Thesis Details
Comparison of the Effect of Fingerprint Image Compression Algorithms on the Quality of Matching Algorithms
This thesis aims to assess the effect of various compression options and image processing techniques for different types of fingerprint images. Also, various fingerprint matching techniques will be tested to measure the similarity between the processed and the original fingerprint image. The work evaluated the performance of JPEG, PNG, and the WSQ compression, as well as the minutiae-based, cross-correlation, and the PSNR matchers. The fingerprint image processing techniques included image normalization, binarization, depth change, noise removal, and resizing. As a result, the PNG compression recorded the best average scores for all fingerprint types according to all tested matchers. Furthermore, the JPEG compression registered the best average compression times, while the WSQ compression produced the smallest compressed file sizes. Moreover, the fingerprint image processing techniques did not improve the matching scores, but only made them worse.
fingerprint, compression algorithms, JPEG, PNG, WSQ, fingerprint matching, compression effect, image quality
Kočí Radek, Ing., Ph.D. (DITS FIT BUT), člen
Křivka Zbyněk, Ing., Ph.D. (DIFS FIT BUT), člen
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT), člen
@bachelorsthesis{FITBT21646, author = "Marek Varga", type = "Bachelor's thesis", title = "Comparison of the Effect of Fingerprint Image Compression Algorithms on the Quality of Matching Algorithms", school = "Brno University of Technology, Faculty of Information Technology", year = 2020, location = "Brno, CZ", language = "english", url = "https://www.fit.vut.cz/study/thesis/21646/" }