.

ISSN 2063-5346
For urgent queries please contact : +918130348310

IMPROVED PRECISION RATE IN OBJECT DETECTION AND CLASSIFICATION USING NOVEL REGION-BASED CONVOLUTIONAL NEURAL NETWORKS OVER SUPPORT VECTOR MACHINE

Main Article Content

G.Parpathy, Rashmita Khilar
» doi: 10.31838/ecb/2023.12.sa1.378

Abstract

Aim: To improve the precision rate in Object Detection and Classification and to identify the objects based on Novel Region-Based Convolutional Neural Networks (RCNN) and Support Vector Machine algorithms. Materials and Methods: Classification is performed by Novel Region-Based Convolutional Neural Networks (N=10) over Support Vector Machine (N=10). The sample size is calculated using GPower with pretest power as 0.8 and alpha 0.05. Result: Mean accuracy of Novel Region-Based Convolutional Neural Networks (96.9%) is high compared to Support Vector Machine (90.00%). The significance value for accuracy and loss is 0.339 (p>0.05). Conclusion: The mean accuracy of the object detection and classification in Novel Region-Based Convolutional Neural Networks (RCNN) is better than the Support Vector Machine algorithm.

Article Details