CN102750538A - Go competition result analysis method based on image processing technique - Google Patents
Go competition result analysis method based on image processing technique Download PDFInfo
- Publication number
- CN102750538A CN102750538A CN2012101508159A CN201210150815A CN102750538A CN 102750538 A CN102750538 A CN 102750538A CN 2012101508159 A CN2012101508159 A CN 2012101508159A CN 201210150815 A CN201210150815 A CN 201210150815A CN 102750538 A CN102750538 A CN 102750538A
- Authority
- CN
- China
- Prior art keywords
- image
- black
- chessboard
- white
- result
- 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
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 title claims abstract description 20
- 238000004458 analytical method Methods 0.000 title abstract description 3
- 238000001514 detection method Methods 0.000 claims abstract description 8
- 230000011218 segmentation Effects 0.000 claims abstract description 8
- 238000013459 approach Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 12
- 230000007797 corrosion Effects 0.000 claims description 10
- 238000005260 corrosion Methods 0.000 claims description 10
- 230000001915 proofreading effect Effects 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000001914 filtration Methods 0.000 description 8
- 238000009499 grossing Methods 0.000 description 8
- 238000006243 chemical reaction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 239000009891 weiqi Substances 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a go competition result analysis method based on an image processing technique. The method comprises the following steps of: step I, preprocessing of a chessboard image: removing other objects except for a chessboard in a collected image through spatial alternation and grayscale interpolation according to the collected image; step II, segmentation of black and white chess pieces in the chessboard image: setting an appropriate threshold value for a corrected image, and respectively segmenting to form a black and white chess piece image; and step III, detection and result judgment of the black and white chess pieces: carrying out opening operation, projection, linedrawing, detection of attribute of the chessboard at an intersection point of lines, filling of chess pieces at blank parts, judgment of results and the like on the segmented black and white chess piece image. Under the condition without adding an extra device, image processing is carried out through a software method, and competition results can be quickly and accurately judged.
Description
Technical field
The present invention relates to view data and handle and the identification field particularly a kind of go result of the match analytical approach based on image processing techniques.
Background technology
In go class match, still adopt conventional artificial to count the method for chess piece basically for the statistics of the chess piece result of the match that adopts common chessboard and entity, it is longer not only to expend time in, and accuracy many times can not guarantee.In today that computer vision technique is popularized day by day, adopting the auxiliary interpretation of machine is a kind of more excellent method.Chessboard after patent art at first uses digital camera (or camera) to the go match carries out IMAQ, carries out machine interpretable with digital image processing techniques again.Do so not only and can reduce the interpretation time greatly, can also guarantee result's accuracy.Utilize computer technology and digital image processing techniques to cut apart black piece and white side automatically among the present invention, the position of location black-and-white piece obtains the result who plays chess fast.
Summary of the invention
Goal of the invention: technical matters to be solved by this invention is the deficiency to prior art; A kind of go result of the match analytical approach based on image processing techniques is provided, thereby makes the state and the result of the match that when people play Weiqi, can count the chess piece of chessboard fast and accurately.
In order to solve the problems of the technologies described above, the invention discloses a kind of go result of the match analytical approach based on image processing techniques, may further comprise the steps:
Step 1, the pre-service of checkerboard image:,, remove other object except that chessboard in the images acquired through spatial alternation and grey scale interpolation according to the image of gathering;
Step 2, the cutting apart of black-and-white piece in the checkerboard image: the image after will proofreading and correct, appropriate threshold is set, be partitioned into the black-and-white piece image respectively;
Step 3, the detection of black-and-white piece and result judge: with the black-and-white piece image that is partitioned into respectively through attribute, the blank space chess piece of the chessboard at opening operation, projection, setting-out, detection line and line intersection point place are filled up, result of the match is accomplished in operation such as judgement as a result judgement.The present invention carries out Flame Image Process through software approach under the situation that does not increase extra means, judge result of the match quickly and accurately.
Among the present invention, preferably, said step 1 may further comprise the steps:
Step (11) in the image of gathering, marks the coordinate points at four angles of chessboard, uses these four coordinate points to carry out affined transformation because need in the geometric transformation below;
Step (12), image carries out geometric transformation, because checkerboard image is when gathering; Have distortion unavoidably; So use geometric transformation that whole checkerboard image is carried out spatial alternation and grey scale interpolation, remove and gather the remainder that removes the chessboard part in the checkerboard image, obtain the rectangular image of rule.
Among the present invention, preferably, said step 2 may further comprise the steps:
Step (21) in the chessboard of go image of gathering, through after the geometric transformation, only three kinds of objects can occur in the image, and black chess piece, white chess piece and background color are yellow chessboard, can be partitioned into the black chess piece through the direct threshold segmentation method of histogram.To the image calculation grey level histogram after proofreading and correct; Carry out filtering through one dimension neighborhood smoothing filter (hereinafter will be introduced) then, peak-to-valley value can appear in filtered grey level histogram, and first peak and second peak-to-peak valley point are before the probability that the black chess piece occurs; After first valley point is chessboard and white chess piece; So only need find valley between first peak value in the gray histogram curve and second peak value to be the segmentation threshold of black chess piece, with this value as the threshold value of cutting apart the black chess piece, and binaryzation; With the black chess piece assignment in the gray level image is 255, and remaining image assignment is 0.
Step (22) because in the image of actual acquisition, has through the gray-scale value of chessboard gray-scale value after the gray processing and white chess piece and to intersect, and just can not white chess piece and chessboard be separated through gray level threshold segmentation like this.The three-component value of RGB through research black, white and yellow chess piece is found; The three-component value of the RGB of black is all smaller; The three-component value of RGB of white is all bigger, and the value of red green component is bigger in the yellow RGB three-component, and the value of blue component is smaller.Their blue component differs bigger in black, white, the yellow chess piece; The blue component of adularescent chess piece is bigger; The blue component of black and yellow chess piece is all smaller; So only need extract the blue component in the coloured image, suitable threshold is set then, promptly can white chess piece and chessboard be separated.When selecting threshold value, adopt automatic threshold to extract equally.Draw and proofread and correct the grey level histogram of back image blue component; Carry out filtering through one dimension neighborhood smoothing filter then; Peak-to-valley value can appear in filtered grey level histogram; First peak is the probability that the black chess piece occurs in the blue component, and second peak is the probability that chessboard occurs, and the 3rd peak is the probability that occurs with white chess piece.So the valley of asking between second peak value and the 3rd peak value promptly is a threshold value of cutting apart white chess piece.As the threshold value of cutting apart white chess piece, and binaryzation is 255 with the white chess piece assignment in the gray level image with this value, and remaining image assignment is 0.
Among the present invention, preferably, said step 3 may further comprise the steps:
Step (31) is made opening operation respectively to the black-and-white piece image that is partitioned into, like this can removal of images in when cutting apart owing to threshold value is selected the inaccurate tiny noise that occurs, the border of all right smooth object;
Step (32) is carried out addition with the image behind the opening operation, does once corrosion operation then, and the effect of corrosion operation is to eliminate the object boundary point, is convenient to when projection, find out easily extreme point like this;
Step (33) with the method for the use of the image after corrosion image projection, is done projection respectively in the horizontal and vertical directions, and is write down its value;
Step (34) is according to the level of record and the value of vertical direction projection, the drop shadow curve of drawing; Through obtaining extreme value behind the one dimension neighborhood smoothing filter; These extreme values just corresponding the position of the chessboard line in the chessboard because the size of chessboard is 19 * 19, so the extreme value of obtaining also is 19 respectively;
Step (35) according to detected chessboard line, detects the black-and-white piece position; When detecting the chess piece position, use the window of M * M to remove to detect chess piece, M representes window size, and M gets 3; After obtaining the black-and-white piece position, use the go chess piece to fill up rule: empty to black or white, empty being filled up to black or white, black or white to empty, empty filled up for black or white, white to empty to white; Empty filled up for white, black to empty to black, empty being filled up to black, using above rule that corresponding blank space is filled up is black or white side.
Step (36), statistics is filled up the number of back black-and-white piece, judges result of the match according to laws of the game then.
Principle of the present invention is according to the image of gathering; Secondly be partitioned into black chess piece and white pawn image at first respectively, split image carried out the opening operation operation respectively, the corrosion that tries again of the image addition after the opening operation; Image after will corroding then carries out projection; Detect 19 * 19 chessboard line of chessboard, black-and-white piece is detected at online intersection point place, fills up rule according to the black-and-white piece that detects according to go and fills up chess piece; Fill up back statistics black-and-white piece number, use the go decision rule to judge result of the match.
Beneficial effect: the present invention carries out Flame Image Process through software approach, after chessboard is gathered, can detect every trellis attitude in the chessboard fast and accurately.The present invention has wide practical use in the analysis of statistics go result of the match and go strategy.
Description of drawings
Below in conjunction with accompanying drawing and embodiment the present invention is done specifying further, of the present invention above-mentioned with or otherwise advantage will become apparent.
Fig. 1 is the geometry correction synoptic diagram.
Fig. 2 is the procedure chart that the black chess piece is cut apart in the present invention.
Fig. 3 is the procedure chart that white chess piece is cut apart in the present invention.
Fig. 4 is that black-and-white piece of the present invention detects the process flow diagram of judging with the result
Fig. 5 is the inventive method simplified flow chart.
Embodiment:
The present invention, the core thinking is to utilize the image of gathering to carry out black-and-white piece to cut apart, and is partitioned into the black-and-white piece image respectively; Secondly split image is carried out the opening operation operation respectively, with the corrosion that tries again of the image addition after the opening operation, the image that is partitioned into of basis carries out the projection of level and vertical direction then; Draw line in the chessboard, chess piece is sought at online then intersection point place, notes the state of chess piece then; According to algorithm, add up the go result of the match then.
As shown in Figure 5, the invention discloses a kind of go result of the match analytical approach based on image processing techniques, may further comprise the steps:
Step 1, the pre-service of checkerboard image:, remove other object except that chessboard in the images acquired through spatial alternation and grey scale interpolation;
Said step 1 may further comprise the steps: step 11 in the image of gathering, marks the coordinate points at four angles of chessboard; Step 12 according to the coordinate points of mark, is removed other object except that chessboard in the image of collection, and is transformed to a rectangular image through geometric transformation.
Step 12 is to the checkerboard image pre-service;
Image to gathering carries out pre-service, image is carried out pre-service make it make the requirement that it can adaptive algorithm seem particularly necessary, and the image pre-service that relates among the present invention comprises spatial alternation and grey scale interpolation.
Geometric transformation is the spatial mappings relation of image mid point and point, can be with a bit transforming to optional position in the image in the image, and keeping before and after the conversion local feature between two width of cloth images similar is that the continuity and the interlinking of local feature on the source images is constant.
Geometric transformation based on bilinear transformation:
Order
G(x，y)＝F(x′，y′)＝F(ax′+by′+cx′y′+d，ex′+fy′+gx′y′+h) (1)
G in the formula (1) (x, the y) image after the expression conversion, F (x ', y ') the expression original image
Promptly
x＝ax′+by′+cx′y′+d (2)
y＝ex′+fy′+gx′y′+h (3)
X in the formula (2), (3), y represent the coordinate of image after the conversion, x ', and the coordinate of y ' expression original image, a, b, c, d, e, f, g, h representes conversion coefficient
4 points of original image (x '
1, y '
1), (x '
2, y '
2), (x '
3, y '
3), (x '
4, y '
4)
Proofread and correct 4 point (x of back image
1, y
1), (x
2, y
2), (x
3, y
3), (x
4, y
4)
According to these 4 pairs of points, can list 8 system of equations, 8 coefficients are arranged in the equation, only need know 8 equations, just can solve 8 unknown numbers, be with matrix representation:
Order
Can obtain AX=B
According to AX=B, can obtain X=A
-1B so just can obtain transformation matrix B.
Original image is through the image after just can obtaining proofreading and correct with up conversion.Before the conversion with conversion after synoptic diagram as shown in Figure 1.
Step 2, the cutting apart of black-and-white piece in the checkerboard image: the image after will proofreading and correct carries out gray processing to be handled, and uses the histogram thresholding dividing method, is partitioned into the black pawn image; Take out the blue component in the RGB three-component of proofreading and correct the back coloured image,, use the histogram thresholding dividing method to be partitioned into white pawn image equally according to blue component;
Said step 2 may further comprise the steps: step 21; In the chessboard of go image of gathering, through after the geometric transformation, only three kinds of objects can appear in the image; Black chess piece, white chess piece and background color are yellow chessboard, can be partitioned into the black chess piece through the direct threshold segmentation method of histogram.When selecting threshold value, adopt the automatic threshold method for distilling, to the image calculation grey level histogram after proofreading and correct; Carry out filtering through one dimension neighborhood smoothing filter then, peak-to-valley value can appear in filtered grey level histogram, and first peak and second peak-to-peak valley point are before the probability that the black chess piece occurs; After first valley point is chessboard and white chess piece; So only need find valley between first peak value in the gray histogram curve and second peak value to be the segmentation threshold of black chess piece, with this value as the threshold value of cutting apart the black chess piece, and binaryzation; With the black chess piece assignment in the gray level image is 255, and remaining image assignment is 0.Cutting procedure figure such as Fig. 2 of black chess piece;
Step 22 because in the image of actual acquisition, has through the gray-scale value of chessboard gray-scale value after the gray processing and white chess piece and to intersect, and just can not white chess piece and chessboard be separated through gray level threshold segmentation like this.The three-component value of RGB through research black, white and yellow chess piece is found; The three-component value of the RGB of black is all smaller; The three-component value of RGB of white is all bigger, and the value of red green component is bigger in the yellow RGB three-component, and the value of blue component is smaller.Their blue component differs bigger in black, white, the yellow chess piece; The blue component of adularescent chess piece is bigger; The blue component of black and yellow chess piece is all smaller; So only need extract the blue component in the coloured image, suitable threshold is set then, both can white chess piece and chessboard be separated.When selecting threshold value, adopt automatic threshold to extract equally.Draw and proofread and correct the grey level histogram of the blue component of image afterwards; Carry out filtering through one dimension neighborhood smoothing filter then; Peak-to-valley value can appear in filtered grey level histogram; First peak is the probability that the black chess piece occurs in the blue component, and second peak is the probability that chessboard occurs, and the 3rd peak is the probability that occurs with white chess piece.So the valley of asking between second peak value and the 3rd peak value promptly is a threshold value of cutting apart white chess piece.As the threshold value of cutting apart white chess piece, and binaryzation is 255 with the white chess piece assignment in the gray level image with this value, and remaining image assignment is 0.Figure is as shown in Figure 3 for white pawn image cutting procedure.
Gray level [0,1 ..., L-1] and the histogram of digital picture of scope is discrete function h (r
k)=n
k, r wherein
kBe k level gray scale, n
kBe that gray level is r in the image
kThe number that occurs of pixel.Often the sum (representing with n) with pixel in the image removes its each value, to obtain normalized histogram.Therefore, a normalized histogram is by P (r
k)=n
k/ n provides, k=0 wherein, and 1 ..., L-1.Briefly, P (r
k) to have provided gray level be r
kThe probability estimate value that takes place.Notice that normalized histogrammic all part sums should equal 1.
In the formula, n is the summation of pixel in the image, n
kBe that gray level is r
kNumber of pixels, L is gray level possible in an image sum.
It is to confirm that according to histogrammic characteristic in the image segmentation threshold carries out image segmentation that histogram thresholding is cut apart; This method is fairly simple, and the histogram of computed image at first is according to the histogram that calculates; Selection can separate the threshold value of target and background, promptly can be partitioned into target or background exactly.
The histogram thresholding dividing method that step 21 and step 22 all are to use, the split image that just when cutting apart, uses is different, when cutting apart the black chess piece, use be that the gray level image of proofreading and correct the back image is cut apart; When cutting apart white chess piece, use be that the blue component of proofreading and correct the back image is cut apart.
One dimension neighborhood smoothing filter:
Be included in the simple average value of signal in the filtering mask neighborhood during output of one dimension neighborhood smooth linear wave filter; The interior signal averaging of neighborhood that this smoothing filter is confirmed with the filtering mask replaces the value of each pixel of original signal, and this processing has reduced the sharp-pointed variation of one-dimensional signal.If one-dimensional signal h (n), the size of filtering mask is M, and M gets odd number, and the output h ' of smooth linear wave filter (n) can use following formula to represent:
In the formula (6), T is the threshold value of one dimension smothing filtering.Be provided with that this threshold value can be removed because the level and smooth blurring effect that produces of neighborhood: when the difference of the mean value of the gray scale of putting in some points and its neighborhood was no more than the threshold value T of regulation, it was constant just to keep its former gray-scale value; If during, replace the gray-scale value of this point with regard to mean value with them greater than threshold value T.Make and come level and smooth one-dimensional signal in this way, both can not change the original characteristic of signal again so that output signal ratio is more level and smooth.
Step 3, the detection of black-and-white piece and result judge: with the black-and-white piece image that is partitioned into respectively through attribute, the blank space chess piece of the chessboard at opening operation, projection, setting-out, detection line and line intersection point place are filled up, result of the match is accomplished in operation such as judgement as a result judgement.
As shown in Figure 4, said step 3 may further comprise the steps: step 31, the black-and-white piece image that is partitioned into is done opening operation respectively;
The first process of corrosion after expansion during opening operation, can removal of images on tiny noise, and smooth object border.
Suppose A, B is Z
2In set, A is represented and can be expressed as with mathematic(al) representation by the B opening operation:
The opening operation available expression is expressed as:
Use the expression formula of set to be expressed as:
Step 32 is carried out addition with the image behind the opening operation, does once corrosion operation then; Step 33 is done projection respectively in the horizontal and vertical directions with the image after the corrosion, and is write down its value;
The projection of image:
Image the projection on a certain direction can be defined as this image pixel gray-scale value on this direction, add up the back sum.Image projection and, its feature space be by two boil down to one dimensions, thereby with a large amount of a spot of image feature informations of image information boil down to, not only calculate simply, and the characteristics of uniqueness and distinguishability are arranged, thereby can carry out image recognition effectively.The projection properties of image can be represented as follows with mathematical method:
Be provided with a digital picture F (x, y) (x=1 wherein, 2,3 ..., w-1, w; Y=1,2,3 ..., h-1, h), this digital picture can represent to be called following two formulas at the projection properties of transverse axis x axle and Z-axis y axle so:
The horizontal direction projection:
The vertical direction projection:
Wherein: w and h are respectively the width and the height of image, and (x y) is the gray-scale value of image to F.
Step 34, according to the level of record and the value of vertical direction projection, the drop shadow curve of drawing, and through one dimension neighborhood smoothing filter, and obtain extreme value;
Step 35 according to chessboard line, detects the black-and-white piece position; Because the size of chessboard of go is 19 * 19, so the maximum value number of level and vertical direction keeps 19 respectively, 19 * 19 chessboard then draws; Intersection point place at chessboard; Detect the state of chess piece, write down the corresponding position of chess piece then and fill up rule according to chess piece then, blank space is filled up chess piece;
Step 36, statistics is filled up the number of back black-and-white piece, judges result of the match according to laws of the game then.
The invention provides a kind of go result of the match analytical approach based on image processing techniques; The method and the approach of concrete this technical scheme of realization are a lot, and the above only is a preferred implementation of the present invention, should be understood that; For those skilled in the art; Under the prerequisite that does not break away from the principle of the invention, can also make some improvement and retouching, these improvement and retouching also should be regarded as protection scope of the present invention.The all available prior art of each ingredient not clear and definite in the present embodiment realizes.
Claims (5)
1. the go result of the match analytical approach based on image processing techniques is characterized in that, may further comprise the steps:
Step 1, the pre-service of checkerboard image:,, remove other object except that chessboard in the images acquired through spatial alternation and grey scale interpolation according to the image of gathering;
Step 2, the cutting apart of black-and-white piece in the checkerboard image: the image after will proofreading and correct, appropriate threshold is set, be partitioned into the black-and-white piece image respectively
Step 3, the detection of black-and-white piece and result judge: with the black-and-white piece image that is partitioned into respectively through attribute, the blank space chess piece of the chessboard at opening operation, projection, setting-out, detection line and line intersection point place are filled up, result of the match is accomplished in operation such as judgement as a result judgement.
2. a kind of go result of the match analytical approach based on image processing techniques according to claim 1 is characterized in that said step 1 may further comprise the steps:
Step (11) in the image of gathering, marks the coordinate points at four angles of chessboard;
Step (12) obtains the image of chessboard through geometric transformation according to the coordinate points of mark.
3. a kind of go result of the match analytical approach based on image processing techniques according to claim 2 is characterized in that said step 2 may further comprise the steps:
Step (21) is used gray level image in the image after correction, appropriate threshold is set is partitioned into the black pawn image;
Step (22), the blue component of use coloured image is provided with appropriate threshold and cuts apart white pawn image in the image after correction.
4. a kind of go result of the match analytical approach based on image processing techniques according to claim 3 is characterized in that said step 3 may further comprise the steps:
Step (31) is made opening operation respectively to the black-and-white piece image that is partitioned into;
Step (32) is carried out addition with the image behind the opening operation, does once corrosion operation then;
Step (33) is done projection respectively in the horizontal and vertical directions with the image after the corrosion, and is write down its value;
Step (34), according to the level of record and the value of vertical direction projection, the drop shadow curve of drawing, and obtain extreme value;
Step (35) according to chessboard line, detects the black-and-white piece position, fills up rule according to chess piece then, and blank space is filled up chess piece;
Step (36), statistics is filled up the number of back black-and-white piece, judges result of the match according to laws of the game then.
5. a kind of go result of the match analytical approach according to claim 4 based on image processing techniques; It is characterized in that; The opening operation of the morphology operations of said step (31), removal are selected the incorrect image that is partitioned into because of segmentation threshold and are contained isolated noise.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210150815.9A CN102750538B (en) | 2012-05-16 | 2012-05-16 | A kind of weiqi game interpretation of result method based on image processing techniques |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210150815.9A CN102750538B (en) | 2012-05-16 | 2012-05-16 | A kind of weiqi game interpretation of result method based on image processing techniques |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102750538A true CN102750538A (en) | 2012-10-24 |
| CN102750538B CN102750538B (en) | 2016-04-27 |
Family
ID=47030703
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210150815.9A Expired - Fee Related CN102750538B (en) | 2012-05-16 | 2012-05-16 | A kind of weiqi game interpretation of result method based on image processing techniques |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102750538B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105205447A (en) * | 2015-08-22 | 2015-12-30 | 周立人 | Go identification method based on go image and go board |
| CN105446904A (en) * | 2014-06-12 | 2016-03-30 | 联想(北京)有限公司 | Multi-device combination application method, apparatus and system |
| CN105664478A (en) * | 2016-01-15 | 2016-06-15 | 上海斐讯数据通信技术有限公司 | Go composition outcome judgment method and mobile terminal |
| CN105701496A (en) * | 2016-01-12 | 2016-06-22 | 北京万同科技有限公司 | Go board surface identification method based on artificial intelligence technology |
| CN105956594A (en) * | 2016-05-10 | 2016-09-21 | 浙江理工大学 | Method of identifying chest piece movement of real chess |
| CN107194944A (en) * | 2017-06-21 | 2017-09-22 | 南京林业大学 | Forest fire image dividing method and device |
| CN107730522A (en) * | 2017-10-12 | 2018-02-23 | 中科视拓（北京）科技有限公司 | A kind of weiqi chess manual recognition methods based on image |
| CN107875625A (en) * | 2017-11-23 | 2018-04-06 | 东华大学 | A kind of voice-based Chinese chess is played chess device |
| CN105446904B (en) * | 2014-06-12 | 2018-08-31 | 联想(北京)有限公司 | A kind of method, apparatus and system of more equipment combination applications |
| CN108509956A (en) * | 2018-03-27 | 2018-09-07 | 深圳大学 | Method, system and the electronic equipment of go victory or defeat judgement based on image procossing |
| CN109559325A (en) * | 2018-12-03 | 2019-04-02 | 中南大学 | Weiqi chess manual recognition methods based on chess manual RGB image |
| CN110399888A (en) * | 2019-07-25 | 2019-11-01 | 西南民族大学 | A kind of go judgment system based on MLP neural network and computer vision |
| CN110766713A (en) * | 2019-10-30 | 2020-02-07 | 上海微创医疗器械（集团）有限公司 | Lung image segmentation method and device and lung lesion region identification equipment |
| CN110909727A (en) * | 2019-11-20 | 2020-03-24 | 北京工业大学 | Image recognition-based go recognition method and program interface |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000654A (en) * | 2006-12-31 | 2007-07-18 | 常熟理工学院 | Automatic recording method for recognising chess manual by image |
| CN101477687A (en) * | 2009-01-22 | 2009-07-08 | 上海交通大学 | Checkerboard angle point detection process under complex background |
| CN102184544A (en) * | 2011-05-18 | 2011-09-14 | 北京联合大学生物化学工程学院 | Method for correcting deformity and identifying image of go notation |
| CN102412627A (en) * | 2011-11-29 | 2012-04-11 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
-
2012
- 2012-05-16 CN CN201210150815.9A patent/CN102750538B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000654A (en) * | 2006-12-31 | 2007-07-18 | 常熟理工学院 | Automatic recording method for recognising chess manual by image |
| CN101477687A (en) * | 2009-01-22 | 2009-07-08 | 上海交通大学 | Checkerboard angle point detection process under complex background |
| CN102184544A (en) * | 2011-05-18 | 2011-09-14 | 北京联合大学生物化学工程学院 | Method for correcting deformity and identifying image of go notation |
| CN102412627A (en) * | 2011-11-29 | 2012-04-11 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105446904A (en) * | 2014-06-12 | 2016-03-30 | 联想(北京)有限公司 | Multi-device combination application method, apparatus and system |
| CN105446904B (en) * | 2014-06-12 | 2018-08-31 | 联想(北京)有限公司 | A kind of method, apparatus and system of more equipment combination applications |
| CN105205447B (en) * | 2015-08-22 | 2018-08-17 | 周立人 | Go recognition methods based on go image and chessboard |
| CN105205447A (en) * | 2015-08-22 | 2015-12-30 | 周立人 | Go identification method based on go image and go board |
| CN105701496B (en) * | 2016-01-12 | 2019-07-05 | 北京万同科技有限公司 | A kind of go disk recognition methods based on artificial intelligence technology |
| CN105701496A (en) * | 2016-01-12 | 2016-06-22 | 北京万同科技有限公司 | Go board surface identification method based on artificial intelligence technology |
| CN105664478A (en) * | 2016-01-15 | 2016-06-15 | 上海斐讯数据通信技术有限公司 | Go composition outcome judgment method and mobile terminal |
| CN105956594A (en) * | 2016-05-10 | 2016-09-21 | 浙江理工大学 | Method of identifying chest piece movement of real chess |
| CN107194944A (en) * | 2017-06-21 | 2017-09-22 | 南京林业大学 | Forest fire image dividing method and device |
| CN107730522A (en) * | 2017-10-12 | 2018-02-23 | 中科视拓（北京）科技有限公司 | A kind of weiqi chess manual recognition methods based on image |
| CN107875625A (en) * | 2017-11-23 | 2018-04-06 | 东华大学 | A kind of voice-based Chinese chess is played chess device |
| CN108509956A (en) * | 2018-03-27 | 2018-09-07 | 深圳大学 | Method, system and the electronic equipment of go victory or defeat judgement based on image procossing |
| CN109559325A (en) * | 2018-12-03 | 2019-04-02 | 中南大学 | Weiqi chess manual recognition methods based on chess manual RGB image |
| CN110399888A (en) * | 2019-07-25 | 2019-11-01 | 西南民族大学 | A kind of go judgment system based on MLP neural network and computer vision |
| CN110399888B (en) * | 2019-07-25 | 2021-08-27 | 西南民族大学 | Weiqi judging system based on MLP neural network and computer vision |
| CN110766713A (en) * | 2019-10-30 | 2020-02-07 | 上海微创医疗器械（集团）有限公司 | Lung image segmentation method and device and lung lesion region identification equipment |
| CN110909727A (en) * | 2019-11-20 | 2020-03-24 | 北京工业大学 | Image recognition-based go recognition method and program interface |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102750538B (en) | 2016-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102750538A (en) | Go competition result analysis method based on image processing technique | |
| CN109191459B (en) | Automatic identification and rating method for continuous casting billet macrostructure center segregation defect | |
| CN107463918B (en) | Lane line extraction method based on fusion of laser point cloud and image data | |
| EP2811423B1 (en) | Method and apparatus for detecting target | |
| JP4172941B2 (en) | Land parcel data creation method and apparatus | |
| CN109034017B (en) | Head pose estimation method and machine readable storage medium | |
| CN104794721B (en) | A kind of quick optic disk localization method based on multiple dimensioned spot detection | |
| CN108510491B (en) | Method for filtering human skeleton key point detection result under virtual background | |
| CN108009529B (en) | Forest fire smoke video target detection method based on characteristic root and hydrodynamics | |
| CN109636732A (en) | A kind of empty restorative procedure and image processing apparatus of depth image | |
| WO2021109697A1 (en) | Character segmentation method and apparatus, and computer-readable storage medium | |
| CN102982545A (en) | Image depth estimation method | |
| CN111274939B (en) | Automatic extraction method for road pavement pothole damage based on monocular camera | |
| CN111354047B (en) | Computer vision-based camera module positioning method and system | |
| CN111382658B (en) | Road traffic sign detection method in natural environment based on image gray gradient consistency | |
| CN109948393A (en) | A kind of localization method and device of bar code | |
| CN114331986A (en) | Dam crack identification and measurement method based on unmanned aerial vehicle vision | |
| CN109389165A (en) | Oil level gauge for transformer recognition methods based on crusing robot | |
| JP4747122B2 (en) | Specific area automatic extraction system, specific area automatic extraction method, and program | |
| CN117218148B (en) | Channel boundary determining method and system based on satellite image and readable storage medium | |
| JP3330829B2 (en) | Automatic detection method of evaluable area in images of machine parts | |
| CN114529715B (en) | Image identification method and system based on edge extraction | |
| CN110853097A (en) | Biscuit identification and positioning method applied to biscuit surface pattern printing equipment | |
| CN115424107A (en) | Underwater pier apparent disease detection method based on image fusion and deep learning | |
| CN1331097C (en) | Spot eliminating method for digital image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| DD01 | Delivery of document by public notice |
Addressee: Nanjing University Document name: Notification to Go Through Formalities of Registration |
|
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160427 Termination date: 20180516 |