Fingerprint Region Extraction Using Guard Regions and Color Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional fingerprint recognition systems using cameras on portable devices face challenges in accurately extracting fingerprint images and ridge directions due to noise, outliers, and cluttered backgrounds, leading to reduced recognition accuracy compared to contact-type sensors.
Innovation Solution
A method and apparatus that utilize a guard region within the captured image to extract fingerprint regions based on predicted color distribution, reducing outliers and improving ridge direction extraction by dividing the image into blocks and applying gradient calculations to enhance image quality and binarization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a camera is used to capture fingerprint images in portable devices, then the device complexity is reduced and portability is improved, but the measurement precision and reliability of fingerprint recognition deteriorate due to noise, outliers, and cluttered backgrounds
Solution Approach 1:
The patent divides the captured image into multiple blocks and processes each block separately to extract ridge directions. This segmentation approach allows the system to handle noisy camera-captured images by focusing on local regions, improving measurement precision while maintaining the simplicity of using a camera in portable devices
Solution Approach 2:
The patent applies preliminary image processing steps including noise filtering, outlier removal, and background subtraction before extracting fingerprint characteristics. These preliminary actions clean up the camera-captured image data, enabling reliable fingerprint recognition despite the inherent limitations of camera-based imaging in portable devices
2Device complexity
If the least square algorithm is used to determine maximum ridge direction, then the calculation process is simplified, but the measurement precision deteriorates due to increased affect of outliers such as wounds and noise
Solution Approach 1:
The patent extracts and removes outliers from the image data before applying the least square algorithm. By taking out the harmful elements (outliers, noise, wound artifacts) that would otherwise skew the ridge direction calculation, the system maintains calculation simplicity while significantly improving measurement precision
Solution Approach 2:
The patent converts the harmful effect of outliers by using statistical methods to identify and eliminate them, transforming the problematic noisy data into clean input for the least square algorithm. This approach allows the simple least square calculation to produce accurate ridge directions by converting the harmful noise into beneficial cleaned data
3Object-affected harmful factors
If the fingerprint region is extracted from the entire captured image, then the background noise is reduced, but the extraction accuracy deteriorates when the fingerprint extends beyond the guard region
Solution Approach 1:
The patent uses color information as an additional dimension to extend the fingerprint region extraction beyond the guard region boundaries. By incorporating color data, the system can identify fingerprint regions that extend outside the initial guard region while still filtering out background noise, thus improving extraction accuracy without sacrificing noise reduction
Data Source
AI summary
An apparatus and methods for capturing a fingerprint are provided. In a first example method, first fingerprint image may be obtained in a guard region within a captured image, the guard region including less than all of the captured image. A fingerprint region may be extracted from the captured image based on a predicted color distribution, the predicted color distribution based on color information associated with the first fingerprint image, the extracted fingerprint region including the first fingerprint image within the guard region and at least a portion of the fingerprint region extending beyond the guard region within the captured image. In a second example method, guard region may be defined within a picture boundary area, the defined guard region including less than all of the picture boundary area. At least one image may be captured, the captured image spanning the picture boundary area. Information associated with the captured image may be extracted from within the guard region. Portions of the captured image associated with a user's fingerprint may then be extracted based on the extracted information, the identified portions including a first portion within the guard region of the captured image and a second portion within the picture boundary area of the captured image outside of the guard region. In another example, an apparatus may be configured to perform either of the above-described first and second example methods.