Dong-Jae Lee

A robust fingerprint matching algorithm using local alignment

This paper describes a minutiae-based fingerprint matching algorithm. Generally, a fingerprint image is nonlinearly deformed by torsion and traction when a finger is pressed on the sensor. This nonlinear deformation changes both position and orientation of minutiae and decreases the reliability of minutiae. Therefore, in matching algorithm using one reference minutiae pair, the reliability of a minutia decreases as the distance from the minutia to the minutia used for alignment increases. The proposed algorithm overcomes this problem by normalizing the distance between minutiae and using local alignment. Experimental results show that the performance of the proposed algorithm is superior to that of using one reference minutiae pair.

Recognizable-Image Selection for Fingerprint Recognition With a Mobile-Device Camera

This paper proposes a recognizable-image selection algorithm for fingerprint-verification systems that use a camera embedded in a mobile device. A recognizable image is defined as the fingerprint image which includes the characteristics that are sufficiently discriminating an individual from other people. While general camera systems obtain focused images by using various gradient measures to estimate high-frequency components, mobile cameras cannot acquire recognizable images in the same way because the obtained images may not be adequate for fingerprint recognition, even if they are properly focused. A recognizable image has to meet the following two conditions: First, valid region in the recognizable image should be large enough compared with other nonrecognizable images. Here, a valid region is a well-focused part, and ridges in the region are clearly distinguishable from valleys. In order to select valid regions, this paper proposes a new focus-measurement algorithm using the secondary partial derivatives and a quality estimation utilizing the coherence and symmetry of gradient distribution. Second, rolling and pitching degrees of a finger measured from the camera plane should be within some limit for a recognizable image. The position of a core point and the contour of a finger are used to estimate the degrees of rolling and pitching. Experimental results show that our proposed method selects valid regions and estimates the degrees of rolling and pitching properly. In addition, fingerprint-verification performance is improved by detecting the recognizable images.

Fingerprint fusion based on minutiae and ridge for enrollment

This paper presents a method to integrate the multiple impressions of a finger for improving fingerprint verification performance. Small-sized sensor has advantage that it can be used in many application fields. However, sufficiently large impression of fingerprint is not available due to the small sensing area, and this degrades the verification performance of the system. The proposed method overcomes this problem by combining the information of fingerprints for enrollment. To combine the fingerprints, the alignment process is important first of all. In the proposed algorithm, multiple impressions of a finger are coarsely aligned using the corresponding minutiae pairs and then are finely aligned using the Distance Map. We construct an integrated template for enrollment in aligned coordinate system. Since this integrated template represents the enlarged finger region, the problem that is occurred by using small sensor can be overcome. Experimental results show that the use of the integrated template of multiple impressions improves the performance of the fingerprint verification system.

Algorithm for Detection and Elimination of False Minutiae in Fingerprint Images

A common problem in fingerprint recognition is the existence of false minutiae which increase both FAR and FRR in fingerprint matching. In this paper, a robust minutiae postprocessing algorithm is proposed. Unlike most algorithms which use simple distance and connectivity criterions for postprocessing, we also used orientation and flow of ridges as the key factor for postprocessing to avoid eliminating true minutiae while postprocessing. It is shown by the experiments that our postprocessing algorithm improves the minutiae extraction accuracy and the performance of the matching process.

An improved fingerprint indexing algorithm based on the triplet approach

This paper proposes a triplet based fingerprint indexing algorithm which selects the candidates for identification from a large number of enrolled fingerprints. Previous triplet based indexing algorithms have three problems: quantization error, triplet matching error, the proportional increase of similarity score to the number of enrolled triplets. The proposed algorithm solves these problems as follows. First, we generate weighted indices through fuzzy membership functions based on the statistics to reduce quantization error. Second, we apply Geometric Relationships to reduce triplet matching error. Finally, we normalize similarity score to solve the last problem. We compare the proposed algorithm with the previous triplet approach and the Fingercode. Experimental results show that the average rank of the enrolled fingerprint which is identical to an input fingerprint, becomes 2.01 times less than the previous triplet method, and becomes 0.4 times less than the Fingercode.

A real-time image selection algorithm: fingerprint recognition using mobile devices with embedded camera

This paper proposes a real-time image selection algorithm for fingerprint recognition system, which uses the embedded camera of the mobile device. In general, auto-focusing algorithms of the camera system use the gradient measures to estimate high-frequency components of an image. In mobile device, images are greatly affected by environmental light sources. Therefore, obtained image might not qualify for the fingerprint recognition system, even when the image is focused. Consequently, image should be investigated whether it is usable or not. Variance-modified-Laplacian of Gaussian (VMLOG) and image quality index (QI) proposed in this paper solve such problem. VMLOG considers high-frequency component and repeatable patterns of ridges. Experimental results shows that the processing time of the proposed algorithm is enough fast to be adapted in real time system as like mobile device and the proposed algorithm selects exactly a recognizable image.