TextCaps : Handwritten Character Recognition with Very Small Datasets

17 Apr 2019Vinoj JayasundaraSandaru JayasekaraHirunima JayasekaraJathushan RajasegaranSuranga SeneviratneRanga Rodrigo

Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of labeled data for such languages and inability of deep learning techniques to properly learn from small number of training samples... (read more)

PDF Abstract

Evaluation results from the paper

 SOTA for Image Classification on MNIST (Accuracy metric )

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Compare
Image Classification EMNIST-Letters TextCaps Accuracy 95.39 # 1
Image Classification Fashion-MNIST TextCaps Accuracy 94.35 # 1
Image Classification MNIST TextCaps Accuracy 99.71 # 1