Local Learning Framework for Recognition of Lowercase Handwritten Characters

Abstract. This paper proposes a general local learning framework to effectively alleviate the complexities of classifier design by means of “divide and conquer” principle and ensemble method. The learning framework consists of quantization layer and ensemble layer. After GLVQ and MLP are applied to the framework, the proposed method is tested on public handwritten lowercase data sets, which obtains a promising performance consistently. Further, in contrast to LeNet5, an effective neural network structure, our method is especially suitable for a large-scale real-world classification problem although it is easily scaled to a small training set with preserving a good performance.

• Type: Conference
• Year: 2001
• Where: MLDM
• Authors: Jian-xiong Dong, Adam Krzyzak, Ching Y. Suen
• Keywords: Learning Framework, Local Learning Framework, Machine Learning, MLDM 2001, Public Handwritten Lowercase