Building pattern classifiers using convolutional neural networks
Baoqing Li, Baoxin Li · 2003
Pattern classification is the core task of many applications such as image segmentation. This paper studies the possibility of building pattern classifiers for text/picture segmentation and text detection problems using convolutional neural networks (CNNs). By using CNNs, explicit feature extraction is avoided-the feature detectors are learned from the training data. More importantly, CNNs can directly operate on grey level images, making its application straightforward. Addressed are practical issues such as kernel size, convergence speed, etc. Experiments on Chinese text/picture segmentation and text detection are presented.