Sensor-oriented feature usability evaluation in fingerprint segmentation

Existing fingerprint segmentation methods usually process fingerprint images captured by different sensors with the same feature or feature set. We propose to improve the fingerprint segmentation result in view of an important fact that images from different sensors have different characteristics for segmentation. Feature usability evaluation, which means to evaluate the usability of features to find the personalized feature or feature set for different sensors to improve the performance of segmen-tation. The need for feature usability evaluation for fingerprint segmen-tation is raised and analyzed as a new issue. To address this issue, we present a decision-tree-based feature-usability evaluation method, which utilizes a C4.5 decision tree algorithm to evaluate and pick the best suitable feature or feature set for fingerprint segmentation from a typical candidate feature set. We apply the novel method on the FVC2002 database of fingerprint images, which are acquired by four different respective sensors and technologies. Experimental results show that the accuracy of segmentation is improved, and time consumption for feature extraction is dramatically reduced with selected feature(s). 1 Introduction Fingerprint recognition systems have been deployed in a wide variety of application domains, including forensics, civil identification, access control, etc. 1,2 In an automatic fingerprint recognition system, captured images typically go through several processing steps including fingerprint segmentation, image enhancement, binarization, thinning, minutiae detection, and matching 1 in general. Fingerprint segmentation, as a preprocessing step, plays an important role in an automatic fingerprint recognition system. Effective segmentation does not only decrease detecting spurious minutiae but also reduce the time of subsequent processing. Fingerprint segmentation aims to partition a fingerprint image into two parts: the foreground and the background. The foreground is recorded from the contact of a fingertip with the sensor. The background is the noisy area at the border of an image, which has no effective information. Many methods for fingerprint segmentation have been discussed in previous literatures. They can be roughly categorized into the following two types: block-wise methods