This paper evaluates a set of enhancement stages for finger vein enhancement that not only has low computational complexity but also high distinguishing power. This proposed set of enhancement stages is centered around fuzzy histogram equalization. Two sets of evaluation are carried out: one with the proposed approach and one with another unique approach that was formulated by rearranging and cropping down the preprocessing steps of the original proposed approach. To extract features, a combination of Hierarchical Centroid and Histogram of Gradients was used. Both enhancement stages were evaluated with K Nearest Neighbor and Deep Neural Networks using 6 fold stratified cross validation. Results showed improvement as compared to three latest benchmarks in this field that used 6-fold validation.

The robotic challeng of developing and implementing a  shortest-path finding algorithm to reach a destination without bumping into  obstacles has been tackled in this  paper. The proposed algorithm is utilized a single ceiling fixed camera and based on the mask and robot size with different sizes for dilation mask. The implementation has been successfully produced thirty-three computer vision figures and two comparison tables of simulation results by using morphological structuring element with different sizes. This paper’s proposal of optimal path finding algorithm is effeciently save robot energy in reaching targets.

Currently, Biometrics has been utilized the top five modality of face, voice, IRIs, fingerprint, and palm to identify individuals. Comparatively, these Biometrics systems need complex computation to be slow and an easy target to hack. Alternatively, this work proposes a novel biometrics system of highly secured recognition with low computation time using specifically designed biometrics sensor. Consequently, finger vein recognition has been developed. Although, this recognition requires high point of safety measures comes with its individual experiments. The most prominent one being the vein pattern is very difficult to extract because finger vein images are constantly low in quality, seriously hampering the feature extraction and classification stages. Sophisticated algorithms need to be designed with the conventional hardware for capturing finger-vein images is modified by using red Surface Mounted Diode (SMD) leds. For capturing images, Canon 750D camera is used with micro lens. The integrated micro lens gives better quality images, and with some adjustments it can also capture finger print. Results have been comparatively improvement for SDUMLA-HMT database and extensively evaluated with k-nearest neighbors (KNN) algorithm. The (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm that can be used to solve both classification and regression problems. KNN calculations are highly accurate in test data. Using stratified 6-fold analysis on all fingers of all hands in collected database, a maximum accuracy of 100% was achieved with an EER of 0% when select right hand and middle finger, based on the analysis of the 106 persons present in the data set. Many approaches have been used to optimize vein image quality. The proposed system has optimum results as compared to existing related works. The work novelty is due to the hardware design of the sensor within the finger-vein recognition system to obtain, simultaneously, finger vein and finger print at low cost, unlimited users for one device and open source.