Offline Handwritten Mathematical Recognition using Adversarial Learning and Transformers
Offline Handwritten Mathematical Expression Recognition (HMER) is a major area in the field of mathematical expression recognition. Offline HMER is often viewed as a much harder problem as compared to online HMER due to a lack of temporal information and variability in writing style. In this paper, we purpose a encoder-decoder model that uses paired adversarial learning. Semantic-invariant features are extracted from handwritten mathematical expression images and their printed mathematical expression counterpart in the encoder. Learning of semantic-invariant features combined with the DenseNet encoder and transformer decoder, helped us to improve the expression rate from previous studies. Evaluated on the CROHME dataset, we have been able to improve latest CROHME 2019 test set results by 4% approx.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Encoder-Decoder Learning Framework towards Offline Handwritten Mathematical Expression Recognition Based on Multi-Scale Deep Neural Network
Offline handwritten mathematical expression recognition is a challenging task, because handwritten mathematical expressions mainly have two problems in the process of recognition. On one hand, it is how to correctly reco…
DecoderStroke extraction for offline handwritten mathematical expression recognition
Offline handwritten mathematical expression recognition is often considered much harder than its online counterpart due to the absence of temporal information. In order to take advantage of the more mature methods for on…
Optical Character RecognitionOptical Character Recognition (OCR)Offline handwritten mathematical symbol recognition utilising deep learning
This paper describes an approach for offline recognition of handwritten mathematical symbols. The process of symbol recognition in this paper includes symbol segmentation and accurate classification for over 300 classes.…
ClusteringDeep LearningSegmentationMathWriting: A Dataset For Handwritten Mathematical Expression Recognition
Recognition of handwritten mathematical expressions allows to transfer scientific notes into their digital form. It facilitates the sharing, searching, and preservation of scientific information. We introduce MathWriting…
FormOptical Character Recognition (OCR)Unsupervised Training Data Generation of Handwritten Formulas using Generative Adversarial Networks with Self-Attention
The recognition of handwritten mathematical expressions in images and video frames is a difficult and unsolved problem yet. Deep convectional neural networks are basically a promising approach, but typically require a la…
Generative Adversarial Network