CN-114144812-B - Method for generating palm/finger foreground mask

Abstract

The invention relates to a method of generating a palm/finger foreground mask for subsequent image processing of a fingerprint on an image acquired using a contactless fingerprint reader with at least a flash, the method comprising the steps of-acquiring two images of the palm/finger in a contactless position near the reader, one image being acquired with the flash on and one image being acquired without the flash, -calculating an adaptive binarization threshold value for each pixel of the image, the threshold value for each pixel being a corresponding value in the difference map, subtracting the corresponding value multiplied by the corresponding flash compensation factor value determined in the flash compensation factor for the image of the non-reflective blank object acquired with the flash, and adding the corresponding value multiplied by the corresponding background enhancement factor determined in the background enhancement factor for the image acquired with the flash off, -calculating a difference map between the image acquired with the flash and the image acquired without the flash, -calculating a second value wherein the threshold value for each pixel is a difference map, the second value being a difference map value, and the difference map is a difference map value being a difference map.

Inventors

• DING YI
• A.J.Wang

Assignees

• 泰雷兹数字安全法国股份有限公司
• 泰雷兹数字安全法国股份有限公司

Dates

Publication Date

20260421

Application Date

20200629

Priority Date

20200629

Claims (7)

1. 1. A method of generating a palm/finger foreground mask for subsequent image processing of a fingerprint on an image acquired using a non-contact fingerprint reader having at least a flash, the method comprising the steps of: acquiring two images of the palm/finger in a non-contact position near the reader, one image taken with the flash on and one image taken without the flash, -Calculating the difference between the image acquired with the flash and the image acquired without the flash using the equation ID (x, y) = |if (x, y) -INF (x, y) |, where IF (x, y) is the pixel value of the flash image at location (x, y) and INF (x, y) is the pixel value of the non-flash image at the same location, and ID (x, y) is the absolute difference between the two images IF and INF; -generating a disparity map based on the calculation of the disparity, wherein the disparity map displays a portion of the image comprising the palm/finger that can be illuminated by the flash; -calculating a flash compensation factor based on a reference Image (IR) of a non-reflective target with the flash on using the equation α (x, y) = IS (x, y)/IR (x, y), where α (x, y) IS the flash compensation factor of the image pixel at location (x, y), IS (x, y) IS the standard illumination value of pixel (x, y) which IS equal to the average brightness level in the image center area without vignetting effect, and IR (x, y) IS the reference pixel value at the same location; -generating a flash compensation factor map based on the calculation of the flash compensation factor; -calculating a backlight enhancement factor using the equation β (x, y) =bnf (x, y)/BF, wherein BF is the average intensity of the brightness of the palm/finger when acquiring a plurality of sample images across different subjects with the flash on, and BNF (x, y) is the average intensity of the brightness with the flash off; -generating a backlight enhancement factor map based on the calculation of the backlight enhancement factor; -calculating the adaptive binarization threshold (T) using the equation T (x, y) =id (x, y) × (1- α (x, y) +β (x, y)) Generating a foreground mask using the equation M (x, y) =255 if T (x, y) > ID (x, y), and M (x, y) being 0 if T (x, y) < ID (x, y), where M (x, y) is the pixel value of the initial foreground mask IFM at position (x, y).
2. 2. The method of claim 1, further comprising the step of noise removal in the binarized image.
3. 3. The method of claim 2, wherein the noise is removed by morphological operations.
4. 4. A method according to any one of claims 1 to 3, further comprising using the foreground mask as input to other modules in a contactless fingerprinting system for advanced contactless fingerprinting tasks.
5. 5. A contactless acquisition fingerprint system comprising at least one contactless fingerprint reader with at least one flash, and further comprising a contactless acquisition fingerprint image processor connected to the at least one contactless fingerprint reader, the contactless fingerprint reader being adapted to acquire an image of a palm/finger in a contactless position in the vicinity of the reader with or without the flash for acquiring a fingerprint of a user, the processor being adapted to generate a palm/finger foreground mask from the image according to the method of claim 1.
6. 6. The non-contact fingerprint acquisition system of claim 5, wherein the processor is further adapted to remove noise from the binarized image.
7. 7. The non-contact fingerprint acquisition system of claim 6, wherein the noise is removed by morphological operations.

Description

Method for generating palm/finger foreground mask Technical Field The present invention relates to a method of generating a palm/finger foreground mask for subsequent image processing of a fingerprint on an image acquired using a contactless fingerprint reader having at least a flash. The invention also relates to a non-contact acquired fingerprint image processor connected to at least a non-contact fingerprint reader having at least a flash and adapted to acquire an image of a palm/finger in a non-contact position in the vicinity of the reader with or without the flash for acquiring a fingerprint of a user implementing the method. Background With conventional contact methods, the fingerprint is captured by direct indentation of the finger on a recording medium or device, such as an ink, optical sensor or electronic sensor. As the demand for faster capture speeds and better user experience grows, contactless fingerprint devices are introduced into the biometric market. The present invention relates to a novel method and apparatus for adaptive background subtraction of non-contact fingerprint images. More specifically, a contactless fingerprint reader captures a contactless fingerprint image. Unlike conventional contact fingerprint readers that capture only the palm/finger touching the reader, a contactless fingerprint reader takes a photograph of the entire palm/finger presented above the device. Thus, due to the nature of the photo representation from the contactless fingerprint reader, the captured photo contains both the palm/finger as foreground and the scene behind the palm/finger as well as noise as background. To identify the position of the palm/fingers (i.e., foreground) in the captured image, background scene and noise need to be removed. In a contactless fingerprint image, background subtraction becomes more challenging because: 1. typically, only a single image is captured for the same palm/finger, such that traditional statistical background modeling that requires image sequences will not work; 2. the dynamics of strong background light and the presence of strong background scene/noise, for example, can be significant in the image, which can even suppress foreground fingers; 3. the illuminance/brightness from the captured image is unevenly distributed such that the foreground palms/fingers have varying gray scales while their positions vary across different subjects. Background subtraction is an essential step in many image processing and computer vision applications or systems. In the past few decades, various methods have been proposed in background subtraction in order to segment foreground objects from background scenes. In one typical application class, the foreground is identified by computing the difference between frames with objects and frames without background. In other types of representative applications, it is assumed that the background can be statistically modeled and updated based on the image sequence. Those general techniques are described, for example, in the following documents: • US6411744B1 “Method and apparatus for performing a clean background subtraction”. Ahmed M. Elgammal, david Harwood and Larry S.Davis. "Non-PARAMETRIC MODEL FOR BACKGROUND SUBTRACTION". In Proceedings of the, 6, th European Conference on Computer Vision ", 2000. • US5748775A “Method and apparatus for moving object extraction based on background subtraction” • M. Piccardi, "Background subtraction techniques: a review"2004 IEEE International Conference on Systems, Man and Cybernetics • Z. Zivkovic, "Improved adaptive Gaussian mixture model for background subtraction," Proceedings of the 17th International Conference on Pattern Recognition, 2004 • Sobral, Andrews & Vacavant, Antoine. "A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos". Computer Vision and Image Understanding, 2014 S. Liao, G. Zhao, V. Kellokumpu, M. Pietik ä inen and S. Z. Li, "Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes," 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, 2010 W. Kim and C. Kim, "Background Subtraction for Dynamic Texture Scenes Using Fuzzy Color Histograms," in IEEE SIGNAL Processing Letters, vol.19, no. 3, pp., 127-130, 2012, 3. Dar-SHYANG LEE, "EFFECTIVE GAUSSIAN MIXTURE LEARNING FOR VIDEO BACKGROUND SUBTRACTION," in IEEE Transactions on PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol.27, no. 5, pp. 827-832, month 5 2005. J. Yao and J. Odobez, "Multi-Layer Background Subtraction Based on Color and Texture," 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, 2007 K, shafique, O, javed and M. Shah, "A Hierarchical Approach to Robust Background Subtraction using Color and Gradient Information,"Motion and Video Computing, IEEE Workshop on (MOTION), Orlando, Florida, 2002. However, in a contactless fingerprinting system, both metho