BENDLET TRANSFORM BASED OBJECT DETECTION SYSTEM USING PROXIMITY LEARNING APPROACH

Ramalingam, Mritha and C. H, Nishanthi (2022) BENDLET TRANSFORM BASED OBJECT DETECTION SYSTEM USING PROXIMITY LEARNING APPROACH. INTERNATIONAL JOURNAL OF ADVANCES IN SIGNAL AND IMAGE SCIENCES, 8 (2). pp. 1-8.

[thumbnail of IJASIS_8(2)_1.edited.pdf] Text
IJASIS_8(2)_1.edited.pdf - Published Version

Download (756kB)

Abstract

This study presents a Bendlet Transform-based Object Detection (BTOD) system that recognizes an object in the image. Finding a specific object in images or videos is the goal of the field of object recognition. Though humans are able to identify a large number of objects, it is very difficult for computer vision systems in general. The appearance of the objects may change depending on the perspective, the size or scale, or translation and rotation. This work extracts Bendlet transform-based features from the images at different levels, and then the discriminant features are selected by employing genetic algorithms. The performance of the BTOD system is analyzed with different nearest neighbours for classifying objects in the Columbia Object Image Library (COIL-100) in terms of classification accuracy. It is observed from the results that the BTOD system with a one-nearest neighbour provides better performance than the two-nearest neighbour classifier. The former classifier gives 99.47% accuracy, whereas the later classifier gives 99.19%.

Item Type: Article
Subjects: Open Article Repository > Medical Science
Depositing User: Unnamed user with email support@openarticledepository.com
Date Deposited: 09 Jan 2023 12:30
Last Modified: 23 Apr 2024 12:07
URI: http://journal.251news.co.in/id/eprint/185

Actions (login required)

View Item
View Item