A Comparison Study of Convolutional Neural Network and Recurrent Neural Network on Image Classification
Xiping Qing · 2022
Image classification is a very important task in the field of computer vision, and it is widely used in daily life. In recent years, deep learning has developed rapidly in the field of image classification. Image classification methods based on deep learning can not only deal with complex images that are difficult to be processed by traditional image classification methods, but also with large-scale image data that are difficult to be dealt with by image classification methods based on machine learning algorithms. The motivation of this paper is to do a comparative analysis of the performance of CNN and RNN on image classification. In this paper, we use the CNN model, the RNN model and the CNN and RNN mixed model, which are commonly used in deep learning, to compare their classification performance on the ISVRC dataset. We learn from the comparison experiments that the CNN model has better accuracy and F1-Score than the other two models for the overall classification results and the classification results of individual categories. The results prove that CNN has better feature extraction ability than RNN for image data, and the further investigation is needed. CNN has become the dominant approach in image classification due to its excellent features such as local connectivity, weight sharing, pooling operation and multilayer structure.