CN102708371A - Method for recognizing and automatically sequencing comic frames according to segmenting lines - Google Patents
Method for recognizing and automatically sequencing comic frames according to segmenting lines Download PDFInfo
- Publication number
- CN102708371A CN102708371A CN2012101201649A CN201210120164A CN102708371A CN 102708371 A CN102708371 A CN 102708371A CN 2012101201649 A CN2012101201649 A CN 2012101201649A CN 201210120164 A CN201210120164 A CN 201210120164A CN 102708371 A CN102708371 A CN 102708371A
- Authority
- CN
- China
- Prior art keywords
- coma
- caricature
- cut
- line
- rule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a scheme for automatically recognizing, extracting and sequencing comic squares according to the comic constituent grammar so as to reduce a large amount of manual segmenting work. The segmented comic squares can be put on the mobile phone or PDA with a small screen to read, therefore, the cartoons can be read conveniently, easily and vividly. According to the method for recognizing and automatically sequencing comic frames provided by the invention, the straight lines in the pictures of the cartoons are detected to provide an iterative segmentation method according to the comic frames, the comic segmenting lines and the distribution characteristics of the comic frames to recognize and sequence the comic frames, and the segmented comic frames are stored by using a binary tree structure. The experiments prove that the method can be used for recognizing and segmenting the comic frames (comic squares) of most cartons and sequencing the comic frames (comic squares) in sequence according to the pot of the story.
Description
Technical field
The present invention designs a kind of identification of caricature frame and auto ordering method based on cut-off rule, belongs to the view data process field.
Background technology
As e-book, convenient economic, automatic sorted advantage that the electronics caricature not only has, and have the moving sense that jumps develops gradually now and comes into vogue, and is especially very welcome in the teenager consumption market.And on mobile phone or PDA, read the stir effect that produce cartoon of electronics caricature along with key up and down, enjoy the reader parent to look at.But the reading of caricature is different from e-book, because the restriction of mobile phone and PDA screen size, and makes plot have sequencing in order on mobile phone, to read, and need be divided into littler picture to every caricature, and don't influence is read.
Occurred the service of a lot of electronics caricature at present, but these work major parts all are to discern the caricature frame of cutting apart in the caricature page or leaf through manual work.Present stage, also fewer to the research of electronics caricature both at home and abroad.People such as Masashi YAMADA have proposed a kind of method that dialog box content in caricature frame and the caricature frame is sorted by angle, mainly focus on the correctness of ranking results, do not mention and how effectively handle the incomplete caricature frame of cut-off rule.Takamasa Tanaka, Kenji Shoji and Fubito Toyama have proposed a kind ofly to represent the caricature frame with tree construction, through with gradient density function identification straight line the caricature frame being carried out topological analysis.It is imperfect that this method can solve cut-off rule, promptly has dialog box to block the situation of cut-off rule, but can not use in real time.Also the work of treatment of the caricature picture of some others has obtained research; Like people such as Syeda-Mahmood a kind of method in the identification of caricature picture Chinese version has been proposed; Make that reading released separately in the literal in the dialog box in the caricature; This also is very important for the electronics caricature, also needs further research work but can really obtain actual application.
Summary of the invention
The technical matters that the present invention will solve is to general caricature cut-off rule characteristics; Through judging the characteristics that cut-off rule had between the caricature frame caricature frame is discerned; And the characteristics of arranging according to the caricature frame have proposed to utilize binary tree and the sort method that the caricature frame combines, and are easily understood, carry out the efficient height.
For solving the problems of the technologies described above, the invention provides a kind of identification of caricature frame and auto ordering method based on cut-off rule, it is characterized in that, do as giving a definition:
A, caricature frame: the minimal graph blade unit that can not cut apart again in every page of caricature;
B, caricature section: the quadrilateral of forming by at least two continuous caricature frames;
This method may further comprise the steps:
A, given caricature page or leaf is done pre-service, comprising:
A, to said caricature page or leaf binaryzation, obtain binary image;
B, said binary image is made profile detect, obtain the foreground image of caricature page or leaf;
B, foreground image is made straight-line detection, obtain the straight line that comprises in the foreground image;
The quadrilateral structure body that obtains after C, the definition straight-line detection is coma; Coma is caricature frame or caricature section; Caricature is cut apart from the coma of maximum and is begun, if coma satisfies one of following condition, judges that then the picture that coma is indivisible and coma is corresponding is the caricature frame; Execution in step G, otherwise execution in step D;
A, coma inside do not have straight line;
Inner maximum foreground image area of b, coma and coma area ratio be less than threshold value m, wherein 0＜m＜0.25;
The ratio of the inner maximum foreground image areas pixel quantity of c, coma and all pixel quantities of coma inside is less than threshold value n, wherein 0＜n＜0.2;
The inner maximum foreground image areas of d, the coma length and width ratio corresponding with coma is less than threshold value p, 0.08＜p＜0.2;
D, from the straight line that straight-line detection is obtained, select cut-off rule, said cut-off rule must meet the following conditions:
A, said cut-off rule only with coma in two relative limits intersect, do not have intersection point with other limits;
The intersection point of b, said cut-off rule and coma is on the edge line of coma;
E, the descending of said cut-off rule by its weight screened one by one, select with other straight-line intersection numbers and be no more than 3 cut-off rule, be defined as the standard cut-off rule;
F, in the width range of each HW pixel of said standard cut-off rule both sides; Select non-intersect or maximum straight lines that intersection point is only arranged with two straight lines with other straight line; From these straight lines, select again one with the split position of the minimum straight line of foreground image number of hits as coma, be defined as the optimal segmentation line; If can not select qualified optimal segmentation line, return step e, select the satisfactory optimal segmentation line of next bar according to the weight of said cut-off rule;
G, employing binary tree data structure store the coma through divisional processing according to the reading order of caricature;
H, according to the optimal segmentation line caricature page or leaf is done to cut apart for the first time after, the caricature section that produces cutting apart of using the same method continues to cut apart and stores the coma of new generation, till not having alienable coma, one page caricature cut apart completion.
The image segmentation threshold value system of selection of adopting printenv and non-supervision to be set to 0 less than the pixel value of threshold value through selecting a threshold value to said caricature page or leaf binaryzation, is set to 1 greater than the pixel value of this threshold value.
The caricature page or leaf foreground image that obtains after profile detected was made micronization processes before straight-line detection, line thickness in the foreground image is refined into greater than the lines of 1 pixel has only a pixel wide.
Judge whether coma inside has the method for straight line to be:, think that then this straight line is inner at coma, otherwise think that this straight line is inner at coma if straight line falls into the inner amount of pixels of coma half the less than straight line pixel total amount.
Adopt Kernel-based Hough transform method to make straight-line detection, and the weight of definite cut-off rule.
The caricature coma method that binary tree stores reading order from right to left is following:
Define a binary tree, the relation of binary tree and caricature coma is that a coma is the node of binary tree, and root node is one page caricature, and intermediate node is the caricature section, and leaf node is the caricature frame; Two parts about if optimal segmentation bundle of lines coma is divided into, then with the coma on the optimal segmentation line right side as left subtree, the coma on the optimal segmentation line left side is as right subtree; If optimal segmentation bundle of lines coma is divided into up and down two parts, then the coma above the optimal segmentation line as left subtree, the coma below the optimal segmentation line is as right subtree; If certain coma does not have the optimal segmentation line, the image that then this coma is corresponding is the caricature frame, does not have child node, no longer it is cut apart; According to the method described above each coma all is stored in the binary tree, all leaves of the binary tree that obtains are all caricature frames, and the reading order of caricature frame is putting in order of corresponding leaf from left to right.
The caricature coma method that binary tree stores reading order from left to right is following:
Define a binary tree, the relation of binary tree and caricature coma is that a coma is the node of binary tree, and root node is one page caricature, and intermediate node is the caricature section, and leaf node is the caricature frame; Two parts about if optimal segmentation bundle of lines coma is divided into, then with the coma on the optimal segmentation line left side as left subtree, the coma on the optimal segmentation line right side is as right subtree; If optimal segmentation bundle of lines coma is divided into up and down two parts, then the coma above the optimal segmentation line as left subtree, the coma below the optimal segmentation line is as right subtree; If certain coma does not have the optimal segmentation line, the image that then this coma is corresponding is the caricature frame, does not have child node, no longer it is cut apart; According to the method described above each coma all is stored in the binary tree, all leaves of the binary tree that obtains are all caricature frames, and the reading order of caricature frame is putting in order of corresponding leaf from left to right.
In the caricature pre-service, binaryzation, profile detect, image thinning is straight-line detection then, make that straight-line detection speed is faster; In cutting procedure, choose cut-off rule and select the optimal segmentation line, improved the accuracy rate that cut-off rule is chosen through weight; Utilize binary tree data structure to come each frame that constitutes a width of cloth caricature is stored and ordering, convenient to operation, practical; Whole proposal fast, accurately, efficiently.
Description of drawings
Fig. 1 is a process flow diagram of the present invention;
Fig. 2 (a) is cut apart synoptic diagram for caricature;
Fig. 2 (b) stores caricature frame schematic diagram for binary tree;
Fig. 3 gets synoptic diagram for the optimal segmentation line selection;
Fig. 4 is examination test result statistical form.
Embodiment
Below in conjunction with accompanying drawing the present invention is described further.
Be illustrated in figure 1 as process flow diagram of the present invention, may further comprise the steps:
A, given caricature page or leaf is done pre-service, comprising:
A, to said caricature page or leaf binaryzation, obtain binary image;
B, said binary image is made profile detect, obtain the foreground image of caricature page or leaf;
B, foreground image is made straight-line detection, obtain the straight line that comprises in the foreground image;
The quadrilateral structure body that obtains after C, the definition straight-line detection is coma; Coma is caricature frame or caricature section; Caricature is cut apart from the coma of maximum and is begun, if coma satisfies one of following condition, judges that then the picture that coma is indivisible and coma is corresponding is the caricature frame; Execution in step G, otherwise execution in step D;
A, coma inside do not have straight line;
Inner maximum foreground image area of b, coma and coma area ratio be less than threshold value m, wherein 0＜m＜0.25;
The ratio of the inner maximum foreground image areas pixel quantity of c, coma and all pixel quantities of coma inside is less than threshold value n, wherein 0＜n＜0.2;
The inner maximum foreground image areas of d, the coma length and width ratio corresponding with coma is less than threshold value p, 0.08＜p＜0.2;
D, from the straight line that straight-line detection is obtained, select cut-off rule, said cut-off rule must meet the following conditions:
A, said cut-off rule only with coma in two relative limits intersect, do not have intersection point with other limits;
The intersection point of b, said cut-off rule and coma is on the edge line of coma;
E, the descending of said cut-off rule by its weight screened one by one, select with other straight-line intersection numbers and be no more than 3 cut-off rule, be defined as the standard cut-off rule;
F, in the width range of each HW pixel of said standard cut-off rule both sides; Select non-intersect or maximum straight lines that intersection point is only arranged with two straight lines with other straight line; From these straight lines, select again one with the optimal segmentation position of the minimum straight line of foreground image number of hits as coma, be defined as the optimal segmentation line; If can not select qualified optimal segmentation line, return step e, select the satisfactory optimal segmentation line of next bar according to the weight of said cut-off rule;
G, employing binary tree data structure store the coma through dividing processing according to the reading order of caricature, and the coma had here both comprised the coma of cutting apart, and also comprised cutting apart the coma that the back produces, and also comprised indivisible coma;
H, according to the optimal segmentation line caricature page or leaf is done to cut apart for the first time after, the caricature section that produces cutting apart of using the same method continues to cut apart and stores the coma of new generation, till not having alienable coma, one page caricature cut apart completion.Wherein, definition as follows, caricature frame: the minimal graph blade unit that can not cut apart again in every page of caricature.Caricature section: the quadrilateral of forming by at least two continuous caricature frames.
Utilize binary tree storage caricature frame structure, judging that with the people caricature ordering has identical principle.The corresponding one page caricature of binary tree.Root node is used for storing one whole page of caricature, at first is divided into two parts to caricature, is placed in the left and right sides subtree of root node.Part to every stalk tree continues to cut apart, and to the last all cuts apart completion.Last result, the caricature frame of promptly cutting apart completion is kept in the leaf node of binary tree.
Shown in Fig. 2 (a); Straight line a, b, c, d are that four optimal segmentation bundle of lines caricatures are divided into (1), (2), (3), (4), (5) five caricature frames; Binary tree shown in Fig. 2 (b) stores above-mentioned five caricature frames as follows: at first regard a whole width of cloth caricature as tree root, be expressed as A, A is made up of two parts; Be part and the following part above the optimal segmentation line a, represent with B, C respectively.Adopt the method for recurrence, E, D two parts about B is divided into by optimal segmentation line c, C is divided into F, G two parts up and down by optimal segmentation line d, and it is leaf that F, G can not divide again.Last optimal segmentation line c is divided into last M up and down, two leaves of N to E.We can represent a binary tree with the form of bracket, i.e. (A (B (D, E (M, N)), C (F, G)))
We adopt binary tree data structure each frame of ordering storage caricature according to caricature, can directly sort to caricature.Here we with Japanese caricature arrange (reading order is for from right to left, from top to bottom) rule for example, we deposit each frame with binary tree according to following rule:
(a) if the optimal segmentation line rolls off the production line on being: need be the part above the optimal segmentation line as left subtree, for example the B among Fig. 2 (b), F, M part are all in the left subtree part; As right subtree, for example the C among Fig. 2 (b), G, N part are all in the right subtree part the part below the optimal segmentation line.
(b) if the optimal segmentation line is a left and right sides line: need the part on the optimal segmentation line right side as left subtree, for example the D part among Fig. 2 (b); The part below the optimal segmentation line as right subtree, the E part among Fig. 2 (b) for example.
All leaves of the binary tree of depositing according to above-mentioned rule are final segmentation result, and have from left to right sequenced order.All leafy nodes of binary tree are final segmentation result among Fig. 2 (b), and reading order is D, M, N, F, G, just in time are (1) (2) (3) (4) (5) according to the ordering of frame.If the reading habit of caricature (changes into from left to right) for from right to left, like homemade caricature, profit uses the same method and cuts apart ordering and get final product, and only needs the caricature frame storage location transposing on optimal segmentation line both sides, the left and right sides is got final product.
Standard cut-off rule as shown in Figure 3, that straight line x finds for us, but for fear of damaging the content of caricature, we are separated with it at the local straight line y place of the blank on its right, and y is the optimal segmentation line.
The selection of optimal segmentation line position: about current straight line in the scope of (or up and down) HW; In the straight line group parallel with current standard cut-off rule; Filter out surpassing 2 straight line with other straight-line intersection quantity, the straight line that is left so all is non-intersect or the line of intersection point only arranged with one or two straight lines with other straight lines.In these straight lines, select one to intersect with foreground pixel and to count minimum straight line again as the optimal segmentation line.To the threshold value of the ratio of division under three kinds of situation of alternative cut-off rule separate provision, wherein ratio of division refers to the physical length of cut-off rule and the ratio of the theoretical length of cut-off rule.Because the centre is not blocked, and its physical length is consistent with theoretical length, ratio of division is 1 like Fig. 3 cathetus m, n.If the middle intercepted situation of cut-off rule occurs, then ratio of division is less than 1.Define the ratio of division of alternative cut-off rule; There is not the cut-off rule ratio of division of intersection point to be defined as RATIO with other straight lines; Have only the cut-off rule ratio of division of an intersection point to be defined as RATIO1 with other straight lines, have the cut-off rule ratio of division of two intersection points to be defined as RATIO2 with other straight lines.If alternative cut-off rule and other straight lines do not have intersection point, we select one to intersect cut-off rule minimum, that ratio of division surpasses RATIO as the optimal segmentation line with prospect so.If alternative cut-off rule and other straight lines have only an intersection point, we select one to intersect cut-off rule minimum, that ratio of division surpasses RATIO1 as the optimal segmentation line with prospect so.If alternative cut-off rule and other straight lines have two intersection points, we select one to intersect cut-off rule minimum, that ratio of division surpasses RATIO2 as the optimal segmentation line with prospect so.Wherein the scope of RATIO is 0.45-0.55, and the RATIO1 scope is 0.7-0.8, and the RATIO2 scope is 0.5-0.6.After the particular location of optimal segmentation line was confirmed, we can cut apart according to this position.If neither one meets the split position of above requirement, return so and continue the choice criteria cut-off rule.Cut-off rule of choosing and the cut-off rule that is excluded are labeled as and use, and upgrade spendable cut-off rule tabulation.
Caricature picture pre-service concrete grammar is following:
Binaryzation: all pictures that the present invention uses all are the pictures after the binaryzation, and the binaryzation of image helps the further processing of image, and image is become simply, and data volume reduces, and can highlight the profile of interested target.Carry out the processing and the analysis of bianry image, at first will obtain binary image to the gray level image binaryzation.The all images of using in the present invention all is the caricature picture after the binaryzation.The present invention has used according to certain rule and from the method that grey level histogram extracts optimal threshold image carried out binaryzation, and method is following: the present invention has used a printenv of NOBUYUKI OTSU proposition and the image segmentation threshold value system of selection of non-supervision to the binaryzation of image
[9]Through selecting a threshold value to come to be set to 0 less than the pixel value of threshold value, be set to 1 greater than the pixel value of this threshold value, be exactly the binaryzation of a width of cloth picture like this.The method that we use can maximize the separation property of gray level classification results, can obtain the threshold value an of the best through this judgment criteria.Process is very simple, only utilizes 0 rank and the 1 rank accumulation square of grey level histogram, because the binaryzation employing is prior art, concrete grammar repeats no more.
Profile detects: in the image pre-service, often need make tracking processing to object edge, also make profile follow the tracks of.As its name suggests, profile is followed the tracks of through finding out marginal point comes lock-on boundary in proper order.In the choosing of cut-off rule; Need to judge the intersection point quantity of cut-off rule and foreground image, the cartoon image of the present invention after to binaryzation done profile and detected the foreground image in the detection caricature; When judging foreground image and cut-off rule intersection point, for choosing of cut-off rule played vital role.The more important thing is that profile detects the back and from profile, carries out straight-line detection, thereby saved the step that is detected a little, only need the pixel on the profile is calculated, for straight-line detection has reduced a large amount of calculating.Because what adopt is prior art, no longer carefully states.
Image thinning: image thinning generally occurs as a kind of image preconditioning technique; Purpose is the skeleton of extraction source image; Promptly be line thickness in the original image to be refined into greater than the lines of 1 pixel have only a pixel wide; Form on " skeleton ", can be relatively easy to analysis image behind the formation skeleton, as extracting the characteristic of image.The refinement basic thought is " depriving layer by layer ", promptly begins in layer to deprive inwards from line edge, till the surplus next pixel of lines.Image thinning has compressed original image ground data volume widely, and keeps the basic topological structure of its shape constant, thereby lays a good foundation for the application such as feature extraction of image.The present invention extracts the back at profile and image is carried out refinement makes the quantity of our calculating prospect and cut-off rule intersection point reduce greatly; Because the intersection point of all cut-off rules and foreground image is proportional minimizing, can't have influence on the situation that we judge cut-off rule simultaneously.
Straight-line detection: adopt following technology, because be prior art, only briefly introduce here: the cut-off rule in the caricature is that the decision caricature is cut apart the situation key point.Cutting apart of caricature need at first detect straight line, and the characteristics through straight line judge whether to be cut-off rule then, and specifically how to cut apart.If the straight line that detects is very few, will make caricature " leaked and divide ", the straight line that detects is too many or inaccurate, can make cutting procedure do a large amount of judgment tasks, causes " the wrong branch " easily.Come the correct cut-off rule that detects to make cutting procedure simplify greatly and accurately so find out a kind of suitable line detection method.The Hough conversion is from image, to discern one of basic skills of geometric configuration in the Flame Image Process, and promptly it can detect the target of known form, and the influence that be interrupted by noise and curve is little.Hough straight-line detection technology is because its is widely used to robustness of noise and misdata, and it is higher still to assess the cost, thus to bigger picture can not be real-time execution.The present invention has adopted the Hough line detection method after a kind of the improvement.Kernel-based Hough transform (KHT) method by Leandro A.F.Fernandes and Manuel M.Oliveira propose is come detection of straight lines.This method be much smaller than Hough straight-line detection method expense, but accuracy is higher owing to earlier the pixel groups cluster collection of about conllinear, choosing wherein the most identical straight line then.Straight-line detection of the present invention is behind image binaryzation, image is carried out profile detect, and profile has been done carried out on the basis of micronization processes then, so the straight-line detection speed among the present invention will be faster.
For some irregular picture, the present invention has designed artificial auxiliary method, and to make picture cut apart more accurate.Adopt the preferential method that detects artificial straight line that the straight line of manual interpolation is judged.
Test result: wherein experimental result is seen Fig. 4, and is successful 184, failed 16, undue 2, divide 13 less, and 1 of wrong branch has reached 92% success ratio.926 seconds computing machine times spent, promptly every needs 4.633 seconds time.Efficient is 0.215/second.
Certainly; The present invention also can have other various embodiments; Under the situation that does not deviate from spirit of the present invention and essence thereof; Those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection domain of the appended claim of the present invention.
Claims (10)
1. the caricature frame based on cut-off rule is discerned and auto ordering method, it is characterized in that this method may further comprise the steps:
A, given caricature page or leaf is done pre-service, comprising:
A, to said caricature page or leaf binaryzation, obtain binary image;
B, said binary image is made profile detect, obtain the foreground image of caricature page or leaf;
B, foreground image is made straight-line detection, obtain the straight line that comprises in the foreground image;
The quadrilateral structure body that C, definition are obtained after the straight-line detection is coma, and coma is caricature frame or caricature section, and wherein the caricature frame refers to minimal graph blade unit in every page of caricature, and the caricature section refers to the quadrilateral be made up of at least two continuous caricature frames; Caricature is cut apart from the coma of maximum and is begun, if coma satisfies one of following condition, judges that then the picture that coma is indivisible and coma is corresponding is the caricature frame, execution in step G, otherwise execution in step D, and wherein the caricature frame refers to minimal graph blade unit in every page of caricature;
A, coma inside do not have straight line;
B, the inner maximum foreground image area of coma and coma area ratio are less than threshold value m;
The ratio of c, the inner maximum foreground image areas pixel quantity of coma and inner all pixel quantities of coma is less than threshold value n;
The inner maximum foreground image areas of d, the coma length and width ratio corresponding with coma is less than threshold value p;
D, from the straight line that straight-line detection is obtained, select cut-off rule, said cut-off rule must meet the following conditions:
A, said cut-off rule only with coma in two relative limits intersect, do not have intersection point with other limits;
The intersection point of b, said cut-off rule and coma is on the edge line of coma;
E, the descending of said cut-off rule by its weight screened one by one, select with other straight-line intersection numbers smaller or equal to 3 cut-off rule, be defined as the standard cut-off rule;
F, in the width range of each HW pixel of said standard cut-off rule both sides; Select non-intersect or maximum straight lines that intersection point is only arranged with two straight lines with other straight line; From these straight lines, select again one with the optimal segmentation position of the minimum straight line of foreground image number of hits as coma, be defined as the optimal segmentation line; If can not select qualified optimal segmentation line, return step e, select the satisfactory optimal segmentation line of next bar according to the weight of said cut-off rule;
G, employing binary tree data structure store coma according to the reading order of caricature, and the coma had here both comprised the coma of cutting apart, and also comprised cutting apart the coma that the back produces, and also comprised indivisible coma;
H, according to the optimal segmentation line caricature page or leaf is done to cut apart for the first time after, the caricature section that produces cutting apart of using the same method continues to cut apart and stores the coma of new generation, till not having alienable coma, one page caricature cut apart completion.
2. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1; It is characterized in that: the image segmentation threshold value system of selection of adopting printenv and non-supervision is to said caricature page or leaf binaryzation; Through selecting a threshold value to come to be set to 0, be set to 1 greater than the pixel value of this threshold value less than the pixel value of threshold value.
3. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1; It is characterized in that: the caricature page or leaf foreground image that obtains after profile is detected; Make micronization processes before the straight-line detection, line thickness in the foreground image is refined into greater than the lines of 1 pixel has only a pixel wide.
4. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1, it is characterized in that: the scope of said threshold value m is: 0＜m＜0.25.
5. identification of caricature frame and the auto ordering method based on cut-off rule according to claim 1, it is characterized in that: the scope of said threshold value n is: 0＜n＜0.2 wherein.
6. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1, it is characterized in that: the scope of said threshold value p is: 0.08＜p＜0.2.
7. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1; It is characterized in that: judge whether coma inside has the method for straight line to be: if straight line falls into the inner amount of pixels of coma half the less than straight line pixel total amount; Think that then this straight line is not inner at coma, otherwise think that this straight line is inner at coma.
8. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1 is characterized in that: adopt Kernel-based Hough transform method to make the weight of straight-line detection, also definite cut-off rule.
9. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1, it is characterized in that: the method for reading order coma is to adopt binary tree data structure to store from right to left:
Define a binary tree, the relation of binary tree and caricature coma is that a coma is the node of binary tree, and root node is one page caricature, and intermediate node is the caricature section, and leaf node is the caricature frame; Two parts about if optimal segmentation bundle of lines coma is divided into, then with the coma on the optimal segmentation line right side as left subtree, the coma on the optimal segmentation line left side is as right subtree; If optimal segmentation bundle of lines coma is divided into up and down two parts, then the coma above the optimal segmentation line as left subtree, the coma below the optimal segmentation line is as right subtree; If certain coma does not have the optimal segmentation line, the image that then this coma is corresponding is the caricature frame, does not have child node, no longer it is cut apart; According to the method described above each coma all is stored in the binary tree, all leaves of the binary tree that obtains are all caricature frames, and the reading order of caricature frame is putting in order of corresponding leaf from left to right.
10. identification of caricature frame and auto ordering method based on cut-off rule according to claim 1, it is characterized in that: the caricature coma method of reading order is to adopt binary tree data structure to store from left to right:
Define a binary tree, the relation of binary tree and caricature coma is that a coma is the node of binary tree, and root node is one page caricature, and intermediate node is the caricature section, and leaf node is the caricature frame; Two parts about if optimal segmentation bundle of lines coma is divided into, then with the coma on the optimal segmentation line left side as left subtree, the coma on the optimal segmentation line right side is as right subtree; If optimal segmentation bundle of lines coma is divided into up and down two parts, then the coma above the optimal segmentation line as left subtree, the coma below the optimal segmentation line is as right subtree; If certain coma does not have the optimal segmentation line, the image that then this coma is corresponding is the caricature frame, does not have child node, no longer it is cut apart; According to the method described above each coma all is stored in the binary tree, all leaves of the binary tree that obtains are all caricature frames, and the reading order of caricature frame is putting in order of corresponding leaf from left to right.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210120164.9A CN102708371B (en) | 2012-04-23 | 2012-04-23 | Method for recognizing and automatically sequencing comic frames according to segmenting lines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210120164.9A CN102708371B (en) | 2012-04-23 | 2012-04-23 | Method for recognizing and automatically sequencing comic frames according to segmenting lines |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102708371A true CN102708371A (en) | 2012-10-03 |
| CN102708371B CN102708371B (en) | 2014-04-30 |
Family
ID=46901114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210120164.9A Expired - Fee Related CN102708371B (en) | 2012-04-23 | 2012-04-23 | Method for recognizing and automatically sequencing comic frames according to segmenting lines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102708371B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105208183A (en) * | 2014-06-27 | 2015-12-30 | 上海玄霆娱乐信息科技有限公司 | Method enabling electronic device to display cartoons |
| CN105574524A (en) * | 2015-12-11 | 2016-05-11 | 北京大学 | Cartoon image page identification method and system based on dialogue and storyboard united identification |
| CN109902541A (en) * | 2017-12-10 | 2019-06-18 | 彼乐智慧科技（北京）有限公司 | A kind of method and system of image recognition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866418A (en) * | 2009-04-17 | 2010-10-20 | 株式会社理光 | Method and equipment for determining file reading sequences |
| CN102184378A (en) * | 2011-04-27 | 2011-09-14 | 茂名职业技术学院 | Method for cutting portable data file (PDF) 417 standard two-dimensional bar code image |
-
2012
- 2012-04-23 CN CN201210120164.9A patent/CN102708371B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866418A (en) * | 2009-04-17 | 2010-10-20 | 株式会社理光 | Method and equipment for determining file reading sequences |
| CN102184378A (en) * | 2011-04-27 | 2011-09-14 | 茂名职业技术学院 | Method for cutting portable data file (PDF) 417 standard two-dimensional bar code image |
Non-Patent Citations (2)
| Title |
|---|
| 20071231 Takamasa Tanaka et al Layout Analysis of Tree-Structured Scene Frames in Comic Images , * |
| TAKAMASA TANAKA ET AL: "Layout Analysis of Tree-Structured Scene Frames in Comic Images", <IJCAI’07 PROCEEDINGS OF THE 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICAL INTELLIGENCE>, 31 December 2007 (2007-12-31) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105208183A (en) * | 2014-06-27 | 2015-12-30 | 上海玄霆娱乐信息科技有限公司 | Method enabling electronic device to display cartoons |
| CN105208183B (en) * | 2014-06-27 | 2018-11-02 | 上海玄霆娱乐信息科技有限公司 | The method that electronic equipment shows caricature |
| CN105574524A (en) * | 2015-12-11 | 2016-05-11 | 北京大学 | Cartoon image page identification method and system based on dialogue and storyboard united identification |
| CN105574524B (en) * | 2015-12-11 | 2018-10-19 | 北京大学 | Based on dialogue and divide the mirror cartoon image template recognition method and system that joint identifies |
| CN109902541A (en) * | 2017-12-10 | 2019-06-18 | 彼乐智慧科技（北京）有限公司 | A kind of method and system of image recognition |
| CN109902541B (en) * | 2017-12-10 | 2020-12-15 | 彼乐智慧科技（北京）有限公司 | Image recognition method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102708371B (en) | 2014-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Plant diseases recognition based on image processing technology | |
| CN108537146B (en) | Print form and handwriting mixed text line extraction system | |
| CN102663382B (en) | Video image character recognition method based on submesh characteristic adaptive weighting | |
| CN102509319B (en) | Method for restoring Thangka image by combining shapes and neighborhood classification of damaged piece | |
| CN110321769A (en) | A kind of more size commodity on shelf detection methods | |
| CN103020618B (en) | The detection method of video image character and system | |
| CN112200117B (en) | Form identification method and device | |
| CN110378239A (en) | A kind of real-time traffic marker detection method based on deep learning | |
| CN101944109A (en) | System and method for extracting picture abstract based on page partitioning | |
| CN102426647A (en) | Station identification method and device | |
| Murdock et al. | ICDAR 2015 competition on text line detection in historical documents | |
| CN101694720B (en) | Multidate SAR image change detection method based on space associated conditional probability fusion | |
| CN111091095A (en) | Method for detecting ship target in remote sensing image | |
| CN104244073A (en) | Automatic detecting and recognizing method of scroll captions in videos | |
| CN103093208A (en) | Method and system for fruit and vegetable recognition | |
| CN114529773A (en) | Form identification method, system, terminal and medium based on structural unit | |
| CN102708371B (en) | Method for recognizing and automatically sequencing comic frames according to segmenting lines | |
| CN110428438A (en) | A kind of single wooden modeling method, device and storage medium | |
| KR20180020421A (en) | Method and system for extracting coastline based on a large-scale high-resolution satellite images | |
| CN111652140A (en) | Method, device, equipment and medium for accurately segmenting questions based on deep learning | |
| CN110942102B (en) | Probability relaxation epipolar matching method and system | |
| CN103207997B (en) | Kernel density estimation-based license plate character segmentation method | |
| CN111488847A (en) | System, method and terminal for acquiring sports game video goal segment | |
| CN101600115A (en) | A kind of method of eliminating periodic characteristic block of image stabilization system | |
| CN101615255B (en) | Video text multi-frame interfusion method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140430 Termination date: 20150423 |
|
| EXPY | Termination of patent right or utility model |