Volume 20 No 22 (2022)
 Download PDF
KNN approach through various image equalization techniques on CIFAR10
Madhan Mohan Subramanian, Dr.Karthikeyan Elangovan
The success of a machine learning system for picture recognition and classification relies on the accuracy and efficiency of feature extraction. Due to the evolution in the digital domain limitless multimedia is generated daily. This calls for the development of a reliable and visually appealing image revival system. In this research, we propose a shape and texture-based image retrieval system, which compares each query image to the photos in the repository using shape and textural facets and then finds images that fall under a predetermined similarity threshold. The proposed method makes use of a statistical strategy for retrieving images.Object identification is a crucial component of many real-world applications, making it one of computer vision's most important subfields. Yet, the detection of small objects has long been an important and challenging issue in the study of object detection.This paper explores the JPEGCF with KNN has the greatest accuracy result of 95.80%. The RGB with KNN produces the lowest accuracy result of 89.07%. The accuracy of the GF with KNN has 94.15%, FOHF with KNN is 93.90% and PHOG with KNN is 95.05%, respectively. Based on the findings the JPEG coefficient with KNN models performs well compare than other models.
Copyright © Neuroquantology

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Articles published in the Neuroquantology are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant IJECSE right of first publication under CC BY-NC-ND 4.0. Users have the right to read, download, copy, distribute, print, search, or link to the full texts of articles in this journal, and to use them for any other lawful purpose.