A discriminative cascade CNN model for offline handwritten digit recognition
Shulan Pan, Yanwei Wang, Changsong Liu, Xiaoqing Ding · 2015
This paper presents a high-performance two-stage cascade CNN model. The main idea behind the cascade CNN model is complementary classification objectives between Stage I and Stage II. Discriminative learning is introduced to train Stage II by feeding back poorly recognized training samples. Experiments have been conducted on the competitive MNIST handwritten digit database. The cascade model achieved the best state-of-the-art performance with an error rate of 0.18%.