Fingerprint verification is one of the most reliable personal identification methods. However, manual fingerprint verification is so tedious, time-consuming, and expensive that it is incapable of meeting today‟s increasing performance requirements. An automatic fingerprint verification system (AFIS) is widely needed. In this study an attempt has been made apply image processing for fingerprint based student verification. According to the national Educational Assessment and Examination Agency (NEAEA) of Ethiopia controlling examines entering into exam room has been done manually. So, the current study focuses on verifying an unauthorized candidate attempting to work on national examination on behalf of another student using forged registration card and female Muslim candidates wearing hijabs and covering their faces. The study passes through different steps. First, the digital fingerprint images are acquired from Yekatit 12 Preparatory school students using inked fingerprint taken on white paper, which is then scanned using Epson model 220 scanner. During preprocessing, image restoration is performed to filter noise from the image histogram equalization, FFT followed by applying Gabor filter. Then binarazation and segmentation to identify region of interest (ROI). Segmentation is done by using block direction estimation and morphological operation. Thinning after segmentation to select important region and increase the reading ridge from fingerprint image. So, as to increase the performance of fingerprint verification, the hybrid of minutiae and BRISK (local feature extractor) had been considered for this study. In this study, the experiments are conducted in three parameters i.e. conducting experiment using minutiae features, BRISK features separately and conducting using the hybrid feature groups. The experimentation results shows that 55% is registered for minutiae feature techniques; 82% is registered for BRISK features and 90 % is achieved for the hybrid of BRISK and Minutiae features. For minutiae the performance of the system is reduced mainly because of intra-class variation, such as displacement, rotation, partial overlap, non-linear distortion, pressure and skin condition, noise, feature extraction errors. Hence, there is a need to conduct future research in the various image processing techniques, for skew detection, noise filtering and image enhancement.