Vol. 08, No. 06 [June 2022]

One of the most reliable personal identification methods is fingerprint verification and it plays an important role in commercial and forensic applications. Designing a recognition system that will increase the accuracy is required. Yet the accuracy of fingerprint recognition systems remains a challenge This article proposes a fingerprint recognition system using canny filter and morphological operator through path analysis test case. The steps involved in the proposed recognition system include; image acquisition, pre-processing, features extraction and matching. Fast fourier transform is used to enhance the quality of the images and the features extracted efficiently to determine the minutia points in fingerprints with morphological operation, and the distribution of grey level co-occurrence matrix (GLCM) with canny filter. The proposed morphological operation can determine the bifurcation, termination of the ridges and valleys, and their corresponding angles, and Euclidean distance is recommended to be used for matching. On the other hand, features such as energy, homogeneity, entropy and correlation are extracted after canny filter is applied and Euclidean distance is again used for matching. The accuracy results from this proposed methods through path analysis cases after comparing for their success rate, false accepted rate and false rejected rate should be about 99% which is higher than any previous techniques.
Key Words: Fingerprint recognition, canny filter, morphological operator, algorithm

Artificial intelligence (AI) has a large and increasing role for personalized training systems. This paper brings both the issues with the standard assessment paradigm and the challenges associated with AI and assessment into a deeper conversation that will ultimately improve assessment practices more generally. It highlights the need for development of actionable and personalized explanations, further incorporation of human-centric design in development of learning tools, rigorous evaluation of the impact of incorporating AI into training and ultimately advancing towards development of trustworthy training systems. The suggested platform architecture consists of an open-source Python API for specifying the workflow of an experiment (the “API”), and a Platform-as-a-Service (PaaS), which is a running instance of back-end infrastructure coupled with computational resources and a large training dataset. This study also aims to synthesize an agenda for future research on AI-driven assessmenttechniques.