DeepHCCR

Offline Handwritten Chinese Character Recognition based on GoogLeNet and AlexNet

Instruction

Training Data : CASIA-HWDB1.0-1.2 and FlexiFont DataSets (Class = 7354)
Testing Data : Chinese Handwriting Recognition Competition in ICDAR2013 (Class = 3755)
AlexNet input size is 108 × 108; GoogLeNet input size is 112 × 112
HCCR-AlexNet Caffemodel can be download from here

Network	Top-1	Top-2	Top-5	Top-10
AlexNet	0.938437	0.975073	0.990790	0.995370
GoogLeNet	0.953227	0.982650	0.993464	0.996728

Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networksx[C]//Advances in neural information processing systems. 2012: 1097-1105.
Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015: 1-9.
Zhong Z, Jin L, Xie Z. High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps[C]//Document Analysis and Recognition (ICDAR), 2015 13th International Conference on. IEEE, 2015: 846-850.
Yin F, Wang Q F, Zhang X Y, et al. ICDAR 2013 Chinese handwriting recognition competition[C]//2013 12th International Conference on Document Analysis and Recognition. IEEE, 2013: 1464-1470.