Handwritten digits recognition base on improved LeNet5

• Published in: The 27th Chinese Control and Decision Conference (2015 CCDC) pp. 4871 - 4875
• Main Authors: Naigong Yu, Panna Jiao, Yuling Zheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2015
• Subjects: convolutional neural networks; Handwriting recognition; Handwritten digit recognition; Stochastic diagonal Levenberg-Marquardt; Support vectors machines
• DOI: 10.1109/CCDC.2015.7162796
• ISSN: 1948-9439

LeNet5 is a kind of Convolutional Neural Network (CNN) and has been used in handwritten digits recognition. In order to improve the recognition rate of LeNet5 in handwritten digits recognition, this article presents an improved LeNet5 by replacing the last two layers of the LeNet5 structure with Support Vector Machines (SVM) classifier. And LeNet5 performs as a trainable feature extractor and SVM works as a recognizer. To accelerate the network's convergence speed, the stochastic diagonal Levenberg-Marquardt algorithm is introduced to train the network. A series of studies has been conducted on the MINST digit database to test and evaluate the proposed method performance. The results show that this method can outperform both SVMs and LeNet5. Moreover, the improved method gets a faster convergence speed in training process.