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

01/05/2018
by   Jianshu Zhang, et al.
0

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 2016, by only using the official training dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/04/2017

A GRU-based Encoder-Decoder Approach with Attention for Online Handwritten Mathematical Expression Recognition

In this study, we present a novel end-to-end approach based on the encod...
research
07/20/2020

Improving Attention-Based Handwritten Mathematical Expression Recognition with Scale Augmentation and Drop Attention

Handwritten mathematical expression recognition (HMER) is an important r...
research
12/07/2021

Handwritten Mathematical Expression Recognition via Attention Aggregation based Bi-directional Mutual Learning

Handwritten mathematical expression recognition aims to automatically ge...
research
06/28/2023

DenseBAM-GI: Attention Augmented DeneseNet with momentum aided GRU for HMER

The task of recognising Handwritten Mathematical Expressions (HMER) is c...
research
01/21/2019

Pattern Generation Strategies for Improving Recognition of Handwritten Mathematical Expressions

Recognition of Handwritten Mathematical Expressions (HMEs) is a challeng...
research
06/20/2013

Determining Points on Handwritten Mathematical Symbols

In a variety of applications, such as handwritten mathematics and diagra...
research
09/16/2016

Image-to-Markup Generation with Coarse-to-Fine Attention

We present a neural encoder-decoder model to convert images into present...

Please sign up or login with your details

Forgot password? Click here to reset