The use of biometrics provides a more reliable security layer in identification and user authentication in many fields of commercial and institutional transactions. Vascular vein patterns from the hand have recently been explored as another approach to the biometric modality because these innate patterns are constant, remains distinct lifelong; relatively stable, cannot be forged, tampered nor copied. This study proposes the use of a rotation invariant algorithm like ORB for a bimodal approach in the vein recognition from the palm and dorsal vein patterns of the hand. Using near-infrared LEDs, Raspberry Pi with NOIR camera module, a portable, real time hand vein pattern recognition device was developed. Image pre-processing, feature extraction, feature matching, database of user information and GUI are implemented in Raspberry Pi, Python and Open CV Libraries. ORB was used for generating feature descriptors and Brute Force Matcher for feature matching. Match scores generated by the classifier from dorsal and palm vein were combined using sum-rule in score level fusion to generate the final recognition results. After experimental tests conducted, system performance resulted to 95.00% accuracy level and overall response time of 2.76secs. The developed architecture can be integrated with other systems like attendance monitoring, access control, identity authentication for financial transactions, forensic investigation, and fraud detection.

In the field of biometrics, vascular or vein pattern matching is a technology that analyses the patterns of blood vessels that can be visible on the surface of the hand through near infrared illumination. This paper presents a comparative analysis of Oriented FAST and Rotated BRIEF (ORB) and Scale Invariant Feature Transform (SIFT) as feature descriptor algorithm for dorsal hand vein recognition. The hardware implementation is a portable and inexpensive image scanning device using Raspberry Pi, 850nm near infrared lights, IR sensitive CCD camera; and OpenCV Libraries as programming platform. Both algorithms are local invariant making it more suitable for dorsal vein patterns because they are resistant to noise and rotation. Images are pre-processed using CLAHE, low pass filter, and morphological operators. Two algorithms are used independently to extract feature points, and finally, Brute Force Matcher and FLANN are used as image classifiers that implements distance calculation between feature points in the image. Independent testing is performed to assess the performance of the two algorithms. Experimental results shows that ORB delivers better performance than SIFT with overall Accuracy rate of 97.22%, Recall of 94.15%, lowest FAR of 0.0662, and FRR of 0.0541. It also generates the lowest recognition time of 2.33seconds when ORB is used with Brute Force Matcher classifier.

Demonstrable skills and qualities referred to as graduate attributes become the central goal of all academic programs to ensure that they produced graduates well prepared and equipped to meet demands of industry and society. Though most assessment methods are effective, self-assessment may help students reflect on their own learning and capabilities. This mixed method study explored the use of structured self-assessment inventory tool to gauge the attainment level of graduate attributes of senior Computer Engineering students. Qualitative analysis of data from interview and prove-it statements were collected and analyzed. Results of the study showed that students perceived to have Basic to Adequate competency level to the core and generic attributes. Further, they emphasized the need for developing their problem-solving skills, design and development skills, communication and team skills to become competitive workforce after graduation.

The integration of technology in pedagogical modality of delivering instructions and facilitation of learning generated various benefits both to faculty and students. This paper aims to conduct a more data driven inquiry that could describe students’ pattern of utilization by analyzing LMS activity logs in various courses dispense thru Moodle and check for correlation of LMS activity level and students’ academic performance with respect to final grade. Though a positive relationship between LMS logs and final grade was established, however contrasting behaviour was exhibited by participants taking different course module online. The study has also considered the demographic profile of students and check if it affects their patterns of LMS utilization.  Relevant data from this paper hopes to provide basis for course improvement and e-learning implementation of the university.