Accurate recognition of words in scenes without character segmentation using recurrent neural network

详细信息    查看全文

• 作者：Bolan Su ^{subl@i2r.a-star.edu.sg}Author Vitae ; Shijian Lu ; ^{slu@i2r.a-star.edu.sg}Author Vitae
• 关键词：Scene text recognition ; Recurrent neural network
• 刊名：Pattern Recognition
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：63
• 期：Complete
• 页码：397-405
• 全文大小：802 K
• 卷排序：63

文摘

We designed a novel method that converts a word image into a sequential signal. We designed an ensembling RNN for word-level scene text recognition which obtained superior recognition accuracy. Our method uses publicly available datasets in training which provides a baseline for benchmarking of the future works. Our method uses word instead character level annotations, which reduces the efforts in ground truth generation greatly.