle values of other line segments fall into the neighborhood. If not, the line segment is deleted.
Illustratively, if the length of a line segment is less than 70, then the line segment is deleted. If the number of character points contained in a line segment is less than 20, the line segment is deleted. If a line segment is tilted by an angle theta, the neighborhood of theta may be set to theta-5, theta + 5. If the inclination angle value of no other line segment falls within the angle range of [ theta-5, theta +5], the line segment is deleted.
After the line segments are screened, the screened line segments can be sorted according to the size of the inclination angles, and the inclination angle of the median is selected and used as the inclination angle of the text image to be corrected.
In an optional embodiment, the rotating the text image to be corrected according to the inclination angle of the text image to be corrected may specifically include:
and judging whether the inclination angle of the text image to be corrected is larger than a preset angle threshold, and if so, rotating the text image to be corrected. Otherwise, the text image to be corrected is not rotated.
Preferably, the angle preset threshold may be 2 degrees.
In some optional implementations of the embodiment, it is determined whether the tilt angle of the text image to be corrected is less than 2 degrees. If so, the text image to be corrected is not rotated.
In some optional implementations of the present embodiment, it is determined whether the tilt angle of the text image to be corrected is between 85 degrees and 95 degrees. If so, the text image to be corrected is rotated twice.
Whether the inclination angle is between 85 degrees and 95 degrees indicates that the text image is a vertically shot image, and at the moment, whether the text image rotates leftwards or rightwards cannot be determined, and the text image can be rotated in any direction. Therefore, for the vertically shot image, the forward and reverse rotations are performed twice according to the inclination angle thereof.
Although the steps in this embodiment are described in the foregoing sequence, those skilled in the art will understand that, in order to achieve the effect of this embodiment, different steps need not be executed in such a sequence, and may be executed simultaneously or in a reverse sequence, and these simple changes are within the protection scope of the present invention.
Based on the same technical concept as the method embodiment, the embodiment of the invention also provides a text image inclination correction system. As shown in fig. 2, the text image inclination correction system 20 includes at least: an acquisition unit 21, a graying unit 22, a binarization unit 23, an extraction unit 24, a filtering unit 25, a determination unit 26, and a rotation unit 27. Wherein the acquiring unit 21 is configured to acquire a text image to be corrected. The graying unit 22 is configured to perform graying processing on the text image to be corrected, resulting in a grayscale image. The binarization unit 23 is configured to perform binarization processing on the grayscale image, resulting in a binary image. The extraction unit 24 is configured to extract a straight line in the binary image by hough transform. The filtering unit 25 is configured to filter the straight line according to the length and the inclination angle of the straight line. The determination unit 26 is configured to determine, for the filtered straight line, the median of the tilt angles as the tilt angle of the text image to be corrected. The rotation unit 27 is configured to rotate the text image to be corrected in accordance with the inclination angle of the text image to be corrected.
In some optional implementation manners of the embodiment of the present invention, the binarization unit may specifically include: the device comprises an extraction module, a first calculation module and a first division module. Wherein the extraction module is configured to extract an image grayscale matrix from the grayscale image. The first calculation module is configured to calculate an image local contrast matrix from the image grayscale matrix. The first partitioning module is configured to perform binary partitioning on the image local contrast matrix by using the Otsu method to obtain a binary image.
In some optional implementation manners of the embodiment of the present invention, the first partitioning module specifically includes: the device comprises an acquisition module, a construction module, a second calculation module, a selection module, a second division module, a first determination module, a second determination module and a third determination module. Wherein the obtaining module is configured to obtain a maximum value and a minimum value of the contrast values in the image local contrast matrix. The construction module is configured to set the number of histogram groups, and equally divide the interval between the maximum value and the minimum value of the contrast value according to the number of the histogram groups, so that the local contrast value of each pixel point falls into the corresponding interval, and construct a histogram. The second calculation module is configured to select any point in the histogram, divide the histogram into two parts according to the point, and calculate the intra-class variance and the inter-class variance of the two parts. The selecting module is configured to select a point in the histogram where the value of the inter-class variance divided by the intra-class variance is maximum as an optimal binary segmentation threshold point. The second partitioning module is configured to partition the image local contrast matrix into a first binary matrix according to the optimal binary segmentation threshold points. The first determination module is configured to perform edge detection on the gray-scale image using a Canny operator to determine an edge matrix. The second determination module is configured to determine a third binary matrix by taking an intersection of the first binary matrix and the edge matrix. The third determination module is configured to determine a binary image from the binary matrix.
In some optional implementation manners of the embodiment of the present invention, the filtering unit specifically includes: the device comprises a fourth determining module, a first judging module, a segmenting module and a screening module. The screening module comprises a second judging module and a first deleting module; or the screening module comprises a third judging module and a second deleting module; or the screening module comprises a third calculating module, a fifth determining module, a fourth judging module and a third deleting module. The fourth determining module is configured to determine a line segment by counting character points on a straight line, wherein a coordinate where a character point with a minimum abscissa is located is taken as a start coordinate of the line segment, and a coordinate where a character point with a maximum abscissa is located is taken as an end coordinate of the line segment. The first judging module is configured to judge whether the distance between adjacent character points on the line segment is larger than a preset threshold value. The segmentation module is configured to segment a line segment from two character points into two line segments if a distance between adjacent character points on the line segment is greater than a distance preset threshold. The second determination module is configured to determine whether the length of the line segment is less than a first threshold. The first deletion module is configured to delete a line segment if the length of the line segment is less than a first threshold. Alternatively, the third judging module is configured to judge whether the number of character points included in the line segment is less than a second threshold. The second deletion module is configured to delete a line segment if the number of character points that the line segment contains is less than a second threshold. Alternatively, the third calculation module is configured to calculate the inclination angle of the line segment. A fifth determination module is configured to determine a neighborhood of the angle of inclination of the line segment. The fourth determination module is configured to determine whether the tilt angle values of other line segments fall within the neighborhood. The third deletion module is configured to delete the other line segment if the tilt angle values of the line segment fall within the neighborhood.
In some optional implementations of the embodiment of the present invention, the rotation unit specifically includes: a fifth judging module and a rotating module. Wherein the fifth judging module is configured to judge whether the inclination angle of the text image to be corrected is greater than an angle preset threshold. The rotation module is configured to rotate the text image to be corrected if the inclination angle of the text image to be corrected is greater than an angle preset threshold.
It should be noted that: in the text image tilt correction system provided in the above embodiment, only the division of the above functional modules is taken as an example when performing text image correction, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the system is divided into different functional modules to complete all or part of the above described functions.
The above system embodiment may be used to implement the above method embodiment, and the technical principle, the technical problems solved, and the technical effects are similar, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the above described system may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
It should be noted that the system embodiment and the method embodiment of the present invention have been described above separately, but the details described for one embodiment may also be applied to another embodiment. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not to be construed as unduly limiting the present invention. Those skilled in the art will understand that: modules or steps in embodiments of the present invention may also be broken down or combined. For example, the modules of the above embodiments may be combined into one module, or may be further split into multiple sub-modules.
The technical solutions provided by the embodiments of the present invention are described in detail above. Although specific examples have been employed herein to illustrate the principles and practice of the invention, the foregoing descriptions of embodiments are merely provided to assist in understanding the principles of embodiments of the invention; also, it will be apparent to those skilled in the art that variations may be made in the embodiments and applications of the invention without departing from the spirit and scope of the invention.
It should be noted that the flowcharts or block diagrams referred to herein are not limited to the forms shown herein, and may be divided and/or combined.
It should be noted that: the numerals and text in the figures are only used to illustrate the invention more clearly and are not to be considered as an undue limitation of the scope of the invention.
The terms "comprises," "comprising," or any other similar term are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus/device.
The term "if" can be interpreted to mean "at … …" or "immediately after … …", depending on the context.
The terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. The terms first, second, etc. are used to denote names, and not to denote any particular order.
The various steps of the present invention may be implemented in a general purpose computing device, for example, they may be centralized on a single computing device, such as: personal computers, server computers, hand-held or portable devices, tablet-type devices or multi-processor apparatus, which may be distributed over a network of computing devices, may perform the steps shown or described in a different order than those shown or described herein, or may be implemented as separate integrated circuit modules, or may be implemented as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific hardware or software or combination thereof.
The methods provided by the present invention may be implemented using programmable logic devices or as computer program software or program modules (including routines, programs, objects, components, data structures, etc.) including performing particular tasks or implementing particular abstract data types, such as a computer program product which is executed to cause a computer to perform the methods described herein. The computer program product includes a computer-readable storage medium having computer program logic or code portions embodied in the medium for performing the method. The computer-readable storage medium may be a built-in medium installed in the computer or a removable medium detachable from the computer main body (e.g., a storage device using a hot-plug technology). The built-in medium includes, but is not limited to, rewritable non-volatile memory such as: RAM, ROM, flash memory, and hard disk. The removable media include, but are not limited to: optical storage media (e.g., CD-ROMs and DVDs), magneto-optical storage media (e.g., MOs), magnetic storage media (e.g., magnetic tapes or removable disks), media with built-in rewritable non-volatile memory (e.g., memory cards), and media with built-in ROMs (e.g., ROM cartridges).
The present invention is not limited to the above-described embodiments, and any variations, modifications, or alterations that may occur to one skilled in the art without departing from the spirit of the invention fall within the scope of the invention.
Claims (8)
1. A method for correcting a tilt of a text image, the method comprising at least:
acquiring a text image to be corrected;
carrying out graying processing on the text image to be corrected to obtain a grayscale image;
carrying out binarization processing on the gray level image to obtain a binary image; the method specifically comprises the following steps: extracting an image gray matrix according to the gray image; calculating an image local contrast matrix according to the image gray matrix; performing binary division on the image local contrast matrix by utilizing an Otsu method to obtain a binary image; wherein, the image local contrast matrix is:
where Con (I, j) is the local contrast of a point with coordinates (I, j) in the gray matrix of the image, Imax(I, j) and Imin(i, j) are the maximum gray value and the minimum gray value of the neighborhood taking the point with the coordinate (i, j) as the center in the gray matrix of the image respectively, and epsilon is the infinitesimal quantity with the prevention denominator of 0;
extracting straight lines in the binary image through Hough transform;
filtering the straight line according to the length and the inclination angle of the straight line;
determining the median of the inclination angles as the inclination angle of the text image to be corrected according to the filtered straight line;
and rotating the text image to be corrected according to the inclination angle of the text image to be corrected.
2. The method according to claim 1, wherein the obtaining the binary image by binary partition of the image local contrast matrix using the Otsu method specifically comprises:
acquiring the maximum value and the minimum value of the contrast value in the image local contrast matrix;
setting the number of histogram groups, equally dividing the interval between the maximum value and the minimum value of the contrast value according to the number of the histogram groups, so that the local contrast value of each pixel point falls into the corresponding interval, and constructing a histogram;
selecting any point in the histogram, dividing the histogram into two parts according to the point, and calculating the intra-class variance and the inter-class variance of the two parts;
selecting a point with the maximum value of the inter-class variance divided by the intra-class variance in the histogram as an optimal binary segmentation threshold point;
dividing the image local contrast matrix into a first binary matrix according to the optimal binary segmentation threshold point;
performing edge detection on the gray level image by using a Canny operator to determine an edge matrix;
taking the intersection of the first binary matrix and the edge matrix to determine a third binary matrix;
and determining a binary image according to the third binary matrix.
3. The method according to claim 1, wherein the filtering the straight line according to the length and the inclination angle of the straight line comprises:
determining a line segment by counting the character points on the straight line, wherein the coordinate of the character point with the minimum abscissa is taken as the initial coordinate of the line segment, and the coordinate of the character point with the maximum abscissa is taken as the final coordinate of the line segment;
judging whether the distance between adjacent character points on the line segment is larger than a preset threshold value or not;
if the distance between the adjacent character points on the line segment is greater than a preset distance threshold, the line segment is divided into two line segments from the two character points;
the line segments are screened as follows:
judging whether the length of the line segment is smaller than a first threshold value; if yes, deleting the line segment; or,
judging whether the number of the character points contained in the line segment is smaller than a second threshold value or not; if yes, deleting the line segment; or,
calculating the inclination angle of the line segment;
determining a neighborhood of the inclination angle of the line segment;
judging whether the inclination angle values of other line segments fall into the neighborhood; if not, the line segment is deleted.
4. The method according to claim 1, wherein the rotating the text image to be corrected according to the inclination angle of the text image to be corrected specifically comprises:
judging whether the inclination angle of the text image to be corrected is larger than a preset angle threshold value or not; and if so, rotating the text image to be corrected.
5. A system for correcting the tilt of a text image, said system comprising at least:
an acquisition unit configured to acquire a text image to be corrected;
the graying unit is configured to perform graying processing on the text image to be corrected to obtain a grayscale image;
a binarization unit configured to perform binarization processing on the grayscale image to obtain a binary image; the binarization unit specifically comprises: an extraction module configured to extract an image grayscale matrix from the grayscale image; a first calculation module configured to calculate an image local contrast matrix according to the image gray matrix; the first division module is configured to perform binary division on the image local contrast matrix by using the Otsu method to obtain a binary image; wherein, the image local contrast matrix is:
where Con (I, j) is the local contrast of a point with coordinates (I, j) in the gray matrix of the image, Imax(I, j) and Imin(i, j) are the maximum gray value and the minimum gray value of the neighborhood taking the point with the coordinate (i, j) as the center in the gray matrix of the image respectively, and epsilon is the infinitesimal quantity with the prevention denominator of 0;
an extraction unit configured to extract a straight line in the binary image by hough transform;
a filtering unit configured to filter the straight line according to a length and an inclination angle of the straight line;
a determining unit configured to determine, for the filtered straight line, a median of the inclination angles as an inclination angle of the text image to be corrected;
a rotation unit configured to rotate the text image to be corrected according to an inclination angle of the text image to be corrected.
6. The system according to claim 5, wherein the first partitioning module specifically comprises:
an obtaining module configured to obtain a maximum value and a minimum value of contrast values in the image local contrast matrix;
the construction module is configured to set the number of histogram groups, and equally divide the interval between the maximum value and the minimum value of the contrast value according to the number of the histogram groups, so that the local contrast value of each pixel point falls into the corresponding interval, and a histogram is constructed;
the second calculation module is configured to select any point in the histogram, divide the histogram into two parts according to the point, and calculate the intra-class variance and the inter-class variance of the two parts;
a selecting module configured to select a point in the histogram where the value of the inter-class variance divided by the intra-class variance is maximum as an optimal binary segmentation threshold point;
a second dividing module configured to divide the image local contrast matrix into a first binary matrix according to the optimal binary segmentation threshold point;
a first determining module configured to perform edge detection on the gray image by using a Canny operator to determine an edge matrix;
a second determining module configured to determine a third binary matrix by taking an intersection of the first binary matrix and the edge matrix;
a third determining module configured to determine a binary image from the third binary matrix.
7. The system according to claim 5, characterized in that the filtering unit comprises in particular:
a fourth determining module, configured to determine a line segment by counting the character points on the straight line, where a coordinate where a character point with a minimum abscissa is located is taken as a start coordinate of the line segment, and a coordinate where a character point with a maximum abscissa is located is taken as an end coordinate of the line segment;
the first judging module is configured to judge whether the distance between adjacent character points on the line segment is larger than a preset threshold value;
a segmentation module configured to segment the line segment from two character points into two line segments if a distance between the adjacent character points on the line segment is greater than a distance preset threshold;
a screening module configured to further include:
a second determination module configured to determine whether the length of the line segment is less than a first threshold;
a first deletion module configured to delete the line segment if the length of the line segment is less than a first threshold; or,
a third judging module configured to judge whether the number of character points included in the line segment is less than a second threshold;
a second deletion module configured to delete the line segment if the number of character points included in the line segment is less than a second threshold; or,
a third calculation module configured to calculate an inclination angle of the line segment;
a fifth determining module configured to determine a neighborhood of the angle of inclination of the line segment;
the fourth judging module is configured to judge whether the inclination angle values of other line segments fall into the neighborhood;
a third deletion module configured to delete the other line segment if the tilt angle values of the line segment fall within the neighborhood.
8. The system according to claim 5, characterized in that said rotating unit comprises in particular:
a fifth judging module configured to judge whether the inclination angle of the text image to be corrected is greater than an angle preset threshold;
a rotation module configured to rotate the text image to be corrected if the inclination angle of the text image to be corrected is greater than an angle preset threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610076128.5A CN105761219B (en) | 2016-02-03 | 2016-02-03 | Text image Slant Rectify method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610076128.5A CN105761219B (en) | 2016-02-03 | 2016-02-03 | Text image Slant Rectify method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105761219A CN105761219A (en) | 2016-07-13 |
| CN105761219B true CN105761219B (en) | 2019-03-15 |
Family
ID=56329702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610076128.5A Expired - Fee Related CN105761219B (en) | 2016-02-03 | 2016-02-03 | Text image Slant Rectify method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105761219B (en) |
Families Citing this family (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106296694B (en) * | 2016-08-13 | 2018-11-09 | 哈尔滨理工大学 | Shaft tower tilts intelligent image and recognizes measurement method |
| CN106503732B (en) * | 2016-10-13 | 2019-07-19 | 北京云江科技有限公司 | The classification method and categorizing system of text image and non-textual image |
| CN107103587B (en) * | 2017-06-05 | 2023-04-21 | 新疆大学 | Method and device for correcting inclination of biochip image |
| CN107748887A (en) * | 2017-09-30 | 2018-03-02 | 五邑大学 | It is a kind of based on dominant with recessive Line segment detection planar document perspective image antidote |
| CN108229410A (en) * | 2018-01-12 | 2018-06-29 | 深圳市商汤科技有限公司 | Image processing method and equipment |
| CN109584165A (en) * | 2018-11-30 | 2019-04-05 | 泰康保险集团股份有限公司 | A kind of antidote of digital picture, device, medium and electronic equipment |
| CN109993161B (en) * | 2019-02-25 | 2021-08-03 | 众安信息技术服务有限公司 | Text image rotation correction method and system |
| CN110188747A (en) * | 2019-04-28 | 2019-08-30 | 广州华多网络科技有限公司 | A kind of sloped correcting method of text image, device and image processing equipment |
| CN110136069B (en) * | 2019-05-07 | 2023-05-16 | 语联网（武汉）信息技术有限公司 | Text image correction method and device and electronic equipment |
| CN112016341A (en) * | 2019-05-28 | 2020-12-01 | 珠海金山办公软件有限公司 | Text picture correction method and device |
| CN110427939A (en) * | 2019-08-02 | 2019-11-08 | 泰康保险集团股份有限公司 | Method, apparatus, medium and the electronic equipment of correction inclination text image |
| CN110516667B (en) * | 2019-08-15 | 2021-10-22 | 浙江万朋教育科技股份有限公司 | Character horizontal correction method based on android |
| CN112395927A (en) * | 2019-08-19 | 2021-02-23 | 长城汽车股份有限公司 | Image processing method and device based on Hough transform |
| CN110781885A (en) * | 2019-10-24 | 2020-02-11 | 泰康保险集团股份有限公司 | Text detection method, device, medium and electronic equipment based on image processing |
| CN111062874B (en) * | 2019-12-12 | 2023-03-31 | 腾讯科技（深圳）有限公司 | Text image display method, device, equipment and storage medium |
| CN111259888B (en) * | 2020-01-15 | 2024-07-05 | 平安国际智慧城市科技股份有限公司 | Image-based information comparison method, device and computer-readable storage medium |
| CN111553344B (en) * | 2020-04-17 | 2023-05-12 | 携程旅游信息技术（上海）有限公司 | Inclination correction method, system, device and storage medium for text image |
| CN111639642B (en) * | 2020-05-07 | 2023-07-07 | 浙江大华技术股份有限公司 | Image processing method, device and apparatus |
| CN111753832B (en) * | 2020-07-02 | 2023-12-08 | 杭州睿琪软件有限公司 | Image processing method, image processing apparatus, electronic device, and storage medium |
| CN112102203A (en) * | 2020-09-27 | 2020-12-18 | 中国建设银行股份有限公司 | Image correction method, device and equipment |
| CN112926579A (en) * | 2021-03-05 | 2021-06-08 | 中国工商银行股份有限公司 | Text image correction method, text image correction device, computer system and readable storage medium |
| CN114419303A (en) * | 2021-12-11 | 2022-04-29 | 麒麟软件有限公司 | Character recognition method and scanning system based on scanning software |
| CN116109915B (en) * | 2023-04-17 | 2023-07-18 | 济宁能源发展集团有限公司 | Intelligent recognition method for container door state |
| CN117690139B (en) * | 2023-12-12 | 2024-06-18 | 北京蓝湾博阅科技有限公司 | Image preprocessing method and system based on paper book reading electronization |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258198A (en) * | 2013-04-26 | 2013-08-21 | 四川大学 | Extraction method for characters in form document image |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4261922B2 (en) * | 2002-01-16 | 2009-05-13 | 株式会社リコー | Document image processing method, document image processing apparatus, document image processing program, and storage medium |
| US7321687B2 (en) * | 2002-03-07 | 2008-01-22 | Canon Kabushiki Kaisha | Apparatus and method for image processing to label an object in a binary image |
-
2016
- 2016-02-03 CN CN201610076128.5A patent/CN105761219B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103258198A (en) * | 2013-04-26 | 2013-08-21 | 四川大学 | Extraction method for characters in form document image |
Non-Patent Citations (1)
| Title |
|---|
| 复杂背景中条码检测定位技术的研究;刘宁钟;《南京航空航天大学学报》;20050210;第37卷(第1期);第65-69页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105761219A (en) | 2016-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105761219B (en) | Text image Slant Rectify method and system | |
| Marzougui et al. | A lane tracking method based on progressive probabilistic Hough transform | |
| CN110781885A (en) | Text detection method, device, medium and electronic equipment based on image processing | |
| CN109447067B (en) | Bill direction detection and correction method and automatic bill checking system | |
| US20210342571A1 (en) | Automated signature extraction and verification | |
| CN105279512B (en) | A kind of inclination licence plate recognition method and device | |
| EP2085928B1 (en) | Detection of blobs in images | |
| CN107103320B (en) | Embedded medical data image identification and integration method | |
| CN109492642B (en) | License plate recognition method, license plate recognition device, computer equipment and storage medium | |
| CN110765992B (en) | Seal identification method, medium, equipment and device | |
| CN109308465B (en) | Table line detection method, device, equipment and computer readable medium | |
| CN108154132A (en) | Method, system and equipment for extracting characters of identity card and storage medium | |
| EP2954457A1 (en) | System and method for identifying similarities in different images | |
| CN109727279B (en) | Automatic registration method of vector data and remote sensing image | |
| CN109447117B (en) | Double-layer license plate recognition method and device, computer equipment and storage medium | |
| CN108241859A (en) | The bearing calibration of car plate and device | |
| CN102706291A (en) | Method for automatically measuring road curvature radius | |
| CN105404868A (en) | Interaction platform based method for rapidly detecting text in complex background | |
| Warif et al. | CMF-iteMS: An automatic threshold selection for detection of copy-move forgery | |
| CN112734729A (en) | Water gauge water level line image detection method and device suitable for night light supplement condition and storage medium | |
| CN112419207A (en) | Image correction method, device and system | |
| Schlegel | Automated extraction of labels from large-scale historical maps | |
| CN115272664A (en) | Instrument panel display method and device, electronic equipment and storage medium | |
| CN109635679B (en) | Real-time target paper positioning and loop line identification method | |
| CN112101139B (en) | Human shape detection method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191108 Address after: Room 501, floor 5, comprehensive building, Zhongchuang Industrial Park, New District, Huaibei Economic Development Zone, Anhui Province Patentee after: Huaibei Avanti Education Technology Co.,Ltd. Address before: 100083 No. 16 East Zhongguancun Road, Longhu, Haidian District, Downing, 8, 2801, Beijing Patentee before: BEIJING LEJENT TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190315 Termination date: 20220203 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |