Performance Comparison of Face Detection and Recognition Algorithms
Journal: International Journal of Science and Research (IJSR) (Vol.8, No. 1)Publication Date: 2019-01-05
Authors : Mohsin Furkh Dar; Sarvottam Dixit;
Page : 986-994
Keywords : SSH; Dlib-R;
Abstract
Recognition of faces is a fundamental cognitive ability that forms an important basis for our social interactions. This paper aims to optimize the existing face recognition system by comparing the results of different algorithms. To achieve this goal, I have analyzed state-of-the-algorithms in both face detection and face recognition. The research for algorithms goes through the analysis of recent benchmarks, two of which (i. e. WIDER FACE [1] and MegaFace [2]) are also used for evaluating those algorithms. The results on these benchmarks allows to determine which algorithms perform better, that is to say SSH [3] for detection and both Dlib-R [4] and ArcFace [5] for recognition. All the tests are performed with algorithm efficiency in mind. And computation time measurements show that the best techniques tend to work slower but that they can achieve practical execution times.
Other Latest Articles
- The Effect of Interest Rate and Financial Leverage on Profitability and Firm Value in Manufacturing Companies in Indonesia Stock Exchange
- Intellectual Capital Analysis and Hedging Decisions on Dividend Policies and Firm Value in Manufacturing Companies on the Indonesia Stock Exchange
- Rural Education in India: Issues and Solution
- Orthognathic Surgery as Treatment Choice for TMJ Disorder: A Case Report
- Preventive and Rehabilitative Treatments in Midline Facial Cleft and Atrial Septal Defect: Case Report
Last modified: 2021-06-28 17:20:55