Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition
2018 24th International Conference on Pattern Recognition (ICPR)(2018)
摘要
Handwritten mathematical expression recognition is a challenging problem due to the complicated two-dimensional structures, ambiguous handwriting input and variant scales of handwritten math symbols. To settle this problem, we utilize the attention based encoder-decoder model that recognizes mathematical expression images from two-dimensional layouts to one-dimensional LaTeX strings. We improve the encoder by employing densely connected convolutional networks as they can strengthen feature extraction and facilitate gradient propagation especially on a small training set. We also present a novel multi-scale attention model which is employed to deal with the recognition of math symbols in different scales and save the fine-grained details that will be dropped by pooling operations. Validated on the CROHME competition task, the proposed method significantly outperforms the state-of-the-art methods with an expression recognition accuracy of 52.8% on CROHME 2014 and 50.1% on CROHME 2016, by only using the official training dataset.
更多查看译文
关键词
expression recognition accuracy,dense encoder,handwritten mathematical expression recognition,two-dimensional structures,ambiguous handwriting input,handwritten math symbols,encoder-decoder model,mathematical expression images,two-dimensional layouts,one-dimensional LaTeX strings,multiscale attention model,CROHME competition task,feature extraction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络