Title: Development of deep intelligent system in complex domain for human recognition

Authors: Swati Srivastava; Bipin K. Tripathi

Addresses: Department of Computer Science and Engineering, Harcourt Butler Technical University, Kanpur 208002, India ' Department of Computer Science and Engineering, Harcourt Butler Technical University, Kanpur 208002, India

Abstract: This paper aims to develop a deep intelligent system that can perform human recognition through proficient and compressed deep learning. The proposed complex deep intelligent system (CDIS) incorporates multiple segments that includes image representation in lower dimensional feature space, fused fuzzy distribution (FFD) and complex hybrid neural classifier (CHNC). One of the advantages of our CHNC is reduction in computational complexity because very few considered complex higher order neurons are sufficient to recognise a human identity. Further, the proposed intelligent system uses the advantages of both supervised and unsupervised learning to enhance the recognition rates. CDIS outperforms the best results accounted in the literature on three benchmark biometric datasets-CASIA iris, Yale face and Indian face datasets with 99.8%, 100% and 98.0% recognition accuracies respectively.

Keywords: fused fuzzy distribution; FFD; complex hybrid neural classifier; CHNC; biometric; deep architecture.

DOI: 10.1504/IJAIP.2024.139949

International Journal of Advanced Intelligence Paradigms, 2024 Vol.28 No.1/2, pp.53 - 73

Received: 20 Apr 2018
Accepted: 29 Jun 2018
Published online: 15 Jul 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article