SangCTC-Improving Traditional CTC Loss Function for Optical Music Recognition (August 2019)

Shah, Jimit K.; Padte, Anuya S.; Ahirao, Purnima

doi:10.1109/punecon46936.2019.9105720

Cited by 2 publications

(1 citation statement)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is accomplished by adding up the likelihood of potential input-to-target alignments, which results in a loss value that may be differentiated with regard to each input node. Assuming a "many-to-one" alignment between the input and the target, the target sequence's length is constrained to be less than the input length [40].…”

Section: Recallmentioning

confidence: 99%

Handwritten Word Recognition using Deep Learning Approach: A Novel Way of Generating Handwritten Words

Akter

Shahriar

Cuzzocrea

et al. 2022

2022 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

A handwritten word recognition system comes with issues such as-lack of large and diverse datasets. It is necessary to resolve such issues since millions of official documents can be digitized by training deep learning models using a large and diverse dataset. Due to the lack of data availability, the trained model does not give the expected result. Thus, it has a high chance of showing poor results. This paper proposes a novel way of generating diverse handwritten word images using handwritten characters. The idea of our project is to train the BiLSTM-CTC architecture with generated synthetic handwritten words. The whole approach shows the process of generating two types of large and diverse handwritten word datasets: overlapped and non-overlapped. Since handwritten words also have issues like overlapping between two characters, we have tried to put it into our experimental part. We have also demonstrated the process of recognizing handwritten documents using the deep learning model. For the experiments, we have targeted the Bangla language, which lacks the handwritten word dataset, and can be followed for any language. Our approach is less complex and less costly than traditional GAN models. Finally, we have evaluated our model using Word Error Rate (WER), accuracy, f1-score, precision, and recall metrics. The model gives 39% WER score, 92% percent accuracy, and 92% percent f1 scores using nonoverlapped data and 63% percent WER score, 83% percent accuracy, and 85% percent f1 scores using overlapped data.

show abstract

Section: Recallmentioning

confidence: 99%