Research on Image Recognition Based on Convolutional Neural Networks

View at publisher Summarise with VIRAT
Authors: Chunxi Guan, Xing Yu, Lijuan Wan, Xiangyu Song, Zhiming Lei, Lai Liusheng, Junfeng Xuan, Xu Wang
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Traditional methods recognize images by extracting their features. However, extracting image features poses certain difficulties, especially for high-dimensional images and those with complex backgrounds. To address this issue,a recognition method based on Convolutional Neural Networks(CNN) is proposed. Under the improved LeNet5 framework, sample images are directly used as input parameters, and the model is trained through a Convolutional Neural Networks to obtain output results, thus eliminating the need to extract complex features. Experimental verification shows that the above method can accurately recognize images. The method proposed in this paper does not require the extraction of complex features, making it highly valuable in image processing.

Fields of Study & Subjects

Advanced Neural Network Applications Advanced Image and Video Retrieval Techniques Computer Science and Engineering

Publication details

Journal / source
International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
Pages
1–4
Publication date
16 January 2026
Language
EN