Classification of handwritten Chinese numbers with convolutional neural networks

Ameri, R; Alameer, A; Ferdowski, S; Abolghasemi, V; Nazarpour, K

Abstract

Deep learning methods have become the key ingredient in the field of computer vision; in particular, convolutional neural networks (CNNs). Appropriating the network architecture and data pre-processing have significant impact on performance. This paper focuses on the classification of handwritten Chinese numbers. Firstly, we applied various methods of pre-processing to our collected image dataset. Secondly, we customised a CNN-based architecture with minimal number of layers and parameters specifically for the task. Experimental results showed that our proposed methods provides superior classification rate of 99.1%. Our results also show that the proposed method has competitive performance compared to smaller neural networks with fewer parameters, e.g. Squeezenet and deeper networks with a larger size and number of parameters, e.g., pre-trained GoogLeNet and MobileNetV2.

Citation

Ameri, R., Alameer, A., Ferdowski, S., Abolghasemi, V., & Nazarpour, K. Classification of handwritten Chinese numbers with convolutional neural networks. Presented at 5th International Conference on Pattern Recognition and Image Analysis (IPRIA)

• Presentation Conference Type: Other
• Conference Name: 5th International Conference on Pattern Recognition and Image Analysis (IPRIA)
• Online Publication Date: Jul 26, 2021
• Publication Date: Jul 26, 2021
• Deposit Date: May 26, 2022
• ISBN: 9781665426596
• DOI: https://doi.org/10.1109/ipria53572.2021.9483557
• Publisher URL: http://dx.doi.org/10.1109/ipria53572.2021.9483557
• Additional Information: Event Type : Conference