Scholarlink

Image classification is a fundamental task in various computer vision applications such as medical diagnosis, remote sensing, and object recognition. Traditional convolutional neural networks (CNNs) have shown remarkable performance in feature extraction and pattern recognition. However, they often face challenges in capturing local interactions and spatial dependencies efficiently. To address this limitation, we propose a Cellular Automata-based Convolutional Neural Network (CA-CNN) model that integrates the dynamic evolution rules of Cellular Automata (CA) into CNN layers. The CA component enhances spatial feature learning and local dependency modelling while maintaining computational efficiency. Experimental analysis on benchmark image datasets demonstrates that the proposed CA-CNN outperforms conventional CNN models in terms of various performance analysis metrics.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

CA-CNN Deep Learning Model for Image Classification

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • M J Elizabeth,
  • Raju Hazari

摘要

Image classification is a fundamental task in various computer vision applications such as medical diagnosis, remote sensing, and object recognition. Traditional convolutional neural networks (CNNs) have shown remarkable performance in feature extraction and pattern recognition. However, they often face challenges in capturing local interactions and spatial dependencies efficiently. To address this limitation, we propose a Cellular Automata-based Convolutional Neural Network (CA-CNN) model that integrates the dynamic evolution rules of Cellular Automata (CA) into CNN layers. The CA component enhances spatial feature learning and local dependency modelling while maintaining computational efficiency. Experimental analysis on benchmark image datasets demonstrates that the proposed CA-CNN outperforms conventional CNN models in terms of various performance analysis metrics.