CN101122999B - Method for automatically extracting stamp image from Chinese painting and calligraphy - Google Patents
Method for automatically extracting stamp image from Chinese painting and calligraphy Download PDFInfo
- Publication number
- CN101122999B CN101122999B CN2007101439463A CN200710143946A CN101122999B CN 101122999 B CN101122999 B CN 101122999B CN 2007101439463 A CN2007101439463 A CN 2007101439463A CN 200710143946 A CN200710143946 A CN 200710143946A CN 101122999 B CN101122999 B CN 101122999B
- Authority
- CN
- China
- Prior art keywords
- image
- color
- seal
- information
- described image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Analysis (AREA)
- Facsimile Image Signal Circuits (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention relates to a method of automatic extracting seal image from Chinese handwriting and drawing works, and the method comprises following steps: The L*a*b* component color analysis and the method of mapping the analysis results to the RGB color space are used to filter the non-red color information from the target image; The remained information of the image is de-noised; The non-seal information in the remained information of the image is eliminated using the geometrical region based secondary splitting and filtering method, the communication region based image filtering method andthe margin detection method; and the existing position corresponding relations between the rectangle L3 and the Chinese handwriting and drawing works are used for image splitting and extracting. The invention provides a method of accurate and automatic extracting all seal image information from a part of or the whole part of a digital image of Chinese handwriting and drawing works, so the invention establishes a foundation for realizing contents-based Chinese handwriting and drawing work image indexing system with the seal image as the key information. The invention can be widely used in the field of cultural relic digitalization.
Description
Technical field
The present invention relates to a kind of image extraction method, the method for seal image in particularly a kind of automatic extraction Chinese Painting and Calligraphy works.
Background technology
Seal in the Chinese Painting and Calligraphy works has important artistic and is worth, and is inalienable part in the painting and calligraphy pieces, the retrieval and the appreciation that help to realize the painting and calligraphy pieces relevant information by discriminating and retrieval to seal image in the painting and calligraphy pieces.
Image retrieval technologies has been individual very active subject since the seventies from twentieth century always.Up to the present, retrieval technique mainly contains two kinds: based on the retrieval technique and the content-based retrieval technology of semanteme.Early stage image retrieval is based on the retrieval of semanteme (image keyword), this search method needs manually every width of cloth image to be marked by its content, then markup information is deposited the retrieval that is used in the text database afterwards, along with increasing of image, artificial mark is difficulty very, and everyone can cause the subjectivity of mark strong excessively to the understanding difference of picture material, is unfavorable for user search.Twentieth century is after the nineties, the research emphasis of image retrieval is based on retrieval (the Content Based Image Retrieval of picture material, CBIR), promptly find out the process that satisfies the image that a certain specific visual signature describes in database, its basic thought is to retrieve by the visual signature of analysis image and contextual relation.This technology uses specific algorithm and technological means to comprise the position of the visual properties of picture material such as color, texture, shape, object and mutual relationship etc. by Computer Automatic Extraction, and deposit a stack features of the mutual difference of the different images that extracts in image feature base, by image in the database is carried out similar coupling with the query sample image at feature space, retrieve the image similar to sample.
Since the nineties in 20th century, the research of CBIR and be applied in and obtained significant progress abroad, some famous image indexing systems are pushed out in succession: QBIC (Query By Image Content) image indexing system is the image and the dynamic scene searching system of the IBM Corporation's exploitation and composition nineties, is first content-based business-like image indexing system; VIR Image Engine is the CBIR engine by the exploitation of Virage company, and it also supports the image retrieval based on visual signatures such as color, color layout, texture and structures simultaneously; RetrievalWare is by a kind of CBIR instrument of Excal ibur Science and Technology Ltd. exploitation, and the retrieval based on color, shape, texture, color structure, brightness structure and 6 kinds of image attributes of aspect ratio is provided; Photobook be Massachusetts Institute Technology the multimedia development in laboratory be used for image querying and the interactive tool browsed, the user can carry out respectively in three subsystems based on shape, based on texture with based on the image retrieval of facial characteristics; The Vi sualSEEK of Columbia University exploitation and WebSEEK are based on visual signature respectively and towards the gopher of text or the image of WWW.
At home, Tsing-Hua University is in the prototype system of the information retrieval based on contents of developing the still image on the Internet in 1997, the multimedia information retrieval system based on feature has been studied by Inst. of Computing Techn. Academia Sinica, and Beijing Huaqi IDTC view data intellectual technology company limited has researched and developed the image intelligent retrieval software and can retrieve by the picture material of design patent.
In the historical relic field, along with going deep into of cultural relic digitalization, a large amount of historical relic images are preserved by the form with digital picture, how can realize historical relic image and relevant information detected one of core topic that becomes field of cultural relic digitalization by image itself (or its sketch).Just the related data that retrieves is at present seen, does not find the relevant report about seal image automatic extracting method in the Chinese Painting and Calligraphy works both at home and abroad as yet.
Consider the special status of seal in painting and calligraphy pieces, utilize the seal information that extracts to retrieve, will improve the precision of retrieval greatly.The Chinese Painting and Calligraphy works are of long standing and well established, the influence of the factors such as external force effect the when seal in the painting and calligraphy pieces is subjected to the material, official seal lid dynamics of age, material, red ink paste used for seals, seal character literary composition, quarter method, shape, font, painting and calligraphy pieces and paper has brought certain difficulty for the extraction of seal image.At present, the research for seal image digitizing field also only limits to " official seal ", accounting and corporate seal's research.Be placed on the identification and the extraction of the seal image in the modern document for these official seals, because its background is simple relatively, and than being easier to realization.For the extraction and the identification of seal image in the Chinese Painting and Calligraphy works, the extracting method of above-mentioned " official seal " then can not play due effect.
Summary of the invention
At the problems referred to above, the purpose of this invention is to provide a kind of method of from the digital picture of view picture painting and calligraphy pieces or local painting and calligraphy pieces, extracting seal image exactly automatically.
For achieving the above object, the present invention takes following technical scheme: the method for seal image in a kind of automatic extraction Chinese Painting and Calligraphy works is characterized in that: it comprises the steps: that (1) utilizes based on L
*a
*b
*Component color is analyzed, with and analysis result non-red color information in the mapping method filtering target digital image of RGB color space; (2) noise that comprises in the described image remaining information is handled; (3) non-seal information in the described image remaining information after noise processed is rejected: adopt based on the secondary splitting of geometric areas and the method for filtration, reject the low-density colouring information in the described image; Employing is based on the image filtering method of connected region, reject residual image part area occupied in the described image much larger than with image information much smaller than the seal possible range; Adopt edge detection method that the non-seal color region of high density of residual image part in the described image is converted into density regions; Adopt describedly based on the secondary splitting of geometric areas and the method for filtration once more, that rejects described image is converted into low-density colouring information by high density; (4) described image is cut apart, extracted seal.
Described image is carried out the conversion of color space, promptly by the RGB color space conversion to the XYZ color space, again by the XYZ color space conversion to L
*a
*b
*Color space:
a
*=500(f(X/Y
n)-f(Y/Y
n))
b
*=200(f(Y/Y
n)-f(Z/Z
n))
Wherein, k
r, k
gAnd k
bBe scale-up factor, x
r, x
g, x
b, y
r, y
g, y
b, z
r, z
g, z
bBe the coordinate of the red, green and blue in the xyY of the International Commission on Illumination chromatic diagram, X
n, Y
nAnd Z
nBe in the international coordinated system of XYZ with reference to the tristimulus values of white light, X, Y, Z and R, G, B are respectively the corresponding color component in the color space separately, L
*, a
*, b
*Be L
*a
*b
*Each component in the color space, f (t) is as follows:
According to the general visual sense characteristic of seal image in the Chinese Painting and Calligraphy works, reject the background image of colder tone in the described image: a is set for greater than 0 adjustable real number value, b is the set of absolute value less than 120 any real numbers, utilizes L then
*a
*b
*The component color analysis result shines upon described image on the RGB color space, promptly works as b
*Color is not in b or a
*Color is picked out during less than a, realizes to visual sense in the described image be the filtration of the information of redness.
Described based on geometric areas secondary splitting and the method for filtration comprise the steps: that (1) is divided into some rectangular areas with described image by the step value of setting, and calculate each field color density; (2) with center, the regional point of crossing divided first, described image is carried out second zone divide and calculate each regional color density as the rectangular area; (3) color density of the described image Zone Full of determining twice division and being obtained, obtain the color density matrix, L1 is the color density matrix of the area dividing first time, L2 is the color density matrix of the area dividing second time, when color density value during greater than the color density threshold values, corresponding matrix element value is 1, otherwise is 0; (4) will correspond to the adjacent grid matrix value of 1 element and be filled to 1 among the L1 with among the L2, obtained a new matrix L 3 that in L1, adds the L2 corresponding informance, keep matrix value among the L3 and be the correspondence image zone of 1 element representative, reject the L3 intermediate value and be the correspondence image zone of 0 element representative.
The present invention is owing to take above technical scheme, it has the following advantages: 1, owing to the invention provides a kind of method that can from view picture painting and calligraphy pieces or local painting and calligraphy pieces digital picture, extract the seal image full detail exactly automatically, think that realization is that the content-based Chinese Painting and Calligraphy works image indexing system of key message is laid a good foundation with the seal image.2, the invention provides a kind of based on L
*a
*b
*Component color is analyzed, with and analysis result to the mapping method of RGB color space, think that the extraction of red image information in visual perception's seal color gamut scope provides a kind of basic ideas and method.3, the invention provides a kind of secondary splitting and filter method, realized comprising the filtration of seal frame based on geometric areas, think that the extraction of seal image provides a kind of research mode based on color and architectural feature.The present invention can be widely used in field of cultural relic digitalization.
Description of drawings
Fig. 1 is the schematic flow sheet of the inventive method
Fig. 2 is that the inventive method is based on L
*a
*b
*Image before component color is filtered
Fig. 3 is that the inventive method is based on L
*a
*b
*Image after component color is filtered
Fig. 4 is the image before the inventive method is carried out noise processed
Fig. 5 is the image after the inventive method is carried out noise processed
Fig. 6 is the inventive method is carried out twice geometric areas division to image a synoptic diagram
Fig. 7 is the graph of a relation between zone of dividing for the first time and the zone of dividing for the second time
Fig. 8 is the color density matrix L 1 of the inventive method geometric areas division for the first time
Fig. 9 is the color density matrix L 2 of the inventive method geometric areas division for the second time
Figure 10 is that the value among the inventive method L2 concerns synoptic diagram to the influence of value among the L1
Figure 11 is that the inventive method adds the new matrix L 3 that L2 influence back obtains in L1
Figure 12 is the seal image that adopts the inventive method to extract
Figure 13 is former Qi's of the artist king of the Qing Dynasty of selecting for use of the present invention a width of cloth landscape painting (part)
Figure 14 is the seal image that adopts the inventive method to extract from embodiment illustrated in fig. 13
The system chart of the Chinese Painting and Calligraphy works retrieval that the inventive method that is based on Figure 15 realizes
Embodiment
Below in conjunction with drawings and Examples, the inventive method is described in detail.
The inventive method is obtained a width of cloth by conventional method and is comprised the Chinese Painting and Calligraphy works of seal information or the digital picture of works part, utilizes a kind of Flame Image Process combined method, and the seal image in the centering state painting and calligraphy pieces is discerned, and extracts one by one.
As shown in Figure 1, the seal image extracting method comprises the steps:
1, utilizes based on L
*a
*b
*Component color is analyzed, with and analysis result non-red color information in the mapping method filtering target image of RGB color space;
2, the noise that comprises in the image remaining information is handled;
3, non-seal information in the image remaining information is rejected;
4, image segmentation is extracted seal.
The RGB color space is generally all adopted in the description of color of image in the computing machine.Though include the R component in the RGB color space, can't utilize it that " red " color in the visual experience is filtered.So the image mapped under the RGB color space is arrived L
*a
*b
*Color space is by analyzing a
*And b
*Component to be to realize the filtration to color of object, wherein+and a
*Expression is red ,-a
*Expression is green ,+b
*Expression is yellow ,-b
*Expression is blue, and the lightness of color is by L
*Percentage represent.The image that the user is submitted to carries out the conversion of color space, promptly by the RGB color space conversion to the XYZ color space, arrive L again
*a
*b
*Color space:
Wherein, k
r, k
gAnd k
bBe scale-up factor, x
r, x
g, x
b, y
r, y
g, y
b, z
r, z
g, z
bBe the coordinate of the red, green and blue in International Commission on Illumination (CIE:International Commission on Illumination) the xyY chromatic diagram, X
n, Y
nAnd Z
nBe with reference to the tristimulus values of white light in the international coordinated system of XYZ.Based on following formula, can further draw ITU-R BT.601 under light source C by the transformational relation of RGB color space to the XYZ color space:
Wherein, X, Y, Z and R, G, B are respectively the corresponding color component in the color space separately, are transformed into L by XYZ again
*a
*b
*:
a
*=500(f(X/X
n)-f(Y/Y
n))
b
*=200(f(Y/Y
n)-f(Z/Z
n))
Wherein, L
*, a
*, b
*Be L
*a
*b
*Each component in the color space, f (t) is as follows:
According to the general visual sense characteristic of seal image in the Chinese Painting and Calligraphy works, the background image of colder tone in the image is rejected.Two threshold values a, b are set, and a is the real number value (adjustable, round numbers usually) greater than 0, and b is the set of absolute value less than 120 any real numbers, as a certain pixel b
*Color is not in b or a
*Color is picked out during less than a, utilize the result after filtering on the RGB color space, image to be shone upon then, can realize the filtration (as Fig. 2, shown in Figure 3, wherein Fig. 2 be effect image filtering before, Fig. 3 be effect image filtering after) of visual sense in the image for red information.
Because the influence of factors such as the pigment of painting and calligraphy pieces, material, preservation condition and bag slurry, image packets after above-mentioned steps is handled contains certain noise, need to handle according to actual conditions, can select one of one or more filter methods such as sef-adapting filter, median filter and Gaussian filter etc. or their combination for use, also can design voluntarily according to actual needs (as Fig. 4, shown in Figure 5, wherein Fig. 4 is the effect before the filtering, and Fig. 5 is filtered effect).
In the filtered image information, red part differs, and to establish a capital be seal image, the red part of non-seal information is for comprising a large amount of low distribution density red information and the image-region of high distribution density red information, seal information distribution density then falls between, and therefore also needs further non-seal information to be rejected.
Employing is rejected the low-density colouring information based on the secondary splitting of geometric areas and the method for filtration.Experiment shows that (this threshold values is the experience setting value that obtains through after a large amount of experiments to color density less than a certain threshold values, it can be adjusted accordingly according to the concavo-convex body proportionate relationship of literal on the seal or image) the zone can not include seal information, so entire image is divided into some rectangular areas by the step value of setting, then color density is calculated in each zone respectively.Seal information is separated when avoiding the zoning, cause segment seal information region to be used as non-seal zone and reject, former figure is carried out second zone divide.Secondary division is with the center as the rectangular area, the regional point of crossing divided first.For example, with image division be 3 * 3 zones (as Fig. 6, shown in Figure 7, wherein Fig. 6 is the effect of twice geometric areas division, and Fig. 7 is area shading part of dividing for the first time and the interregional corresponding relation of dividing the second time).In addition, area dividing can be determined the position of seal image in specific painting and calligraphy pieces, for the back seal image provides coordinate information.
Determine that twice division obtains the color density of image Zone Full, obtain the color density matrix, when color density value during greater than the color density threshold values, corresponding matrix element value is 1, otherwise is 0.If the color density matrix of geometric areas division for the first time is L1, the color density matrix of geometric areas division for the second time is L2.For example, with image division is that 4 * 4 rectangular area is (as Fig. 8, shown in Figure 9, wherein Fig. 8 is that geometric areas is divided the color matrix that obtains for the first time, the color matrix that Fig. 9 obtains for geometric areas division for the second time), the corresponding element value of element in L1 that among the L2 is 1 was filled to for 1 (as shown in figure 10), obtains a new matrix (as shown in figure 11) that in L1, has added the L2 corresponding informance.Be located at and added among the L1 that to correspond to the color matrix that is obtained behind 1 the element information among the L2 be L3.Matrix value is that the correspondence image field color density of 1 element representative has reached the requirement that may comprise seal image information among the L3, so keep the image information that it had; The L3 intermediate value is that the correspondence image field color density of 0 element representative does not reach the requirement that may comprise seal image information, so reject the image information in these zones.
After low-density colouring information is rejected, only contain the higher information of color density in the residual image, at first adopt image filtering method based on connected region, reject area occupied in the residual image much larger than with image information much smaller than the seal possible range, present embodiment adopts seed fill algorithm.At this moment, only include seal image and the isolated high density color image close in the image with the seal image size, but not the abundant structures information that seal image does not obviously possess seal image to be had.Adopt edge detection method such as Suo Beier (Sobel) operator, Roberts operator, Canny operator and Laplace operator etc., highdensity non-seal color region is converted into density regions, seal image still keeps certain density.Present embodiment adopts Canny rim detection to carry out edge of image and detects, and the seal part still possesses relatively abundanter characteristic information behind the crisperding, and those isolated high density color regions are weakened because of not possessing abundant marginal information.From the angle of information distribution, seal partly changes relative high density part into, and isolated high density color part then deteriorates to relative low-density part.Residual image is carried out adopting once more based on the secondary splitting of geometric areas and the method for filtration after marginal information extracts, reject former high density colouring information, and revise the value of respective element in the matrix L 3.
According to the position corresponding relation that exists between matrix L 3 and the painting and calligraphy pieces image, be identified as the area relative image boundary of seal among the identification L3 that can be more or less freely, and extract seal image (as shown in figure 12).
As shown in figure 13, three pieces of seal images that comprise in the width of cloth landscape painting (part) of present embodiment to former Qi of the Chinese artist king of the Qing Dynasty extract (as shown in figure 14), and extraction ratio can reach 100%.
The invention provides a kind of method that can from view picture painting and calligraphy pieces or painting and calligraphy pieces topography, extract the full detail of seal image exactly automatically, can realize a content-based Chinese Painting and Calligraphy works searching system (as shown in figure 15) of utilizing seal image as key message.A large amount of painting and calligraphy pieces are extracted characteristics of image and seal image feature and are stored in painting and calligraphy pieces feature database and seal storehouse respectively.Can inquire about (can be a width of cloth painting and calligraphy pieces or its topography) during user search according to demand, utilize seal information accurately to locate the painting and calligraphy pieces that is retrieved, and obtain the relevant information of these works.
Although disclose specific embodiments of the invention and accompanying drawing for the purpose of illustration, its purpose is to help to understand content of the present invention and implement according to this, but it will be appreciated by those skilled in the art that: without departing from the spirit and scope of the invention and the appended claims, various replacements, variation and modification all are possible.Therefore, the present invention should not be limited to most preferred embodiment and the disclosed content of accompanying drawing, and claimed scope is as the criterion with the scope that claims define.
Claims (2)
1. a method of extracting seal image in the Chinese Painting and Calligraphy works automatically is characterized in that it comprises the steps:
1) utilizes based on L
*a
*b
*Component color is analyzed, with and analysis result non-red color information in the mapping method filtering target digital image of RGB color space;
2) noise that comprises in the described image remaining information is handled;
3) non-seal information in the described image remaining information after noise processed is rejected: adopt based on the secondary splitting of geometric areas and the method for filtration, reject the low-density colouring information in the described image; Employing is based on the image filtering method of connected region, reject residual image part area occupied in the described image much larger than with image information much smaller than the seal possible range; Adopt edge detection method that the non-seal color region of high density of residual image part in the described image is converted into density regions; Adopt describedly based on the secondary splitting of geometric areas and the method for filtration once more, that rejects described image is converted into low-density colouring information by high density;
4) described image is cut apart, extracted seal;
Describedly comprise the steps: based on the secondary splitting of geometric areas and the method for filtration
(1) described image is divided into some rectangular areas by the step value of setting, and calculates each field color density;
(2) with center, the regional point of crossing divided first, described image is carried out second zone divide and calculate each regional color density as the rectangular area;
(3) color density of the described image Zone Full of determining twice division and being obtained, obtain the color density matrix, L1 is the color density matrix of the area dividing first time, L2 is the color density matrix of the area dividing second time, when color density value during greater than the color density threshold value, corresponding matrix element value is 1, otherwise is 0;
(4) will correspond to the adjacent grid matrix value of 1 element and be filled to 1 among the L1 with among the L2, obtained a new matrix L 3 that in L1, adds the L2 corresponding informance, keep matrix value among the L3 and be the correspondence image zone of 1 element representative, reject the L3 intermediate value and be the correspondence image zone of 0 element representative.
2. the method for seal image in a kind of automatic extraction Chinese Painting and Calligraphy works as claimed in claim 1 is characterized in that: described image is carried out the conversion of color space, promptly by the RGB color space conversion to the XYZ color space, again by the XYZ color space conversion to L
*a
*b
*Color space:
a
*=500×(f(X/X
n)-f(Y/Y
n))
b
*=200×(f(Y/Y
n)-f(Z/Z
n)
Wherein, k
r, k
gAnd k
bBe scale-up factor, x
r, x
g, x
b, y
r, y
g, y
b, z
r, z
g, z
bBe the coordinate of the red, green and blue in the xyY of the International Commission on Illumination chromatic diagram, X
n, Y
n, Z
nBe in the international coordinated system of XYZ with reference to the tristimulus values of white light, X, Y, Z and R, G, B are respectively the corresponding color component in the color space separately, L
*, a
*, b
*Be L
*a
*b
*Each component in the color space, f (t) is as follows:
According to the general visual sense characteristic of seal image in the Chinese Painting and Calligraphy works, reject the background image of colder tone in the described image: be provided with a for greater than 0 be real number value, b is the set of absolute value less than 120 any real numbers, utilizes L then
*a
*b
*The component color analysis result shines upon described image on the RGB color space, promptly works as b
*Color is not in b or a
*Color is picked out during less than a, realizes to visual sense in the described image be the filtration of the information of redness.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2007101439463A CN101122999B (en) | 2007-04-16 | 2007-08-15 | Method for automatically extracting stamp image from Chinese painting and calligraphy |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN200710090132 | 2007-04-16 | ||
CN200710090132.8 | 2007-04-16 | ||
CN2007101439463A CN101122999B (en) | 2007-04-16 | 2007-08-15 | Method for automatically extracting stamp image from Chinese painting and calligraphy |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101122999A CN101122999A (en) | 2008-02-13 |
CN101122999B true CN101122999B (en) | 2010-07-07 |
Family
ID=39085324
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2007101439463A Expired - Fee Related CN101122999B (en) | 2007-04-16 | 2007-08-15 | Method for automatically extracting stamp image from Chinese painting and calligraphy |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101122999B (en) |
Families Citing this family (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101556652B (en) * | 2009-04-15 | 2011-11-30 | 北京联合大学 | Chinese painting & calligraphy color layering analysis method based on machine learning |
CN101980200B (en) * | 2010-11-03 | 2013-09-04 | 东莞市高鑫机电科技服务有限公司 | Method and system for constructing Chinese element engineering database and application thereof in field of industrial design |
CN103049904B (en) * | 2012-11-30 | 2016-04-20 | 北京华夏力鸿商品检验有限公司 | A kind of image extraction method and system, digital certificates method for making and system thereof |
CN103414944B (en) * | 2013-07-16 | 2017-07-25 | 深圳Tcl新技术有限公司 | The method and apparatus of rapid preview file destination |
CN103413355B (en) * | 2013-07-31 | 2016-08-10 | 中国科学院遥感与数字地球研究所 | A kind of double geographical longitude and latitude grid cutting method |
CN104268199B (en) * | 2014-09-22 | 2017-05-31 | 江苏瑞丰信息技术股份有限公司 | A kind of image automatic annotation method based on Web social media |
CN104933682B (en) * | 2015-06-03 | 2018-07-06 | 浙江大学 | A kind of integrated denoising method of upright stone tablet class image |
CN107403405A (en) * | 2016-05-20 | 2017-11-28 | 富士通株式会社 | Image processing apparatus, image processing method and information processor |
JP6474756B2 (en) * | 2016-06-09 | 2019-02-27 | 本田技研工業株式会社 | Defect inspection method and apparatus |
CN109284758B (en) * | 2018-09-29 | 2021-11-16 | 武汉工程大学 | Invoice seal eliminating method and device and computer storage medium |
CN110378940B (en) * | 2019-06-17 | 2023-04-07 | 东南大学 | Aviation image feature point matching diffusion recursive calibration method |
CN110532808B (en) * | 2019-08-20 | 2023-04-11 | 江西金格科技有限公司 | Electronic signature method based on electronic document image object |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5960112A (en) * | 1996-11-26 | 1999-09-28 | Wen-Hsing Hsu | Method and device for the automatic matching of seal prints |
CN1635533A (en) * | 2003-12-30 | 2005-07-06 | 刘瑞祯 | Digital stamp system |
CN1677434A (en) * | 2005-03-14 | 2005-10-05 | 天津大学 | Seal false-true identifying method and integrated identifying machine |
CN1838163A (en) * | 2006-01-17 | 2006-09-27 | 沈前卫 | Universal electronic stamping system based on PKI |
-
2007
- 2007-08-15 CN CN2007101439463A patent/CN101122999B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5960112A (en) * | 1996-11-26 | 1999-09-28 | Wen-Hsing Hsu | Method and device for the automatic matching of seal prints |
CN1635533A (en) * | 2003-12-30 | 2005-07-06 | 刘瑞祯 | Digital stamp system |
CN1677434A (en) * | 2005-03-14 | 2005-10-05 | 天津大学 | Seal false-true identifying method and integrated identifying machine |
CN1838163A (en) * | 2006-01-17 | 2006-09-27 | 沈前卫 | Universal electronic stamping system based on PKI |
Non-Patent Citations (1)
Title |
---|
JP特开2002-7807A 2002.01.11 |
Also Published As
Publication number | Publication date |
---|---|
CN101122999A (en) | 2008-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101122999B (en) | Method for automatically extracting stamp image from Chinese painting and calligraphy | |
CN101533517B (en) | Structure feature based on Chinese painting and calligraphy seal image automatic extracting method | |
CN102855495B (en) | Method for implementing electronic edition standard answer, and application system thereof | |
CN102360490B (en) | Color conversion and editing propagation-based method for enhancing seasonal feature of image | |
Recky et al. | Windows detection using k-means in cie-lab color space | |
CN100573523C (en) | A kind of image inquiry method based on marking area | |
CN103679145A (en) | Automatic gesture recognition method | |
US9384519B1 (en) | Finding similar images based on extracting keys from images | |
CN103049446A (en) | Image retrieving method and device | |
CN102819728A (en) | Traffic sign detection method based on classification template matching | |
CN104598907B (en) | Lteral data extracting method in a kind of image based on stroke width figure | |
CN102147867B (en) | Method for identifying traditional Chinese painting images and calligraphy images based on subject | |
CN101853514A (en) | Interactive vectorization method of colorful geologic map image and system thereof | |
CN101866352A (en) | Design patent retrieval method based on analysis of image content | |
CN102360506A (en) | Local linear preserver-based scene color style uniformizing method | |
CN104463134A (en) | License plate detection method and system | |
CN103383700A (en) | Image retrieval method based on margin directional error histogram | |
CN104463138A (en) | Text positioning method and system based on visual structure attribute | |
EP2110758A1 (en) | Searching method based on layout information | |
CN105957124A (en) | Method and device for color editing of natural image with repetitive scene elements | |
CN103399863B (en) | Image search method based on the poor characteristic bag of edge direction | |
CN105654087A (en) | Color template-based offline handwritten character extraction method | |
CN101540050B (en) | Method and device for obtaining scene boundary | |
Mustaffa et al. | Content-based image retrieval based on color-spatial features | |
CN110619331A (en) | Color distance-based color image field positioning 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 | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100707 Termination date: 20130815 |