CN112435218B - Method and device for evaluating and screening deformation degree of document image - Google Patents
Method and device for evaluating and screening deformation degree of document image Download PDFInfo
- Publication number
- CN112435218B CN112435218B CN202011219391.8A CN202011219391A CN112435218B CN 112435218 B CN112435218 B CN 112435218B CN 202011219391 A CN202011219391 A CN 202011219391A CN 112435218 B CN112435218 B CN 112435218B
- Authority
- CN
- China
- Prior art keywords
- document
- deformation degree
- image
- outline
- calculating
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012216 screening Methods 0.000 title claims abstract description 35
- 238000013139 quantization Methods 0.000 claims abstract description 46
- 238000011156 evaluation Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000006740 morphological transformation Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000013441 quality evaluation Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 206010034960 Photophobia Diseases 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 208000013469 light sensitivity Diseases 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000037303 wrinkles Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a deformation degree evaluation and screening method and device for document images, wherein the method comprises the following steps: extracting a document contour from the document image; calculating a quantization index of the deformation degree according to the extracted document outline; substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the deformation degree score of the document image. The invention can quantitatively score the deformation degree of the document image so as to conveniently screen the document image according to the assessed deformation degree and improve the screening efficiency of the image.
Description
Technical Field
The invention relates to the technical field of image quality evaluation, in particular to a method and a device for evaluating and screening the deformation degree of a document image.
Background
The paper document is used as a main information transmission medium, an image acquired by shooting the document is called a document image, and the document image has rich application scenes in life of people along with popularization of portable mobile devices such as mobile phones and tablet computers. However, the quality of images acquired by using mobile equipment in natural scenes is uneven, and no good evaluation method for document image quality exists at present. Whether it be individuals or businesses, high quality images are typically manually screened from the captured document images, which greatly increases production costs. By calculating objective scores of the document image quality and quantifying the image quality, the document image can be screened by setting evaluation thresholds and other methods, so that the production cost is effectively reduced, and the production efficiency is improved.
According to the current research situation of the reference-free image quality evaluation method, most of the current methods are reference-free image quality evaluation methods based on specific distortion types, including fuzzy, noise, compression and other distortion type evaluation methods, which quantify the overall quality of the image, and in recent years, many methods have achieved good effects. However, for document images, image content is an important aspect for measuring image quality, and this aspect is mainly the degree of deformation of the image, for example, in application scenes such as image recognition, even if the whole photographed document image is clear, when the document in the image is deformed, the accuracy of the result is affected. At present, the research on document deformation degree is less, and the method is mainly a document image correction method and a text information extraction method aiming at characters.
Disclosure of Invention
Therefore, the invention aims to provide a deformation degree evaluation and screening method and device for document images, which can quantitatively score the deformation degree of the document images so as to screen the document images according to the evaluated deformation degree and improve the screening efficiency of the images.
Based on the above object, the present invention provides a deformation degree evaluation method of a document image, comprising:
Extracting a document contour from the document image;
Calculating a quantization index of the deformation degree according to the extracted document outline;
Substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the deformation degree score of the document image.
The parameters in the nonlinear formula are obtained by pre-fitting according to the quantization index and subjective scores of the deformation degree of each document image in the data set.
Preferably, the extracting the document outline from the document image specifically includes:
Calculating an edge image of the document image by adopting an edge detection algorithm;
Processing the edge image by adopting a morphological transformation closing operation to obtain a closed contour;
extracting and screening the document contour by adopting a contour detection algorithm aiming at the obtained closed contour;
the document contour is simplified using a polygon fitting algorithm.
Preferably, the calculating the quantization index of the deformation according to the extracted document outline specifically includes:
determining a minimum circumscribed rectangle of the document outline, and calculating the area of the minimum circumscribed rectangle;
calculating the area of the document outline;
and calculating the quantization index of the deformation according to the document outline and the area of the minimum circumscribed rectangle.
The invention also provides a screening method of the document images, which comprises the following steps:
Obtaining a deformation degree score of the document image according to the deformation degree evaluation method;
And screening out qualified document images according to the deformation degree scores of the document images.
The invention also provides a deformation degree evaluation device of the document image, which comprises the following steps:
a document contour extraction module for extracting a document contour from the document image;
The deformation degree calculation module is used for calculating a quantization index of the deformation degree according to the extracted document outline;
And the deformation degree scoring module is used for substituting the calculated quantization index into a nonlinear formula fitted in advance to calculate the deformation degree score of the document image.
The invention also provides a screening device of the document images, which comprises:
A module in an apparatus as described above;
And the screening module is used for screening out qualified document images according to the deformation degree scores of the obtained document images.
The invention also provides an electronic device comprising a central processing unit, a signal processing and storing unit and a computer program stored on the signal processing and storing unit and capable of running on the central processing unit, wherein the central processing unit executes the deformation degree evaluation and screening method of the document image.
In the technical scheme of the invention, the document outline is extracted from the document image; calculating a quantization index of the deformation degree according to the extracted document outline; substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the deformation degree score of the document image; therefore, the deformation degree of the document image can be quantitatively scored, so that the document image can be conveniently screened according to the assessed deformation degree, and the screening efficiency of the image is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for evaluating the deformability of a document image according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for extracting a document contour according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for calculating a quantization index of deformation according to an embodiment of the present invention;
FIG. 4 is a flowchart of a method for fitting parameters in a nonlinear equation according to an embodiment of the present invention;
FIGS. 5a and 5b are block diagrams illustrating an internal structure of a device for evaluating and screening a deformation degree of a document image according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present invention.
Detailed Description
The present invention will be further described in detail below with reference to specific embodiments and with reference to the accompanying drawings, in order to make the objects, technical solutions and advantages of the present invention more apparent.
It should be noted that unless otherwise defined, technical or scientific terms used in the embodiments of the present invention should be given the ordinary meaning as understood by one of ordinary skill in the art to which the present disclosure pertains. The terms "first," "second," and the like, as used in this disclosure, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
The inventor of the present invention considers that, since the document deformability affects the identification of document contents, the larger the document deformability is, the more difficult the identification of document contents is, so that the objective score of the deformability is mainly used for application scenes related to image screening. In general, the types of distortion of a document image are classified into three types, namely, wrinkles generated by folding a paper document in half, distortions generated by bending the paper document, and geometric distortions generated by differences in photographing angles. The deformation of the document is related to the outline of the document, if the same standard image is taken as a reference, the deformation degree of the document is generally larger, and the area of the outline of the document is smaller, so that the deformation degree of the document is inversely proportional to the area of the outline of the document on the premise of the standard image. Taking the minimum circumscribed rectangle of the document outline as a reference, namely the circumscribed rectangle with the smallest area containing the complete document outline, taking the ratio of the document outline to the area of the minimum circumscribed rectangle as a quantization index, and when the document image has no document deformation, the quantization index is 1; when the document image has document deformation, the larger the degree of deviation of the outline shape of the document from the rectangle, the smaller the corresponding area, and the smaller the quantization index.
Thus, in the technical scheme of the invention, the document outline is extracted from the document image; calculating a quantization index of the deformation degree according to the extracted document outline; substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the deformation degree score of the document image; therefore, the deformation degree of the document image can be quantitatively scored, so that the document image can be conveniently screened according to the assessed deformation degree, and the screening efficiency of the image is improved.
The following describes the technical scheme of the embodiment of the present invention in detail with reference to the accompanying drawings.
The deformation degree evaluation and screening method for the document image provided by the embodiment of the invention has the flow shown in figure 1, and comprises the following steps:
Step S101: a document outline is extracted from the document image.
In this step, a conventional image processing method may be used to extract a document contour from a document image, for example, methods such as edge detection and morphological transformation, and after processing an original image, a simplified document contour may be obtained, where a specific method flow is shown in fig. 2, and includes the following sub-steps:
substep S201: and calculating an edge image of the document image by adopting an edge detection algorithm.
In the substep, firstly, carrying out gray processing on a document image to obtain a gray image which does not contain color information; wherein, the gray value I gray＝0.299Ir+0.587Ig+0.114Ib of the pixel of the gray image; wherein I r、Ig、Ib is the Red (Red), green (Green), blue (Blue) component of the pixel in the document image, respectively.
Further, edge detection is performed on the grayscale image to calculate an edge image, for example, an edge image is calculated using a Canny (Canny) edge detection algorithm; the edge image is a binary image (the value is 0 or 255) containing the image edge, the selection of the high and low thresholds in the Canny edge detection algorithm directly influences the number of edges in the edge image, and the processing effect of the edge detection algorithm is measured by the average value of the edge image in the substep. In one example, an average value of the edge image may be set to 20, a ratio of the low threshold to the high threshold is 1/3, 15 is a low threshold starting point, 3 is an incremental step, a linear search method is used to select an appropriate threshold, and the edge image under the high and low thresholds is calculated.
Sub-step S202: processing the edge image by adopting a morphological transformation closing operation to obtain a closed contour.
Specifically, the edge image includes an image edge including a document contour; while the document outline is typically made up of a plurality of adjacent (non-interconnected) edges, to obtain a closed document outline, the edge image is processed in this substep using a closing operation in morphological transformations, i.e. an expanding operation followed by a corroding operation, to obtain a closed outline. Whether the outline can be closed depends on the structural elements used for the closing operation, and in one example, a 4x4 rectangular structural element may be selected to process the edge image, outputting a closed outline containing the document outline, i.e., a closed edge image.
Substep S203: and extracting and screening the document contour by adopting a contour detection algorithm aiming at the determined closed contour.
Specifically, the contours are a set of pixel point coordinate sequences, and for the closed areas without holes in the interior of the image, the contours only have outer contours, while for the closed areas with holes in the image, the contours usually have two outer contours and inner contours, a father-son relationship is formed between the contours, and the holes can be further nested. The document in the document image is the main component of the image, so the area of the closed area corresponding to the document outline is the largest, and the document area is not contained by other objects, so the document outline is the outermost outline. Thus, in this substep, all the outermost contours in the closed contours of the image are extracted using a contour detection algorithm, and the contour in which the area of the closed region is the largest is taken as the contour of the document.
Substep S204: the document contour is simplified using a polygon fitting algorithm.
Specifically, the document contour extracted by the contour detection algorithm is composed of a continuous adjacent point coordinate sequence, and due to the light sensitivity characteristic of the image edge in reality, the pixel points in the document contour cannot completely fit the document contour in the image, so that the real document contour is difficult to accurately represent.
In practice the document contour can be approximated by polygons of a small number of feature point coordinate sequences, i.e. the document contour curve is simplified. When the document deformation does not occur, the document outline is rectangular and can be represented by 4 vertexes; when the document is deformed, the number of feature points in the outline of the document is determined by the degree and shape of the deformation of the document, and is usually less than 100.
In the technical scheme of the invention, the document contour is simplified by using the Fabry-Perot algorithm, and redundant points in the contour are removed. The algorithm defines the maximum distance difference epsilon between the original curve and the reduced curve, by increasing epsilon the points making up the original curve can be reduced to obtain the reduced curve. This substep uses the following method to select ε: the number of points of the document contour is c, and because the document contours of different images are greatly different, the value of epsilon is searched on [0, + ] under the limiting condition of c, the approximate interval is calculated by a power function 2 n, and then the accurate value is searched on the interval by a dichotomy, namely the first epsilon meeting the limiting condition of c. In this example, the document outline is simplified with the constraint c.ltoreq.15.
Step S102: and calculating a quantization index of the deformation degree according to the extracted document outline.
Specifically, after the simplified document outline is obtained, the minimum circumscribed rectangle is calculated according to the document outline, then the areas of the document outline and the circumscribed rectangle are calculated respectively, the ratio of the two is a quantization index of the deformation degree, the flow is shown in fig. 3, and the method comprises the following substeps:
substep S301: and determining the minimum circumscribed rectangle of the document outline, and calculating the area of the minimum circumscribed rectangle.
Specifically, the minimum circumscribed rectangle is the circumscribed rectangle with the smallest circumscribed area of the document outline, the input of the substep is the simplified document outline, firstly, a convex hull of an outline point coordinate sequence in the document outline is calculated, then, the minimum circumscribed rectangle of the convex hull is calculated by using a rotary caliper method, and the rectangle is the minimum circumscribed rectangle of the document outline. The minimum bounding rectangle is represented by a rotating rectangle and comprises a rectangle centroid, a length and a width and a rotation angle, the area A rotatedRect of the corresponding closed area is equal to the product of the length L rotatedRect and the width W rotatedRect of the rotating rectangle, and the calculation formula is as follows: a rotatedRect＝LrotatedRect*WrotatedRect.
Substep S302: the area of the document outline is calculated.
Specifically, since there is no self-intersecting portion in the document outline, the area of the closed area corresponding to the document outline, that is, the area of the document outline is calculated by using the green formula. The calculation formula of the document contour area A document is: the formula calculates the cross product of coordinate vectors of every two adjacent contour points, wherein n is the number of the contour points, and n is more than 2,/> Is a contour point sequence,/>Represents the i-th point coordinate (x i,yi) vector, and
Substep S303: and calculating the quantization index of the deformation according to the document outline and the area of the minimum circumscribed rectangle.
In this substep, the definition of the quantization index I deformation of the deformability of the document image is as follows:
after the document outline and the area of the minimum circumscribed rectangle are obtained, the quantitative index of the deformation degree of the document image can be obtained by calculating the ratio of the document outline and the area of the minimum circumscribed rectangle.
Step S103: substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the score of the deformation degree of the document image.
Specifically, the input of the nonlinear formula is a quantization index of the document image deformability, and the document image deformability score can be obtained by substituting the quantization index into the formula.
Step S104: and screening out qualified document images according to the deformation degree scores of the document images.
Specifically, the deformability score of the document image may be compared with a set threshold; and screening the document images with the deformation scores smaller than the set threshold value into qualified document images.
Therefore, in the online business requiring the user to upload the document image, whether the uploaded document image is qualified or not can be judged through the deformation degree score of the document image;
In addition, in the word recognition algorithm based on machine learning and the neural network, certain requirements are placed on the quality of the document images for training, the document images with low document deformation degree can be automatically screened out in batches through the deformation degree scoring of the document images to serve as the document images for training, and therefore the training of word recognition on the neural network is achieved.
The parameters in the nonlinear formula are fitted in advance, the formula and the fitting step of the formula parameters are shown in fig. 4, and the specific flow is as follows:
Step S401: the degree of deformation of each document image in the dataset is subjectively scored.
Specifically, the step is to subjectively evaluate each document image dataset in the datasets to obtain subjective scores of the deformability of each document image. In one example, the degrees of deformation of document images in a dataset may be classified into four levels, each corresponding to a different scoring interval. For each document image in the data set, grading the deformation degree of the document image by a digital observer, and finally taking the average value of all grades as the subjective grade of the deformation degree of the document image.
Step S402: a quantization index of the degree of deformation of each document image in the dataset is calculated.
The method comprises the step of calculating image characteristics of each document image in a data set to obtain a quantization index of deformation degree of each document image. Specifically, for each document image in the dataset, the quantization index of the deformability of the document image may be calculated by the method of steps S101 to S102 described above.
Step S403: and fitting parameters in a nonlinear formula according to the quantization index and subjective scores of the deformation degree of each document image in the data set.
Specifically, a subjective score calculation formula for calculating the document image deformability by using an iterative least squares estimation method can be adopted, and the formula calculates the corresponding score according to the quantization index. In image processing, a nonlinear formula of 4 parameters is commonly used to fit image features and subjective scores of image quality, and in one example, the fitting targets are quantization indexes and subjective scores, and the nonlinear formula is shown in formula 1:
Wherein x is a quantization index of the deformation degree of the document image, f (x) is a deformation degree score of the document image, and k 1、k2、k3、k4 is a regression parameter obtained by pre-fitting in a formula.
Further, toRepresenting a non-linear formula, wherein/>The quantitative index of the deformation degree of the document image i is x i, i is [ 1], the number of the document images in the dataset is N, and the subjective score of the deformation degree of the document image i is y i, and the subjective score of the deformation degree of the document image i is y/oIs to minimize the following equation 2:
The quantitative index and subjective score of the deformation degree of each document image in the data set are used as input, and the calculation can be carried out to obtain Substituting it into the nonlinear formula shown in formula 1 above results in a fitted nonlinear formula.
Based on the deformation degree evaluation and screening method of the document image, the embodiment of the invention provides a deformation degree evaluation and screening device of the document image, and internal structure block diagrams are respectively shown in fig. 5a and 5 b; the deformation degree evaluation device for the document image provided by the embodiment of the invention comprises the following modules: a document contour extraction module 501, a deformation calculation module 502 and a deformation scoring module 503.
The document contour extraction module 501 is used for extracting a document contour from a document image; specifically, the document contour extraction module 501 may extract the document contour according to the method of step S101 described above.
The deformation degree calculation module 502 is used for calculating a quantization index of the deformation degree according to the extracted document outline; specifically, the deformability calculation module 502 determines a minimum circumscribed rectangle of the document outline, and calculates the area of the minimum circumscribed rectangle; calculating the area of the document outline; and calculating the quantization index of the deformation according to the document outline and the area of the minimum circumscribed rectangle. Specifically, the deformation calculation module 502 may calculate the quantization index of the deformation according to the method of step S102 described above.
The deformation degree scoring module 503 is configured to substitute the calculated quantization index into a nonlinear formula fitted in advance, and calculate a deformation degree score of the document image; a fitted nonlinear formula may be shown in equation 1 above.
Further, the deformation degree evaluation device for a document image provided by the embodiment of the invention may further include: the formula fitting module 504.
The formula fitting module 504 is configured to obtain parameters in the nonlinear formula by pre-fitting according to the quantization index and subjective score of the deformation degree of each document image in the dataset. Specifically, the formula fitting module 504 may obtain the parameters in the nonlinear formula according to the method in each step in the flowchart shown in fig. 4.
As shown in fig. 5b, the screening device for document images provided in the embodiment of the present invention includes each module in the deformation degree evaluation device for document images, and further includes: a screening module 505.
The screening module 505 is configured to screen out qualified document images according to the deformation degree scores of the obtained document images.
Fig. 6 shows a more specific hardware architecture of an electronic device according to this embodiment, where the device may include: a processor 1010, a memory 1020, an input/output interface 1030, a communication interface 1040, and a bus 1050. Wherein processor 1010, memory 1020, input/output interface 1030, and communication interface 1040 implement communication connections therebetween within the device via a bus 1050.
The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit ), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits, etc., for executing a relevant program to implement the deformation evaluation method of the document image or the screening method of the document image provided in the embodiments of the present specification.
The Memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory ), static storage, dynamic storage, etc. Memory 1020 may store an operating system and other application programs, and when the embodiments of the present specification are implemented in software or firmware, the associated program code is stored in memory 1020 and executed by processor 1010.
The input/output interface 1030 is used to connect with an input/output module and may be connected with a nonlinear receiver to receive information from the nonlinear receiver for information input and output. The input/output module may be configured as a component in a device (not shown) or may be external to the device to provide corresponding functionality. Wherein the input devices may include a keyboard, mouse, touch screen, microphone, various types of sensors, etc., and the output devices may include a display, speaker, vibrator, indicator lights, etc.
Communication interface 1040 is used to connect communication modules (not shown) to enable communication interactions of the present device with other devices. The communication module may implement communication through a wired manner (such as USB, network cable, etc.), or may implement communication through a wireless manner (such as mobile network, WIFI, bluetooth, etc.).
Bus 1050 includes a path for transferring information between components of the device (e.g., processor 1010, memory 1020, input/output interface 1030, and communication interface 1040).
It should be noted that although the above-described device only shows processor 1010, memory 1020, input/output interface 1030, communication interface 1040, and bus 1050, in an implementation, the device may include other components necessary to achieve proper operation. Furthermore, it will be understood by those skilled in the art that the above-described apparatus may include only the components necessary to implement the embodiments of the present description, and not all the components shown in the drawings.
In the technical scheme of the invention, the document outline is extracted from the document image; calculating a quantization index of the deformation degree according to the extracted document outline; substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the deformation degree score of the document image; therefore, the deformation degree of the document image can be quantitatively scored, so that the document image can be conveniently screened according to the assessed deformation degree, and the screening efficiency of the image is improved.
The computer readable media of the present embodiments, including both permanent and non-permanent, removable and non-removable media, may be used to implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device.
Those of ordinary skill in the art will appreciate that: the discussion of any of the embodiments above is merely exemplary and is not intended to suggest that the scope of the disclosure, including the claims, is limited to these examples; the technical features of the above embodiments or in the different embodiments may also be combined within the idea of the invention, the steps may be implemented in any order and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
Additionally, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures, in order to simplify the illustration and discussion, and so as not to obscure the invention. Furthermore, the devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., such specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative in nature and not as restrictive.
While the invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of those embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. of the present invention should be included in the scope of the present invention.
Claims (6)
1. A method for evaluating a degree of deformation of a document image, comprising:
Extracting a document contour from the document image;
Calculating a quantization index of the deformation degree according to the extracted document outline: determining a minimum circumscribed rectangle of the document outline, and calculating the area of the minimum circumscribed rectangle; calculating the area of the document outline; calculating to obtain a quantization index of the deformation according to the ratio of the document outline to the area of the minimum circumscribed rectangle;
Substituting the calculated quantization index into a nonlinear formula fitted in advance, and calculating the deformation degree score of the document image;
The parameters in the nonlinear formula are obtained by pre-fitting according to the quantization index and subjective scores of the deformation degree of each document image in the data set.
2. The method according to claim 1, wherein the extracting the document outline from the document image specifically comprises:
Calculating an edge image of the document image by adopting an edge detection algorithm;
Processing the edge image by adopting a morphological transformation closing operation to obtain a closed contour;
extracting and screening the document contour by adopting a contour detection algorithm aiming at the obtained closed contour;
the document contour is simplified using a polygon fitting algorithm.
3. A method for screening document images, comprising:
The deformation degree evaluation method according to any one of claims 1 to 2, obtaining a deformation degree score of the document image;
And screening out qualified document images according to the deformation degree scores of the document images.
4. A deformation degree evaluation device of a document image, characterized by comprising:
a document contour extraction module for extracting a document contour from the document image;
The deformation degree calculation module is used for calculating a quantization index of the deformation degree according to the extracted document outline: determining a minimum circumscribed rectangle of the document outline, and calculating the area of the minimum circumscribed rectangle; calculating the area of the document outline; calculating to obtain a quantization index of the deformation according to the ratio of the document outline to the area of the minimum circumscribed rectangle;
the deformation degree scoring module is used for substituting the calculated quantization index into a nonlinear formula fitted in advance to calculate the deformation degree score of the document image;
And the formula fitting module is used for pre-fitting to obtain parameters in the nonlinear formula according to the quantization index and subjective scores of the deformation degree of each document image in the data set.
5. A screening apparatus for document images, comprising:
A module in an apparatus as claimed in claim 4;
And the screening module is used for screening out qualified document images according to the deformation degree scores of the obtained document images.
6. An electronic device comprising a central processing unit, a signal processing and storage unit, and a computer program stored on the signal processing and storage unit and executable on the central processing unit, characterized in that the central processing unit implements the method according to any of claims 1-3 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011219391.8A CN112435218B (en) | 2020-11-04 | 2020-11-04 | Method and device for evaluating and screening deformation degree of document image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011219391.8A CN112435218B (en) | 2020-11-04 | 2020-11-04 | Method and device for evaluating and screening deformation degree of document image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112435218A CN112435218A (en) | 2021-03-02 |
| CN112435218B true CN112435218B (en) | 2024-06-25 |
Family
ID=74695432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011219391.8A Active CN112435218B (en) | 2020-11-04 | 2020-11-04 | Method and device for evaluating and screening deformation degree of document image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112435218B (en) |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458265B (en) * | 2013-02-01 | 2015-03-04 | 深圳信息职业技术学院 | Method and device for evaluating video quality |
| CN103400367A (en) * | 2013-07-03 | 2013-11-20 | 河海大学常州校区 | No-reference blurred image quality evaluation method |
| JP2015114949A (en) * | 2013-12-13 | 2015-06-22 | 大日本印刷株式会社 | Image processor, image processing method, program for image processor, and recording medium |
| CN104021574B (en) * | 2014-07-04 | 2016-12-07 | 武汉武大卓越科技有限责任公司 | Pavement disease automatic identifying method |
| CN104134204B (en) * | 2014-07-09 | 2017-04-19 | 中国矿业大学 | Image definition evaluation method and image definition evaluation device based on sparse representation |
| WO2018017599A1 (en) * | 2016-07-19 | 2018-01-25 | Vid Scale, Inc. | Quality evaluation system and method for 360-degree video |
| CN106570484B (en) * | 2016-11-07 | 2019-11-26 | 中国科学院自动化研究所 | MIcrosope image acquisition method based on sequence section |
| US10699100B2 (en) * | 2016-11-07 | 2020-06-30 | Institute Of Automation, Chinese Academy Of Sciences | Method for microscopic image acquisition based on sequential section |
| CN108010023B (en) * | 2017-12-08 | 2020-03-27 | 宁波大学 | High dynamic range image quality evaluation method based on tensor domain curvature analysis |
| CN108345881B (en) * | 2018-02-01 | 2021-12-21 | 福州大学 | Document quality detection method based on computer vision |
| CN110415207A (en) * | 2019-04-30 | 2019-11-05 | 杭州电子科技大学 | A method of the image quality measure based on image fault type |
| CN111028195B (en) * | 2019-10-24 | 2023-03-24 | 西安电子科技大学 | Example segmentation based redirected image quality information processing method and system |
-
2020
- 2020-11-04 CN CN202011219391.8A patent/CN112435218B/en active Active
Non-Patent Citations (2)
| Title |
|---|
| Image Quality Assessment Based on Multiscale Geometric Analysis;Xinbo Gao 等;《IEEE Transactions on Image Processing》;20091231;第18卷(第7期);1409-1423 * |
| 监控图像质量的无参评估方法研究;陈天文;《中国优秀硕士学位论文全文数据库 信息科技辑》;20200315;第2020年卷(第3期);I138-982 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112435218A (en) | 2021-03-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| RU2680765C1 (en) | Automated determination and cutting of non-singular contour of a picture on an image | |
| Liu et al. | GcsDecolor: gradient correlation similarity for efficient contrast preserving decolorization | |
| Zhang et al. | Multiple-level feature-based measure for retargeted image quality | |
| CN111401324A (en) | Image quality evaluation method, device, storage medium and electronic equipment | |
| CN105046254A (en) | Character recognition method and apparatus | |
| CN103353881B (en) | Method and device for searching application | |
| CN111222548A (en) | Similar image detection method, device, equipment and storage medium | |
| CN111325271A (en) | Image classification method and device | |
| CN113609984A (en) | Pointer instrument reading identification method and device and electronic equipment | |
| CN111414803A (en) | Face recognition method and device and electronic equipment | |
| CN110807110A (en) | Image searching method and device combining local and global features and electronic equipment | |
| JP2012103758A (en) | Local feature amount calculation device and method therefor, and corresponding point search device and method therefor | |
| CN111047618A (en) | Multi-scale-based non-reference screen content image quality evaluation method | |
| CN113947613A (en) | Target area detection method, device, equipment and storage medium | |
| CN107423739B (en) | Image feature extraction method and device | |
| CN112435218B (en) | Method and device for evaluating and screening deformation degree of document image | |
| US11295494B2 (en) | Image modification styles learned from a limited set of modified images | |
| CN112132750A (en) | Video processing method and device | |
| CN116883698A (en) | Image comparison method and related device | |
| CN113537158B (en) | Image target detection method, device, equipment and storage medium | |
| CN109685757B (en) | Non-reference image quality evaluation method and system based on gray difference statistics | |
| JP2011186595A (en) | Information generation device, object detection device, information generation method, object detection method, and program | |
| Negri et al. | Comparing support vector machine contextual approaches for urban area classification | |
| CN114612994A (en) | Method and device for training wrinkle detection model and method and device for detecting wrinkles |
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 |