CN116798077A - Palm photo detection method - Google Patents
Palm photo detection method Download PDFInfo
- Publication number
- CN116798077A CN116798077A CN202311041952.3A CN202311041952A CN116798077A CN 116798077 A CN116798077 A CN 116798077A CN 202311041952 A CN202311041952 A CN 202311041952A CN 116798077 A CN116798077 A CN 116798077A
- Authority
- CN
- China
- Prior art keywords
- palm
- image
- gradient
- contour
- curve
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 27
- 230000008859 change Effects 0.000 claims abstract description 32
- 238000005260 corrosion Methods 0.000 claims abstract description 5
- 230000007797 corrosion Effects 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 210000003462 vein Anatomy 0.000 description 3
- 230000008569 process Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1382—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
- G06V40/1388—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger using image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a palm photo detection method, which belongs to the field of biological identification and comprises the following steps: collecting a palm image of a user, binarizing and cutting out a palm binary image according to a minimum circumscribed rectangle, carrying out corrosion operation on the outer edge contour of fingers in a palm area binary image to obtain a mask image, cutting out a palm area image according to the mask image to obtain a palm area image, calculating a gradient distribution map of the palm area image, respectively taking a model of the gradient distribution map based on a palm area and a background area in the mask image to obtain an outer contour gradient image of the palm and an inner contour gradient image of the palm, respectively calculating gradient average values of the outer contour gradient image of the palm and the inner contour gradient image of the palm, judging whether the palm image is based on the gradient average values of the outer contour gradient image of the palm and the inner contour gradient image of the palm, and judging whether the palm image is based on the change width of the palm contour. The invention can effectively distinguish whether the palm image is a photo, avoid malicious attack in biological recognition and improve the safety.
Description
Technical Field
The invention relates to the technical field of biological recognition, in particular to a palm photo detection method.
Background
Palm recognition comprises palm print recognition and palm vein recognition, is an identity recognition method emerging in recent years, and is an important supplement to the existing human body biological feature recognition technology.
Palm biological recognition technology is an identity authentication method based on palm biological recognition disclosed in Chinese patent application with application publication number of CN113378640A, and comprises the following steps: acquiring a palm image of an object to be authenticated; extracting palm features in the palm image, wherein the palm features comprise finger features and palm vein features, palm print features and/or palm print and palm vein features; and carrying out legality authentication on the object to be authenticated according to the palm features and a preset palm template list to obtain an authentication result.
The palm biological recognition technology is more and more widely applied because of the convenience in operation. However, various attack means are also endless, and the most common attack means are photo or video attacks. Once the attack means is successful, serious potential safety hazards are caused, and the property safety and life safety of the user are threatened.
Disclosure of Invention
The main purpose of the invention is to provide a palm photo detection method which is applied to palm biological recognition, and can distinguish living palms from non-living palms, so that potential safety hazards in the biological recognition process are reduced.
In order to achieve the above object, the present invention provides the following solutions:
the invention relates to a palm photo detection method, which is characterized by comprising the following steps of: which comprises the following steps:
step 1, acquiring a palm image of a user, performing binarization processing on the palm image to obtain a palm binary image, calculating a minimum circumscribed rectangle of a palm region in the palm binary image, and intercepting the palm binary image according to the minimum circumscribed rectangle to obtain a palm region binary image;
step 2, performing corrosion operation on the outline of the outer edge of the finger in the binary image of the palm area to obtain a mask image, and intercepting the palm image according to the mask image to obtain a palm area image;
step 3, calculating a gradient distribution map of the palm area image;
step 4, respectively taking a model of the gradient distribution map based on a palm region and a background region in the mask image to obtain a palm outer contour gradient map and a palm inner gradient map, and respectively calculating gradient average values of the palm outer contour gradient map and the palm inner gradient map;
step 5, comparing the gradient average value of the palm outline gradient map and the gradient average value of the palm interior gradient map, if the gradient average value of the palm outline gradient map is larger than the gradient average value of the palm interior gradient map, carrying out next detection, otherwise, judging that the palm image is a palm photo, and ending the detection;
and 6, acquiring a palm outline curve in the palm area image, calculating the palm outline change width according to the palm outline curve, and further distinguishing whether the palm image is a palm photo or a real palm based on the palm outline change width.
Preferably, in the step 1, after the palm image of the user is obtained, whether a rectangular frame exists in the palm image is judged, if the rectangular frame exists, the palm image is considered to be a palm photo, and the detection is ended.
Preferably, the step 3 of calculating the gradient profile of the palm area image includes: and calculating the difference value of gray values of each pixel point in the palm area image and four pixel points with the distance r, and calculating the sum of absolute values of the difference values, and taking the sum as the gradient value of the pixel point to obtain a gradient distribution diagram, wherein r is in direct proportion to the ratio of the palm area image to the palm image.
Preferably, the method for acquiring the palm outer contour gradient map in the step 4 includes: and setting the gradient value of the corresponding region of the palm region in the mask image to 0 in the gradient distribution map to obtain an outer contour gradient map.
Preferably, the method for acquiring the palm interior gradient map in the step 4 includes: and setting the gradient value of the background area in the mask image in the corresponding area in the gradient distribution diagram to be 0, and obtaining the inner outline information diagram of the palm.
Preferably, the specific step of further distinguishing whether the palm image is a palm photo or a real palm according to the palm contour change width in step 6 is:
step 6.1, acquiring a palm contour curve in a palm region binary image, and acquiring a palm outer contour curve in a palm region image according to the palm contour curve, wherein the palm outer contour curve is a pixel point corresponding to the palm contour curve in the palm region image;
step 6.2, taking n pixel points on the left and right sides of each contour point on the palm contour curve, and n points on the upper and lower sides to form a horizontal gray level curve and a numerical gray level curve;
step 6.3, respectively deriving the second order of the two gray level curves to respectively obtain the change rates of the two gray level curves;
step 6.4, respectively confirming peak points of each gray level curve according to gray level values, and solving two pixel points with the maximum absolute values of the change rates at two sides of the peak points as critical contour points;
step 6.5, calculating the absolute value of the coordinate difference of two critical contour points as the change width of the contour points;
step 6.6, traversing all contour points, and repeating the steps 6.2-6.5;
and 6.7, setting a contour width threshold, calculating the average value of the variation widths of all contour points as the variation width of the palm contour, and if the variation width of the palm contour is smaller than the contour width threshold, determining the palm image as a real palm, otherwise, determining the palm image as a palm photo.
Preferably, in the step 6.2, n has a value of 30.
Preferably, in the step 6.4, if there are a plurality of peak points in the gray scale curve, a point closest to a center point of the gray scale curve is taken as a peak point, and a gray scale value of the peak point is greater than a gray scale value of 3 pixels adjacent to the peak point.
Preferably, in the step 6.5, calculating the absolute value of the coordinate difference between the two critical contour points as the variation width of the contour point includes: and calculating column coordinates of two critical contour points on the horizontal gray scale curve as the horizontal variation width of the contour point, and calculating row coordinates of two critical contour points on the vertical gray scale curve as the vertical variation width of the contour point, wherein the variation width of the contour point is equal to the average value of the horizontal variation width and the vertical variation width of the contour point.
Preferably, after obtaining the palm image of the user, the step 1 performs fixed noise removal on the palm image, and the method includes: and counting the minimum non-zero gray values of all pixel points in the palm image, taking the minimum non-zero gray values as fixed noise, and subtracting the fixed noise from the gray value of each pixel point in the palm image to obtain the palm image with the fixed noise removed.
The invention has the following technical effects:
1. according to the palm photo detection method, based on the fact that the photo is different from the real palm in light reflection, the palm photo and the real palm can be detected by calculating the gradient of the outer outline of the palm and the inner outline of the palm and the change width of the outline of the palm, the palm photo is removed and only the real palm image is identified, and potential safety hazards in the biological identification process are reduced.
2. The gradient average value of the palm outline gradient map of the real palm is larger than the gradient average value of the palm outline gradient map in a palm photo or a palm video, but the gradient average value of the palm outline gradient map of the real palm is not larger than the gradient average value of the palm outline gradient map of the other printing palm based on the condition of the same palm and compared with the condition of different palms, because factors such as lines, different placement positions, skin colors, camera shooting effects and the like among different palms can influence the contour change of an image, the gradient average value of the palm outline gradient map of the real palm and the printing palm cannot be distinguished; according to the invention, the palm interior gradient map is introduced, the palm photo is distinguished from the real palm by comparing the gradient average values of the palm outline gradient map and the palm interior gradient map, and the palm photo is distinguished from the real palm according to the palm attribute, so that the image difference caused by factors such as illumination, skin color, camera shooting effect and the like is avoided, and the compatibility is improved.
Drawings
Fig. 1 is a flowchart of a palm photo detection method according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be specifically described with reference to the following examples and the accompanying drawings, but the scope of the present invention is not limited thereto.
Referring to fig. 1, the invention relates to a palm photo detection method, which comprises the following steps:
step 1, acquiring a palm image of a user, wherein the palm image can be a real palm image acquired by an identification device or can be a photo or printing paper of the palm of the user, if an acquired object is a fake photo or printing paper, the frames of the paper and the photo are sometimes shot during shooting, so that a complete or incomplete rectangular frame usually appears in the acquired palm image; because different cameras have different fixed noises to influence the image quality, fixed noise removal is needed for the palm image, when the fixed noise is removed, the minimum non-zero gray values of all pixel points in the palm image are counted and used as the fixed noise, and the gray value of each pixel point in the palm image is subtracted by the fixed noise to obtain the palm image with the fixed noise removed; and carrying out binarization processing on the palm image to obtain a palm binary image, calculating a minimum circumscribed rectangle of a palm region in the palm binary image, and cutting the palm binary image according to the minimum circumscribed rectangle to obtain the palm region binary image.
Step 2, performing corrosion operation on the outline of the outer edge of the finger in the binary image of the palm area to obtain a mask image, wherein the width of the outline of the outer edge of the finger can be increased through the corrosion operation, so that the subsequent treatment is facilitated; and intercepting a palm image according to the mask image to obtain a palm area image.
Step 3, calculating a gradient distribution map of the palm area image, wherein the specific steps are as follows: calculating the difference value of gray values of each pixel point in the palm area image and four pixel points with the distance r, calculating the sum of absolute values of the difference values, and taking the sum of the absolute values of the calculated difference values as the gradient value of the pixel point to obtain a gradient distribution map, wherein r is in direct proportion to the ratio of the size of the palm area image to the size of the palm image. Because the palm is placed randomly, the distance between the palm and the palm can be different in size, and the change rate of the palm image shot by the closer distance is slower, the method sets the self-adaptive distance r according to the distance between the palm and the palm, and the influence of the distance between the palm and the palm is avoided.
Step 4, based on the palm area and the background area in the mask image obtained in the step 2, respectively taking the model of the gradient distribution map to obtain a palm outline gradient map and a palm inner gradient map: the method for acquiring the palm outline gradient map comprises the following steps: setting the gradient value of a corresponding region of a palm region in the mask image in the gradient distribution diagram to be 0, and obtaining a palm outline gradient diagram, wherein the palm region is a region with a pixel value of 1; the method for obtaining the palm inner gradient map comprises the following steps: setting the gradient value of the background area in the mask image in the corresponding area in the gradient distribution diagram to be 0, and obtaining a gradient diagram in the palm, wherein the background area is the area with the pixel value of 0; respectively calculating gradient average values of the palm outline gradient map and the palm inner gradient map;
step 5, because the gradient average value of the real palm outline gradient map is larger than the gradient average value of the palm inner gradient map, and the gradient average value of the printed palm outline gradient map is close to the gradient average value of the palm inner gradient map, therefore, the gradient average value of the palm outline gradient map and the gradient average value of the palm inner gradient map are compared, if the gradient average value of the palm outline gradient map is larger than the gradient average value of the palm inner gradient map, the next detection is carried out, otherwise, the palm image is judged to be a palm photo, and the detection is ended;
step 6, gradient of the image, namely gray level change condition of the image, wherein gradient values are also arranged at other gray level slowly-changing places except for gray level abrupt change places; the outer contour curve of the palm in the palm area image has a certain width, if the outer contour curve is a real palm, the change width is narrow if the gray level change is fast, and the change width is wide if the gray level change of the non-real palm is slow. Based on the above, the step obtains a palm outline curve in the palm area image, calculates a palm outline change width according to the palm outline curve, and further distinguishes whether the palm image is a palm photo or a real palm based on the palm outline change width, and the specific steps are as follows:
step 6.1, acquiring a palm contour curve (namely a point that a binarization value is changed from 1 to 0 or from 1) in a palm area binary image, and acquiring a palm outer contour curve in a palm area image according to the palm contour curve, wherein the palm outer contour curve is a pixel point corresponding to the palm contour curve in the palm area image;
step 6.2, taking n pixel points on the left and right sides of each contour point on the palm contour curve, and n points on the upper and lower sides to form a horizontal gray level curve and a numerical gray level curve, wherein the n is preferably 30;
step 6.3, respectively deriving the second order of the two gray level curves to obtain the change rate of the two gray level curves;
step 6.4, respectively confirming peak points of each gray level curve according to gray level values, and solving two pixel points with the maximum absolute values of the change rates at two sides of the peak points as critical contour points; if a plurality of peak points exist in the gray scale curve, the point closest to the center point of the gray scale curve is taken as the peak point, and the gray scale value of the peak point is larger than that of the adjacent 3 pixel points around the peak point
Calculating the absolute value of the coordinate difference of two critical contour points as the change width of the contour point, and recording numerical values, wherein the method specifically comprises the steps of calculating the column coordinates of the two critical contour points on a horizontal gray scale curve as the horizontal change width of the contour point, and calculating the row coordinates of the two critical contour points on a vertical gray scale curve as the vertical change width of the contour point, wherein the change width of the contour point is equal to the average value of the horizontal change width and the vertical change width of the contour point;
step 6.6, traversing all contour points, and repeating the steps 6.2-6.5;
and 6.7, setting a contour width threshold, calculating the average value of the variation widths of all contour points as the variation width of the palm contour, and if the variation width of the palm contour is smaller than the contour width threshold, determining the palm image as a real palm, otherwise, determining the palm image as a palm photo.
The above embodiments are only illustrative of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention, and various modifications and improvements made by those skilled in the art to the technical solutions of the present invention should fall within the protection scope defined by the claims of the present invention without departing from the design spirit of the present invention.
Claims (10)
1. A palm photo detection method is characterized in that: which comprises the following steps:
step 1, acquiring a palm image of a user, performing binarization processing on the palm image to obtain a palm binary image, calculating a minimum circumscribed rectangle of a palm region in the palm binary image, and intercepting the palm binary image according to the minimum circumscribed rectangle to obtain a palm region binary image;
step 2, performing corrosion operation on the outline of the outer edge of the finger in the binary image of the palm area to obtain a mask image, and intercepting the palm image according to the mask image to obtain a palm area image;
step 3, calculating a gradient distribution map of the palm area image;
step 4, respectively taking a model of the gradient distribution map based on a palm region and a background region in the mask image to obtain a palm outer contour gradient map and a palm inner gradient map, and respectively calculating gradient average values of the palm outer contour gradient map and the palm inner gradient map;
step 5, comparing the gradient average value of the palm outline gradient map and the gradient average value of the palm interior gradient map, if the gradient average value of the palm outline gradient map is larger than the gradient average value of the palm interior gradient map, carrying out next detection, otherwise, judging that the palm image is a palm photo, and ending the detection;
and 6, acquiring a palm outline curve in the palm area image, calculating the palm outline change width according to the palm outline curve, and further distinguishing whether the palm image is a palm photo or a real palm based on the palm outline change width.
2. The palmprint detection method of claim 1, wherein: and step 1, judging whether a rectangular frame exists in the palm image after the palm image of the user is obtained, and if the rectangular frame exists, determining the palm image as a palm photo and ending the detection.
3. The palmprint detection method of claim 1, wherein: the step 3 of calculating the gradient distribution map of the palm area image includes: and calculating the difference value of gray values of each pixel point in the palm area image and four pixel points with the distance r, and calculating the sum of absolute values of the difference values, and taking the sum as the gradient value of the pixel point to obtain a gradient distribution diagram, wherein r is in direct proportion to the ratio of the palm area image to the palm image.
4. The palmprint detection method of claim 1, wherein: the method for acquiring the palm outline gradient map in the step 4 comprises the following steps: and setting the gradient value of the corresponding region of the palm region in the mask image to 0 in the gradient distribution map to obtain a palm outline gradient map.
5. The palmprint detection method of claim 1, wherein: the method for acquiring the gradient map in the palm in the step 4 comprises the following steps: and setting the gradient value of the background region in the mask image in the corresponding region in the gradient distribution map to be 0, so as to obtain the gradient map in the palm.
6. The palmprint detection method of claim 1, wherein: the specific steps of the step 6 for further distinguishing whether the palm image is a palm photo or a real palm based on the palm contour change width are as follows:
step 6.1, acquiring a palm contour curve in a palm region binary image, and acquiring a palm outer contour curve in a palm region image according to the palm contour curve, wherein the palm outer contour curve is a pixel point corresponding to the palm contour curve in the palm region image;
step 6.2, taking n pixel points on the left and right sides of each contour point on the palm contour curve, and n points on the upper and lower sides to form a horizontal gray level curve and a numerical gray level curve;
step 6.3, respectively deriving the second order of the two gray level curves to respectively obtain the change rates of the two gray level curves;
step 6.4, respectively confirming peak points of each gray level curve according to gray level values, and solving two pixel points with the maximum absolute values of the change rates at two sides of the peak points as critical contour points;
step 6.5, calculating the absolute value of the coordinate difference of two critical contour points as the change width of the contour points;
step 6.6, traversing all contour points, and repeating the steps 6.2-6.5;
and 6.7, setting a contour width threshold, calculating the average value of the variation widths of all contour points as the variation width of the palm contour, and if the variation width of the palm contour is smaller than the contour width threshold, determining the palm image as a real palm, otherwise, determining the palm image as a palm photo.
7. The palmprint detection method of claim 6, wherein: in the step 6.2, n has a value of 30.
8. The palmprint detection method of claim 6, wherein: in the step 6.4, if the gray scale curve has a plurality of peak points, the point closest to the center point of the gray scale curve is taken as the peak point, and the gray scale value of the peak point is greater than the gray scale value of the 3 pixel points adjacent to the peak point.
9. The palmprint detection method of claim 6, wherein: in the step 6.5, calculating the absolute value of the coordinate difference between the two critical contour points as the variation width of the contour point includes: and calculating column coordinates of two critical contour points on the horizontal gray scale curve as the horizontal variation width of the contour point, and calculating row coordinates of two critical contour points on the vertical gray scale curve as the vertical variation width of the contour point, wherein the variation width of the contour point is equal to the average value of the horizontal variation width and the vertical variation width of the contour point.
10. The palmprint detection method of claim 1, wherein: after the palm image of the user is obtained, the step 1 is used for removing fixed noise from the palm image, and the method comprises the following steps: and counting the minimum non-zero gray values of all pixel points in the palm image, taking the minimum non-zero gray values as fixed noise, and subtracting the fixed noise from the gray value of each pixel point in the palm image to obtain the palm image with the fixed noise removed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311041952.3A CN116798077B (en) | 2023-08-18 | 2023-08-18 | Palm photo detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311041952.3A CN116798077B (en) | 2023-08-18 | 2023-08-18 | Palm photo detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116798077A true CN116798077A (en) | 2023-09-22 |
| CN116798077B CN116798077B (en) | 2023-11-07 |
Family
ID=88048226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311041952.3A Active CN116798077B (en) | 2023-08-18 | 2023-08-18 | Palm photo detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116798077B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10123331A1 (en) * | 2001-05-14 | 2002-11-28 | Infineon Technologies Ag | Method for recognizing falsification during finger printing, involves determining the ratio of finger rills to finger lines in finger print images |
| CN102436650A (en) * | 2010-09-29 | 2012-05-02 | 奥林巴斯株式会社 | image processing apparatus and image processing method |
| CN103559489A (en) * | 2013-11-19 | 2014-02-05 | 沈阳工业大学 | Method for extracting features of palm in non-contact imaging mode |
| CN106650703A (en) * | 2017-01-06 | 2017-05-10 | 厦门中控生物识别信息技术有限公司 | Palm anti-counterfeiting method and apparatus |
| US20180300571A1 (en) * | 2015-10-10 | 2018-10-18 | Xiamen Zkteco Information Technology Co., Ltd. | Finger vein identification method and device |
| CN111274851A (en) * | 2018-12-05 | 2020-06-12 | 上海中移信息技术有限公司 | Living body detection method and device |
| CN114782478A (en) * | 2022-06-22 | 2022-07-22 | 北京圣点云信息技术有限公司 | Palm image segmentation method and device |
-
2023
- 2023-08-18 CN CN202311041952.3A patent/CN116798077B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10123331A1 (en) * | 2001-05-14 | 2002-11-28 | Infineon Technologies Ag | Method for recognizing falsification during finger printing, involves determining the ratio of finger rills to finger lines in finger print images |
| CN102436650A (en) * | 2010-09-29 | 2012-05-02 | 奥林巴斯株式会社 | image processing apparatus and image processing method |
| CN103559489A (en) * | 2013-11-19 | 2014-02-05 | 沈阳工业大学 | Method for extracting features of palm in non-contact imaging mode |
| US20180300571A1 (en) * | 2015-10-10 | 2018-10-18 | Xiamen Zkteco Information Technology Co., Ltd. | Finger vein identification method and device |
| CN106650703A (en) * | 2017-01-06 | 2017-05-10 | 厦门中控生物识别信息技术有限公司 | Palm anti-counterfeiting method and apparatus |
| CN111274851A (en) * | 2018-12-05 | 2020-06-12 | 上海中移信息技术有限公司 | Living body detection method and device |
| CN114782478A (en) * | 2022-06-22 | 2022-07-22 | 北京圣点云信息技术有限公司 | Palm image segmentation method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116798077B (en) | 2023-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414333B (en) | Image boundary detection method and device | |
| KR100480781B1 (en) | Method of extracting teeth area from teeth image and personal identification method and apparatus using teeth image | |
| US9251614B1 (en) | Background removal for document images | |
| US10558841B2 (en) | Method and apparatus for recognizing fingerprint ridge point | |
| US7853047B2 (en) | System for recognizing fingerprint image, method and program for the same | |
| CN112232332B (en) | Non-contact palm detection method based on video sequence | |
| CN105447489B (en) | A kind of character of picture OCR identifying system and background adhesion noise cancellation method | |
| KR20100080712A (en) | Method for setting lip region for lip reading and apparatus for the same | |
| JP6338429B2 (en) | Subject detection apparatus, subject detection method, and program | |
| US10262185B2 (en) | Image processing method and image processing system | |
| CN116798077B (en) | Palm photo detection method | |
| CN112016565A (en) | Segmentation method for fuzzy numbers at account number of financial bill | |
| CN115578781A (en) | Method for detecting and identifying iris by removing shielding and readable storage medium | |
| CN114463814B (en) | Quick certificate photo glasses detection method based on image processing | |
| CN111199527B (en) | Finger vein image noise detection method based on multi-direction self-adaptive threshold | |
| CN112528741B (en) | State identification method and device for transformer substation pressure plate | |
| JP6580201B2 (en) | Subject detection apparatus, subject detection method, and program | |
| JP2005010842A (en) | Banded pattern extraction system and line pattern extraction method | |
| CN117115867B (en) | Palm vein image living body detection method | |
| KR20070076187A (en) | Fingerprint recognition method | |
| US7577277B2 (en) | Method of binarizing images containing linear structures | |
| CN115909468B (en) | Face five sense organs shielding detection method, storage medium and system | |
| JPH05342412A (en) | Extracting system for gradient vector and feature extracting system for character recognition | |
| CN114841896B (en) | Image processing method, apparatus, and computer-readable storage medium | |
| JP4732626B2 (en) | Form processing method, apparatus, and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |