Contactless Fingerprint Foreground Masks Using Flash Difference Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contactless fingerprint identification systems face challenges in accurately segmenting foreground slap/fingers from background noise and dynamic scenes due to the absence of image sequences for statistical modeling and uneven lighting, which traditional background subtraction methods struggle to address.
Innovation Solution
A method involving the acquisition of two images with and without flash light, followed by calculating a difference map, applying adaptive binarization thresholds with flashlight and background enhancement factors, and performing morphological noise removal to generate a foreground mask.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional statistical background modelling is used, then background can be removed effectively, but it requires a sequence of images which is not available in contactless fingerprint capture
Solution Approach 1:
The patent segments the single image into two virtual images by selectively activating the flash light for different regions. The flash on image captures foreground (fingers) while the flash off image captures background, enabling background subtraction without requiring a sequence of images.
Solution Approach 2:
The patent changes the illumination parameter (flash light state) to create two distinct images from a single capture moment. By varying the flash activation state, it generates sufficient information for background modelling without requiring temporal sequences.
2Illumination intensity
If flash light is used to illuminate the slap/fingers, then foreground visibility is improved, but uneven lighting distribution causes variant grayscale values that complicate segmentation
Solution Approach 1:
The patent introduces an intermediary adaptive thresholding mechanism that accounts for uneven flash illumination. The threshold is calculated based on local image statistics and flash compensation factors, mediating between the uneven lighting and the segmentation requirement.
Solution Approach 2:
The patent applies local quality adjustment by using spatially varying threshold values and flash compensation factors. Different regions of the image receive customized processing parameters based on their local illumination conditions, enabling accurate segmentation despite uneven lighting.
3Loss of information
If background scene and noise are captured in the image, then complete scene information is obtained, but foreground identification becomes more difficult due to salient background elements
Solution Approach 1:
The patent extracts the background information into a separate image (flash off image) and then subtracts it from the flash on image. This separation technique removes the salient background elements while preserving foreground information, making foreground identification straightforward.
Solution Approach 2:
The patent uses periodic flash activation (on and off states) to capture two complementary images. This periodic illumination pattern enables the system to separate foreground and background information through temporal multiplexing, even though the overall capture process is rapid.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach effectively identifies and extracts the foreground slap/fingers area, enhancing the performance and speed of contactless fingerprint identification systems while reducing hardware complexity and cost.
Implementation Method 1
acquisition of two images of the slap/fingers in a contactless position in vicinity of the reader, one image taken with flash light on and one image taken without flash light
Data Source
Figure 1~3
Figure 4~6
Figure 7
AI summary
The present invention relates to a method to generate a slap/fingers foreground mask to be used for subsequent image processing of fingerprints on an image acquired using a contactless fingerprint reader having at least a flash light, said method comprising the following steps: acquisition of two images of the slap/fingers in a contactless position in vicinity of the reader, one image taken with flash light on and one image taken without flash light, calculation of a difference map between the image acquired with flash light and the image acquired without flash light, calculation of an adaptive binarization threshold for each pixel of the image, the threshold for each pixel being the corresponding value in the difference map, to which is subtracted this corresponding value multiplied by a corresponding flashlight compensation factor value determined in a flashlight compensation factor map using an image of a non-reflective blank target acquired with flash light and to which is added this corresponding value multiplied by a corresponding background enhancement factor value determined in a background enhancement factor map using the image acquired without flash light, binarization of the difference map by attributing a first value to pixels where the adaptive binarization threshold value is higher than the corresponding value in the difference map and a second value to pixels where the adaptive binarization threshold value is lower than the corresponding value in the difference map, the binarized image being the slap/fingers foreground mask.