CN116665258B - Palm image finger seam segmentation method - Google Patents

Palm image finger seam segmentation method Download PDF

Info

Publication number
CN116665258B
CN116665258B CN202310942998.6A CN202310942998A CN116665258B CN 116665258 B CN116665258 B CN 116665258B CN 202310942998 A CN202310942998 A CN 202310942998A CN 116665258 B CN116665258 B CN 116665258B
Authority
CN
China
Prior art keywords
pixel
point
palm
seam
finger
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202310942998.6A
Other languages
Chinese (zh)
Other versions
CN116665258A (en
Inventor
罗秋伟
赵国栋
李学双
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Shengdian Century Technology Co ltd
Original Assignee
Jiangsu Shengdian Century Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Shengdian Century Technology Co ltd filed Critical Jiangsu Shengdian Century Technology Co ltd
Priority to CN202310942998.6A priority Critical patent/CN116665258B/en
Publication of CN116665258A publication Critical patent/CN116665258A/en
Application granted granted Critical
Publication of CN116665258B publication Critical patent/CN116665258B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • 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
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • 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
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • 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
    • G06V10/40—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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The application relates to a palm image finger seam segmentation method, belonging to the technical field of biological recognition, which comprises the steps of sequentially selecting n pixel frames in a palm image, calculating pixel differences between a pixel frame center point and all boundary points of the pixel frame, calculating the average value of the pixel differences between the pixel frame center point and all boundary points of the pixel frame, judging whether the pixel frame center point is a finger seam pre-judging point according to the pixel value of the pixel frame center point, the average value of the pixel differences between the pixel frame center point and all boundary points of the pixel frame, and the included angle formed by the boundary points corresponding to the two minimum absolute values of the pixel differences and the pixel frame center point, judging whether the finger seam pre-judging point is the finger seam point according to the number of other finger seam pre-judging points in the neighborhood range of the finger seam pre-judging point, performing binarization processing on the palm image to obtain a palm binary image, mapping the finger seam point to the palm binary image for pixel change, thereby accurately positioning the finger seam region and improving the recognition passing rate.

Description

Palm image finger seam segmentation method
Technical Field
The application belongs to the technical field of biological feature recognition, and particularly relates to a palm image finger seam segmentation method.
Background
In palm print recognition or palm vein recognition, the ROI area of the palm needs to be positioned according to the concave points of the finger root.
For example, the application patent with the publication number of CN103268483B discloses a palmprint recognition method under open environment non-contact acquisition, a low-resolution common camera is adopted to acquire palmprint images, a human hand is required to be naturally opened, middle fingers are vertically upwards placed in a certain range in front of the camera, and a skin color model is firstly established to extract the human hand from a complex background; then locating the finger root point through the key point, and establishing a coordinate system to extract the palmprint ROI; then, a texture primitive algorithm based on statistics is adopted to extract palmprint characteristics; and finally, performing feature matching by using cosine similarity to realize palm print recognition.
However, in the process of actually collecting palmprint or palmar vein by the collecting device, the collected palmprint or palmar vein image is often a closed palms due to the randomness of palm placement, and the adjacent fingers are adhered, so that the finger root pits are difficult to locate, and the ROI area of the palms cannot be accurately located, so that the passing rate of recognition is seriously affected.
Disclosure of Invention
The application aims to provide a palm image finger seam segmentation method, which aims to solve the problem that when a palm image is acquired, a palm ROI (region of interest) is difficult to position due to palm closure, so that the recognition passing rate is affected.
In order to solve the technical problems, the technical scheme provided by the application is as follows:
the application relates to a palm image finger seam segmentation method, which comprises the following steps:
step 1, acquiring a palm image of a user, and calculating a pixel average value th1 of the palm image;
step 2, selecting n-n pixel frames, wherein the pixel value of the central point of each pixel frame is as followsI 0 ；
Step 3, comparing the pixel value of the center point of the pixel frame with the average value of the pixels of the palm image, ifI 0 > th1, determining that the center point of the pixel frame is not a seam point, returning to step 2, ifI 0 Less than or equal to th1, and performing the next judgment;
step 4, respectively calculating pixel differences between the center point of the pixel frame and each boundary point of the pixel frame;
step 5, calculating the average value of the pixel differences between the center point of the pixel frame and the boundary points of the pixel frameAveD；
Step 6, setting an average value threshold th2, ifAveDIf the central point of the pixel frame is more than th2, judging that the central point of the pixel frame is not a seam point, returning to the step 2, ifAveDNot more than th2, carrying out the next step;
step 7, taking boundary points corresponding to two values with the minimum absolute value of the pixel difference in the step 4, and forming an included angle with the center point of the pixel frame, wherein the included angle isαSetting an included angle thresholdValue th3, ifαIf the sum is more than th3, judging that the center point of the pixel frame is a seam indicating pre-judging point, otherwise, judging that the center point of the pixel frame is not a seam indicating point;
step 8, repeating the step 2 to the step 7 on the palm image full graph, and determining all the pre-judgment points of the finger joints;
step 9, judging whether the finger seam pre-judging point is a finger seam point or not based on the number of other finger seam pre-judging points in the (n+2) neighborhood range around the finger seam pre-judging point;
and 10, performing binarization processing on the palm image to obtain a palm binary image, and mapping the finger seam points to the palm binary image to perform pixel change so as to divide the finger seam.
Preferably, in the step 4, a calculation formula for calculating the pixel difference between each boundary point of the pixel frame and the center point of the pixel frame is as follows:
，
in the formula (i),I 0 is the pixel value of the center point of the pixel frame,I i for the pixel value of any one pixel box boundary point,dI i is the difference between the pixel value of the center point of the pixel frame and the pixel value of any boundary point of the pixel frame, n is the width of the pixel frame,iis the firstiAnd (5) pixel frame boundary points.
Preferably, in the step 5, the average value of pixel differences between each boundary point of the pixel frame and the center point of the pixel frameAveDThe calculation formula of (2) is as follows:
。
preferably, in the step 6, the average value threshold th2 is taken to be-5.
Preferably, in the step 7, the angle between the boundary point corresponding to the two minimum absolute values of the pixel difference and the center point of the pixel frame isαThe calculation formula of (2) is as follows:
，
in the formula (i),x 1 、y 1 an abscissa representing one of boundary points having the smallest absolute value of a pixel difference from a center point of the pixel frame,x 2 、y 2 the abscissa and ordinate representing another boundary point having the smallest absolute value of the pixel difference from the center point of the pixel frame,x 0 、y 0 representing the abscissa of the center point of the pixel frame.
Preferably, in the step 7, the included angle threshold th3 is 150 °.
Preferably, in the step 9, when the number N of other finger seam pre-determined points in the (n+2) neighborhood range surrounding the finger seam pre-determined point satisfies (n+2)/2 < N < n+2), the finger seam pre-determined point is determined to be a finger seam point.
Preferably, in the step 10, mapping the finger seam point onto the palm binary image for pixel change is as follows: and if the pixel value of the pixel point corresponding to the finger joint point on the palm binary image is 1, adjusting the pixel value to be 0.
Preferably, the palm image acquired in the step 1 is a palmprint image or a palmvein image.
Compared with the prior art, the application has the following beneficial technical effects:
according to the palm image seam-pointing segmentation method, n pixel frames are sequentially selected from a palm image, pixel differences between boundary points of the pixel frames and pixel frame center points are calculated, average values of the pixel differences between the boundary points of the pixel frames and the pixel frame center points are calculated, whether the pixel frame center points are seam-pointing pre-judgment points or not is judged according to pixel values of the pixel frame center points, the average values of the pixel differences between the boundary points of the pixel frames and the pixel frame center points, and the included angle formed by the boundary points corresponding to the two minimum absolute values of the pixel differences and the pixel frame center points, and then whether the seam-pointing pre-judgment points are seam-pointing points is judged according to the number of other seam-pointing pre-judgment points in the neighborhood range around the seam-pointing pre-judgment points, and pixel change operation is carried out on the pixel points corresponding to the seam-pointing points on a binary image, so that the seam-pointing region is segmented, and a palm region is accurately positioned, and the recognition passing rate is improved.
Drawings
Fig. 1 is a flowchart of a palm image finger seam segmentation method according to the present application.
Detailed Description
The technical solution of the present application is further specifically described by the following specific examples, which are given by way of illustration and not limitation, and all other examples obtained by those skilled in the art without making any inventive effort are within the scope of the present application.
The application relates to a palm image finger seam segmentation method, which comprises the following steps:
step 1, acquiring palm images of a user, wherein the palm images can be palm print images or palm vein images; accumulating the pixel values of each pixel point of the palm image, counting the total number of the pixel points, dividing the accumulated pixel values by the total number of the pixel points to obtain a pixel average value th1 of the whole palm image;
step 2, selecting n x n pixel frames in the palm image, wherein the pixel frames can be 3*3 pixel frames, 5*5 pixel frames and other odd pixel frames, and the pixel value of the central point of the pixel frame isI 0 ；
Step 3, comparing the pixel value of the center point of the pixel frame with the average value of the pixels of the palm image, wherein the pixel value of the finger joint point is generally lower than the pixel value of the surrounding pixel points due to the effect of light scattering, so that the pixel value of the finger joint point is generally lower than the average pixel value of the palm image, and ifI 0 > th1, determining that the center point of the pixel frame is not a seam point, returning to step 2, ifI 0 Less than or equal to th1, and performing the next judgment;
step 4, respectively calculating pixel differences between a pixel frame center point and boundary points of the pixel frame, wherein a calculation formula is as follows:
，
in the formula (i),I 0 is the pixel value of the center point of the pixel frame,I i image for boundary point of any pixel frameThe value of the element is calculated,dI i is the difference between the pixel value of the center point of the pixel frame and the pixel value of any boundary point of the pixel frame, n is the width of the pixel frame,iis the firstiA pixel frame boundary point;
step 5, calculating the average value of the pixel differences between the center point of the pixel frame and the boundary points of the pixel frameAveDThe calculation formula is as follows:
；
step 6. As described above, the pixel value of the finger joint point is lower than the pixel values of other pixel points on the palm image, so that if the finger joint point is the finger joint point, the difference between the finger joint point and the pixel value of other pixel points is less than or equal to 0, so that the average value is the average valueAveDIf the average value is smaller than 0, an average value threshold value th2 is set in the application, and th2 is taken to be-5 according to the actual image batch running result, ifAveDIf the central point of the pixel frame is more than th2, judging that the central point of the pixel frame is not a seam point, returning to the step 2, ifAveDNot more than th2, carrying out the next step;
step 7, taking boundary points corresponding to two values with the minimum absolute value of the pixel difference in the step 4, and forming an included angle with the center point of the pixel frame, wherein the included angle isαAngle of included angleαThe calculation formula of (2) is as follows:
，
in the formula (i),x 1 、y 1 an abscissa representing one of boundary points having the smallest absolute value of a pixel difference from a center point of the pixel frame,x 2 、y 2 the abscissa and ordinate representing another boundary point having the smallest absolute value of the pixel difference from the center point of the pixel frame,x 0 、y 0 an abscissa representing a center point of the pixel frame;
according to the fact that the pixel value of the finger seam point is lower than the pixel values of other pixel points in the palm image, it can be known that the boundary points corresponding to the two values with the minimum absolute value of the pixel difference should be the finger seam point above the center point and the finger seam point below the center point respectively, and the finger seam is approximately in a straight line, so that the two points areThe finger joint points and the central point should be approximately 180 degrees, the included angle threshold value th3 and th3 are set in the application, 150 degrees is taken according to the actual image batch running result, ifαIf the sum is more than th3, judging that the center point of the pixel frame is a seam indicating pre-judging point, otherwise, judging that the center point of the pixel frame is not a seam indicating point;
step 8, repeating the step 2 to the step 7 on the palm image full graph, and determining all the pre-judgment points of the finger joints;
step 9, judging whether the finger seam is a finger seam point or not based on the number of other finger seam pre-judging points in the (n+2) neighborhood around the finger seam pre-judging point, wherein the finger seam is approximately in a straight line, so that a plurality of finger seam points are arranged in the (n+2) neighborhood of the finger seam point, and therefore, whether the finger seam point is the finger seam point or not can be judged according to the number of the finger seam pre-judging points around the finger seam pre-judging point, and the specific judging method of the application comprises the following steps: when the number N of other finger seam pre-judging points in the (n+2) neighborhood range around the finger seam pre-judging point meets (n+2)/2 < N < n+2, judging the finger seam pre-judging point as a finger seam point, otherwise, judging the finger seam pre-judging point as not a finger seam point;
step 10, performing binarization processing on the palm image to obtain a palm binary image, wherein the binarization processing belongs to a well-known technical scheme in the field, and the embodiment is not elaborated again, and then mapping the finger seam points onto the palm binary image for pixel change, and the specific method is as follows: firstly, judging whether the pixel value of the corresponding pixel point of the finger joint point on the palm binary image is 1, if so, adjusting the pixel value to be 0, thereby dividing the finger joint. In the process of actually collecting palmprint or palmar vein by the collecting equipment, the palm is placed randomly, the collected palmprint or palmar vein image is often a closed palm, and adjacent fingers are adhered, so that in the process of binarization processing, the adjacent fingers can be used as a communicating domain to be difficult to divide the finger seam.
Based on the palm image binary image segmented by the finger joints, finger root pits can be positioned, the ROI (region of interest) of the palm image can be conveniently extracted, and palm print image recognition or palm vein image recognition is performed based on the ROI. The method of extracting the ROI area of the palm image, the palm print image and the palm vein image identification is not intended to be protected by the present application, and the ROI area, the palm print and the palm vein image identification can be performed by any method known in the art, and will not be described in detail herein.
The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present application and the core ideas thereof; also, it is within the scope of the present application to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the application.

Claims (9)

1. A palm image finger seam segmentation method is characterized in that: which comprises the following steps:
step 1, acquiring a palm image of a user, and calculating a pixel average value th1 of the palm image;
step 2, selecting n-n pixel frames, wherein the pixel value of the central point of each pixel frame is as followsI 0 ；
Step 3, comparing the pixel value of the center point of the pixel frame with the average value of the pixels of the palm image, ifI 0 > th1, determining that the center point of the pixel frame is not a seam point, returning to step 2, ifI 0 Less than or equal to th1, and performing the next judgment;
step 4, respectively calculating pixel differences between the center point of the pixel frame and each boundary point of the pixel frame;
step 5, calculating the average value of the pixel differences between the center point of the pixel frame and the boundary points of the pixel frameAveD；
Step 6, setting an average value threshold th2, ifAveDIf the central point of the pixel frame is more than th2, judging that the central point of the pixel frame is not a seam point, returning to the step 2, ifAveDNot more than th2, carrying out the next step;
step 7, taking boundary points corresponding to two values with the minimum absolute value of the pixel difference in the step 4, and forming an included angle with the center point of the pixel frame, wherein the included angle isαSetting an included angle threshold th3, ifα> th3, the center point of the pixel frame is determined to be the fingerA seam pre-judging point is adopted, otherwise, the central point of the pixel frame is judged to be not a seam pointing point;
step 8, repeating the step 2 to the step 7 on the palm image full graph, and determining all the pre-judgment points of the finger joints;
step 9, judging whether the finger seam pre-judging point is a finger seam point or not based on the number of other finger seam pre-judging points in the (n+2) neighborhood range around the finger seam pre-judging point;
and 10, performing binarization processing on the palm image to obtain a palm binary image, and mapping the finger seam points to the palm binary image to perform pixel change so as to divide the finger seam.
2. The palm image finger seam segmentation method according to claim 1, wherein: in the step 4, the calculation formula for calculating the pixel difference between each boundary point of the pixel frame and the center point of the pixel frame is as follows:
，
in the formula (i),I 0 is the pixel value of the center point of the pixel frame,I i for the pixel value of any one pixel box boundary point,dI i is the difference between the pixel value of the center point of the pixel frame and the pixel value of any boundary point of the pixel frame, n is the width of the pixel frame,iis the firstiAnd (5) pixel frame boundary points.
3. The palm image finger seam segmentation method according to claim 2, wherein: in the step 5, the average value of the pixel differences between each boundary point and the center point of the pixel frameAveDThe calculation formula of (2) is as follows:
。
4. the palm image finger seam segmentation method according to claim 2, wherein: in the step 6, the average value threshold th2 is taken to be-5.
5. The palm image finger seam segmentation method according to claim 1, wherein: in the step 7, the angle between the boundary point corresponding to the two minimum absolute values of the pixel difference and the center point of the pixel frame isαThe calculation formula of (2) is as follows:
，
in the formula (i), x 1 、y 1 an abscissa representing one of boundary points having the smallest absolute value of a pixel difference from a center point of the pixel frame, x 2 、y 2 the abscissa and ordinate representing another boundary point having the smallest absolute value of the pixel difference from the center point of the pixel frame, x 0 、y 0 representing the abscissa of the center point of the pixel frame.
6. The palm image finger seam segmentation method according to claim 5, wherein: in the step 7, the included angle threshold th3 is 150 °.
7. The palm image finger seam segmentation method according to claim 5, wherein: in the step 9, when the number N of other finger seam pre-judging points in the (n+2) neighborhood range around the finger seam pre-judging point satisfies (n+2)/2 < N < n+2, the finger seam pre-judging point is judged to be a finger seam point.
8. The palm image seam segmentation method according to claim 1, wherein in the step 10, the seam point is mapped onto a palm binary image for pixel change as follows: and if the pixel value of the pixel point corresponding to the finger joint point on the palm binary image is 1, adjusting the pixel value to be 0.
9. The palm image finger seam segmentation method according to claim 1, wherein: the palm image acquired in the step 1 is a palm print image or a palm vein image.
CN202310942998.6A 2023-07-31 2023-07-31 Palm image finger seam segmentation method Active CN116665258B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310942998.6A CN116665258B (en) 2023-07-31 2023-07-31 Palm image finger seam segmentation method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310942998.6A CN116665258B (en) 2023-07-31 2023-07-31 Palm image finger seam segmentation method

Publications (2)

Publication Number Publication Date
CN116665258A CN116665258A (en) 2023-08-29
CN116665258B true CN116665258B (en) 2023-10-20

Family

ID=87710041

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310942998.6A Active CN116665258B (en) 2023-07-31 2023-07-31 Palm image finger seam segmentation method

Country Status (1)

Country Link
CN (1) CN116665258B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117133027B (en) * 2023-10-26 2024-02-09 江苏圣点世纪科技有限公司 Palm boundary segmentation method in palm vein recognition under complex background

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103268483A (en) * 2013-05-31 2013-08-28 沈阳工业大学 Method for recognizing palmprint acquired in non-contact mode in open environment
CN105512656A (en) * 2014-09-22 2016-04-20 郭进锋 Palm vein image collection method
CN113936307A (en) * 2021-12-17 2022-01-14 北京圣点云信息技术有限公司 Vein image recognition method and device based on thin film sensor
CN114783010A (en) * 2022-06-22 2022-07-22 北京圣点云信息技术有限公司 Extraction method of interest region of palm print image

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103268483A (en) * 2013-05-31 2013-08-28 沈阳工业大学 Method for recognizing palmprint acquired in non-contact mode in open environment
CN105512656A (en) * 2014-09-22 2016-04-20 郭进锋 Palm vein image collection method
CN113936307A (en) * 2021-12-17 2022-01-14 北京圣点云信息技术有限公司 Vein image recognition method and device based on thin film sensor
CN114783010A (en) * 2022-06-22 2022-07-22 北京圣点云信息技术有限公司 Extraction method of interest region of palm print image

Also Published As

Publication number Publication date
CN116665258A (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN107578035B (en) Human body contour extraction method based on super-pixel-multi-color space
Wu et al. Fingerprint image enhancement method using directional median filter
CN108009472B (en) Finger back joint print recognition method based on convolutional neural network and Bayes classifier
WO2021027364A1 (en) Finger vein recognition-based identity authentication method and apparatus
Guan et al. Accurate segmentation of partially overlapping cervical cells based on dynamic sparse contour searching and GVF snake model
Lu et al. Finger vein identification using polydirectional local line binary pattern
CN116665258B (en) Palm image finger seam segmentation method
CN108615239B (en) Tongue image segmentation method based on threshold technology and gray level projection
CN112232332B (en) Non-contact palm detection method based on video sequence
CN107729820A (en) A kind of finger vein identification method based on multiple dimensioned HOG
CN104766316B (en) New lip partitioning algorithm in tcm inspection
Yang et al. Superpixel based finger vein ROI extraction with sensor interoperability
CN111507206A (en) Finger vein identification method based on multi-scale local feature fusion
CN108629762B (en) Image preprocessing method and system for reducing interference characteristics of bone age evaluation model
CN108921813A (en) Unmanned aerial vehicle detection bridge structure crack identification method based on machine vision
CN112699845A (en) Online non-contact palm vein region-of-interest extraction method
Gonçalves et al. Automatic system for counting cells with elliptical shape
CN111639562A (en) Intelligent positioning method for palm region of interest
CN105930811A (en) Palm texture feature detection method based on image processing
Jarjes et al. GVF snake-based method for accurate pupil contour detection
Kabbara et al. An automatic algorithm for human identification using hand X-ray images
Lin et al. Image segmentation based on edge detection and region growing for thinprep-cervical smear
Wang et al. A novel finger vein pattern extraction method using oriented filtering technology
CN113936305B (en) Middle finger position confirmation method and feature extraction method in palm recognition process
Fernandez et al. Fingerprint core point detection using connected component approach and orientation map edge tracing approach

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