Handwritten Digit Recognition Scheme Based on Noise Reduction and Trestle Self-Coding. Issue 4 (June 2021)

• Record Type: Journal Article
• Authors: Wang, Jingchen; Yan, Tong
• Is Part Of: Journal of physics. Volume 1952:Issue 4(2021)
• Publication Date: 2021-06
• Subjects: Noise Reduction Auto coding -- Stack Auto coding -- Handwritten Digit Recognition -- Convolution Neural Network; Physics -- Congresses; 530.5
• DOI: 10.1088/1742-6596/1952/4/042002
• Languages: English
• ISSNs: 1742-6588

Abstract

Abstract: In this paper, in order to improve the accuracy of handwritten number recognition, a convolutional neural network based on noise reduction and stack auto coding is formed by combining the denoising auto coding algorithm with stack auto coding algorithm. In this paper, the MNIST dataset is preprocessed first, then the noise reduction and stack auto coding network layer are constructed, and finally the stack auto coding algorithm based on the improved denoising auto coding is used to train and test the dataset. Experimental data show that the proposed method achieves low loss value and effectively improves the recognition accuracy in the MNIST test set.