Patent
Text recognition method and device
Yang Song,Wan Shaohua,Chen Zhijun +2 more
- 15 Feb 2017
21
TL;DR: In this paper, the authors proposed a text recognition method that combines CNN and RNN to achieve integral recognition of the text image to be recognized, so that the method avoids the problem that texts need to be separated character by character and then recognized character-by-character in the prior art which leads to accumulated errors, and the text recognition rate can be improved.
read more
Abstract: The invention provides a text recognition method and device. The method comprises: determining convolutional neural network (CNN) features of a text image and obtaining an eigenvector sequence of a preset dimension; and using a recurrent neural network (RNN) to decode the eigenvector sequence of the preset dimension, and obtaining texts in the text image to be recognized. According to the technical scheme provided by embodiments of the invention, the method combines the CNN and RNN to achieve integral recognition of the text image to be recognized, so that the method avoids the problem that texts need to be separated character by character and then recognized character by character in the prior art which leads to accumulated errors, and the text recognition rate can be improved.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
License plate recognition method based on depth learning, recognition device, equipment and storage medium
Wang Jianzong,Ma Jin,Huang Zhangcheng,Wu Tianbo,Xiao Jing +4 more
- 09 Feb 2018
TL;DR: In this article, a license plate recognition method based on depth learning, a recognition device, equipment and a storage medium is described. But the method is not suitable for the automatic recognition of vehicles.
15
Patent
Character recognition method and device and terminal
Yang Song
- 29 Dec 2017
TL;DR: In this paper, a character recognition method and a device and a terminal is described, which comprises steps of extracting the feature of a to-be-recognized image to obtain the feature map of the image, generating a feature sequence according to the feature information, encoding the feature sequence to obtain an encoded feature sequence, and repeating the following processes until all characters in the image are recognized: according to a preset weight vector, weighting the encoded feature sequences to obtain a feature vector, and decoding the feature vector to generate a recognition result of a character.
7
Patent
Detection identification and detection identification network training methods and apparatuses, device and medium
Liu Xuebo,Liang Ding +1 more
- 29 Jun 2018
TL;DR: In this article, the authors proposed a detection identification method consisting of the steps of inputting a to-be-processed image to a detection network, wherein the detection identification network comprises a shared network layer, a detector network layer and an identification network layer.
7
Patent
Identification method and device of certificate characters
Ma Zheng,Chen Zhi,He Caiyang,He Pengfei,Zhang Xinyu +4 more
- 18 Sep 2018
TL;DR: In this paper, an identification method and device of certificate characters is presented. The method comprises steps of acquiring a to-be-identified certificate picture; using a character region detection model to detect the to-besidentified certificate image so as to obtain a character regions of the to be-besided certificate picture, and using the character identification model to identify the character region of the image.
7
Patent
Character recognition method and device
Yang Song
- 13 Mar 2018
TL;DR: In this paper, the authors proposed a method consisting of performing feature extraction on the to-be-identified character region image by using a first convolutional neural network, obtaining a characteristic graph matrix, cutting the feature graph matrix to obtain a row of characteristic sequences, identifying the row of feature sequences by usinga circulation neural network to obtain the characters in the to be-be identified character regions image.
6
References
Patent
Character identification method and device
Zhang Yiwei,Zhang Chi,Yin Qi +2 more
- 27 Jul 2016
TL;DR: In this article, a character identification method consisting of the steps of: obtaining an image to be identified, detecting the image, and obtaining expected character frames containing characters, expanding and merging the expected characters frames to generate character rows, and identifying the characters in the generated character rows.
22
Patent
Visual-and-vocal sense based dialogue data interactive processing method and apparatus
Xu Zhenjing,Lu Yuhao +1 more
- 31 Aug 2016
TL;DR: In this article, a visual-and-vocal sense-based dialogue data interactive processing method and an apparatus are presented to detect visual and audio characteristics of the current image with audios being monitored, and a dialogue pattern is formed according to the dialogue or answers can be provided by the search into an answer database.
22
Patent
Complex optical text sequence identification system based on convolution and recurrent neural network
Liu Shilin,He Hongjing,Chen Bingzhang,Wu Yunong,Yao Jia +4 more
- 15 Jun 2016
TL;DR: In this paper, a complex optical text sequence identification system based on convolution and recurrent neural network (RNN) is proposed, which includes an image and text input module, a sliding sampling module, and a CNN and an RNN, where the RNN successively identifies the front part of each character, the back part of every character, numbers, letters, punctuation or blank according to the CNN input signal and the output data of the CNN for the last moment.
15
Patent
A method and apparatus for providing automatically recommendations concerning an industrial system
Sanjeev Kumar Karn,Ulli Waltinger +1 more
- 26 Nov 2015
TL;DR: In this article, a diagnostic system and method for providing recommendations concerning an industrial system is described. But the system is not suitable for the extraction of ontology instances of classes within a domain related ontology using RNNs.
15
Patent
Complex image and text sequence identification method
Liu Shilin,He Hongjing,Chen Bingzhang,Wu Yunong,Yao Jia +4 more
- 15 Jun 2016
TL;DR: In this article, a sliding sampling box is used to perform sliding sampling on an image and text sequence to identify the sub images obtained through sampling by means of a CNN and outputting the characteristics to an RNN, wherein the RNN successively identifies the front part of each character, the back part of every character, numbers, letters, punctuation, or blank according to the input signal.
12
Related Papers (5)
Ma Ao,Teng Bin,Sun Cuifeng +2 more
- 11 Oct 2019
Zhang Hanwen,Zhang Hongtao,Li Zhaojia,Qu Jianfang +3 more
- 22 Oct 2019