Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition

2018-08-17T14:08:07+00:00 January 11th, 2018|AI, NLP, Machine Learning, Content Mgmt and Publishing Tech|Comments Off on Multi-Scale Attention with Dense Encoder for Handwritten Mathematical Expression Recognition

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. This paper discusses the attention based encoder-decoder model that recognizes mathematical expression images from two-dimensional layouts to one-dimensional LaTeX strings. The encoder is improved by employing densely connected convolutional networks as they can strengthen feature extraction and facilitate gradient propagation especially on a small training set.

Click Here to Download Paper

Bitnami