Due to its widespread uses in the surveillance system, human identification is now being given a lot of attention. Unimodal authentication like speech and facial recognition are used in most individual biometric identification. Unimodal biometric systems have drawbacks, especially when dealing with outliers and incorrect data. Because of its many advantages, including increased safety versus traditional unimodal biometric & remarkable identification accuracy, multifunctional authentication technologies are receiving increasing attention from academics. So, this work in the paper creates a biometric recognition method that employs both facial & fingerprints identification. CNN & ORB algorithms are used to create a multibiometric person identification system. The next step is a matched score level synthesis built on the Balanced Tally, which brings together the disparate aspects. If fusion score is higher than that of the threshold t, the validation procedure is fulfilled. The technique is rigorously tested on many datasets from the UCI ML Repository Database, including one real-world dataset using state-of-the-art methods. The suggested methodology shows great promise in the area of facial detection.
Article Details
Unique Paper ID: 158896
Publication Volume & Issue: Volume 9, Issue 11
Page(s): 903 - 910
Article Preview & Download
Share This Article
Conference Alert
NCSST-2023
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2023
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT