An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory

Abstract Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CR...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pengfei Meng, Shuangcheng Jia, Qian Li
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/da4d000f1ad24142a21e258db08b060d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:da4d000f1ad24142a21e258db08b060d
record_format	dspace
spelling	oai:doaj.org-article:da4d000f1ad24142a21e258db08b060d2021-11-28T12:15:35ZAn innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory10.1038/s41598-021-01520-y2045-2322https://doaj.org/article/da4d000f1ad24142a21e258db08b060d2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01520-yhttps://doaj.org/toc/2045-2322Abstract Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CRNN. The CRNN is less effective in recognizing long dense small characters. Aiming at the shortcomings of CRNN, we proposed an improved CRNN network, named CRNN-RES, based on BiLSTM and multiple receptive fields. Specifically, on the one hand, the CRNN-RES uses a dual pooling core to enhance the CNN network’s ability to extract features. On the other hand, by improving the last RNN layer, the BiLSTM is changed to a shared parameter BiLSTM network using recursive residuals, which reduces the number of network parameters and improves the accuracy. In addition, we designed a structure that can flexibly configure the length of the input data sequence in the RNN layer, called the CRFC layer. Comparing the CRNN-RES network proposed in this paper with the original CRNN network, the extensive experiments show that when recognizing English characters and numbers, the parameters of CRNN-RES is 8197549, which decreased 133,752 parameters compare with CRNN. In the public dataset ICDAR 2003 (IC03), ICDAR 2013 (IC13), IIIT 5k-word (IIIT5k), and Street View Text (SVT), the CRNN-RES obtain the accuracy of 96.90%, 89.85%, 83.63%, and 82.96%, which higher than CRNN by 1.40%, 3.15%, 5.43%, and 2.16% respectively.Pengfei MengShuangcheng JiaQian LiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Pengfei Meng Shuangcheng Jia Qian Li An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
description	Abstract Sequence recognition of natural scene images has always been an important research topic in the field of computer vision. CRNN has been proven to be a popular end-to-end character sequence recognition network. However, the problem of wide characters is not considered under the setting of CRNN. The CRNN is less effective in recognizing long dense small characters. Aiming at the shortcomings of CRNN, we proposed an improved CRNN network, named CRNN-RES, based on BiLSTM and multiple receptive fields. Specifically, on the one hand, the CRNN-RES uses a dual pooling core to enhance the CNN network’s ability to extract features. On the other hand, by improving the last RNN layer, the BiLSTM is changed to a shared parameter BiLSTM network using recursive residuals, which reduces the number of network parameters and improves the accuracy. In addition, we designed a structure that can flexibly configure the length of the input data sequence in the RNN layer, called the CRFC layer. Comparing the CRNN-RES network proposed in this paper with the original CRNN network, the extensive experiments show that when recognizing English characters and numbers, the parameters of CRNN-RES is 8197549, which decreased 133,752 parameters compare with CRNN. In the public dataset ICDAR 2003 (IC03), ICDAR 2013 (IC13), IIIT 5k-word (IIIT5k), and Street View Text (SVT), the CRNN-RES obtain the accuracy of 96.90%, 89.85%, 83.63%, and 82.96%, which higher than CRNN by 1.40%, 3.15%, 5.43%, and 2.16% respectively.
format	article
author	Pengfei Meng Shuangcheng Jia Qian Li
author_facet	Pengfei Meng Shuangcheng Jia Qian Li
author_sort	Pengfei Meng
title	An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
title_short	An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
title_full	An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
title_fullStr	An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
title_full_unstemmed	An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory
title_sort	innovative network based on double receptive field and recursive bi-directional long short-term memory
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/da4d000f1ad24142a21e258db08b060d
work_keys_str_mv	AT pengfeimeng aninnovativenetworkbasedondoublereceptivefieldandrecursivebidirectionallongshorttermmemory AT shuangchengjia aninnovativenetworkbasedondoublereceptivefieldandrecursivebidirectionallongshorttermmemory AT qianli aninnovativenetworkbasedondoublereceptivefieldandrecursivebidirectionallongshorttermmemory AT pengfeimeng innovativenetworkbasedondoublereceptivefieldandrecursivebidirectionallongshorttermmemory AT shuangchengjia innovativenetworkbasedondoublereceptivefieldandrecursivebidirectionallongshorttermmemory AT qianli innovativenetworkbasedondoublereceptivefieldandrecursivebidirectionallongshorttermmemory
_version_	1718408106459791360

An innovative network based on double receptive field and Recursive Bi-directional Long Short-Term Memory

Ejemplares similares