Overview

Original Research

PARTICLE HYBRIDIZED SEALION OPTIMIZATION ALGORITHM (PHSLA) - A NOVEL OBJECT DETECTION METHOD

SURAJ PARDESHI 1, PRAVIN YANNAWAR 2, RAMESH MANZA 3, BHARTI GAWALI 4, and FILBERT HILMAN JUWONO 5.

Vol 17, No 08 ( 2022 )   |  DOI: 10.5281/zenodo.7005884   |   Author Affiliation: Vision and Intelligent System Laboratory, Department of Computer Science and Information Technology, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad (MS), India 1,2; Department of Computer Science and Information Technology, Dr. Babasaheb Ambedkar Marathwada University, Aurangabad (MS), India 3,4; Department of Electrical and Computer Engineering, Curtin University, Sarawak, Malaysia 5.   |   Licensing: CC 4.0   |   Pg no: 1154-1175   |   To cite: SURAJ PARDESHI, et al., (2022). PARTICLE HYBRIDIZED SEALION OPTIMIZATION ALGORITHM (PHSLA) - A NOVEL OBJECT DETECTION METHOD. 17(08), 1154–1175. https://doi.org/10.5281/zenodo.7005884   |   Published on: 17-08-2022

Abstract

Assistive innovation empowers individuals to accomplish autonomy while performing household tasks, and it improves their overall quality of life as well. The purpose of this research is to propose model for object detection in an indoor environment for visually challenged persons. Initially, the input image from real-world scenario is subjected to pre-processing via wiener filtering. Subsequently, segmentation is carried out by the novel proposed Multi-Kernel K-means clustering model and SURF, SIFT, Shape based features via canny edges & Gradient features via HOG were extracted from segmented source. The optimal features are selected from extracted features by a new hybrid algorithm referred as Particle Hybridized SeaLion Optimization Algorithm (PHSLA) and selected optimal features are classified using Optimized Convolutional Neural Network (OCNN) for detecting the object. Final Comparative study is carried out between the proposed hybrid model and existing work. It was observed that CNN and PHSLA revived 98% accuracy in classification of real time objects.

Keywords

Object Detection; Visually Challenged (VC); Multi-Kernal K-means; SIFT; SURF; PHSLA; OCNN.