Keywords : Gabor filter


Wrist and Palm Vein pattern recognition using Gabor filter

Mohammed Hamzah Abed

Journal of Al-Qadisiyah for Computer Science and Mathematics, 2017, Volume 9, Issue 1, Pages 49-60

Wrist and palm vein pattern can be considering as a promising biometric technique for identification, through the study of the pattern of blood vessels that visible from the skin. This kind of recognition is very important for many reasons; vein exists inside of the human body makes it difficult to change pattern like shift the position of vein from part to another, unlike another method of techniques of recognition. In this paper work wrist and palm vein are studied for identification and verification, this work divided into three phases preprocessing, features extraction and recognition. in preprocessing phase apply resize and image “enhancement” using “CLAHE and 2-D Gaussian high pass filter”, the features of each image are extracted by using Gabor filters. LDA and PCA are used to minimize the dimension of the features set. For vein image, identification used Euclidean distance to measure the similarity. The average CRR of vein palm in proposed work is 94.49% and the average CRR of vein wrist is 92.33.

Fingerprint Image Enhancement – A Survey

Salman Abd kadum

Journal of Al-Qadisiyah for Computer Science and Mathematics, 2015, Volume 7, Issue 2, Pages 166-180

Fingerprint image enhancement is one of the most important operation in (Automated fingerprint Identification system, AFIS), and affect directly on the accuracy of the results in all other steps in fingerprint system (like feature extracting, noise removal, alignment, and matching), so the selection of suitable and efficient method is very important to avoid faulty results and to make fingerprint systems more reliable. Fingerprint images are rarely of perfect quality; they may be degraded and corrupted due to variations in skin and impression conditions. The available enhancement algorithms are based on either the local orientation field filtering scheme in space domain or the Gabor filtering scheme in the frequency domain. The local orientation could not be correctly estimated for fingerprint images of poor quality, which greatly restricts the applicability of these filtering techniques. The Gabor filters could obtain the reliable orientation estimate even for corrupted images, but it is time consuming. It is unsuitable for an on-line fingerprint recognition system such as AFIS.