[1]周成伟. 基于卷积神经网络的自然场景中数字识别[J].计算机技术与发展,2017,27(11):101-105.
　ZHOU Cheng-wei. Recognition of Numbers in Natural Scene with Convolutional Neural Network[J].,2017,27(11):101-105.
点击复制

 基于卷积神经网络的自然场景中数字识别()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
27
期数:
2017年11期
页码:
101-105
栏目:
智能、算法、系统工程
出版日期:
2017-11-10

文章信息/Info

Title:
  Recognition of Numbers in Natural Scene with Convolutional Neural Network
文章编号:
1673-629X（2017)11-0101-05
作者:
 周成伟
 南京邮电大学 计算机学院
Author(s):
 ZHOU Cheng-wei
关键词:
 ; 卷积神经网络; 自然场景; 数字识别;  端到端
Keywords:
 ; convolutional neural network; natural scene; number recognition; end to end
分类号:
TP301
文献标志码:
A
摘要:
 从复杂的图片背景中提取文本信息一直是计算机视觉中的热点与难点问题.近年来,随着卷积神经网络在图像识别研究的突破性进展,传统的人工提取图像特征方式逐渐为深层网络学习特征方式所取代,而应用卷积神经网络(CNN)的场景文本识别方法也越来越受到广泛的关注.为此,提出了自然场景下基于卷积网络结构的数字识别改进方法.该方法能够对目标区域进行检测,并进行端到端的数字字符识别训练,数字识别部分提取的特征还可用来初始化目标检测的网络部分,以减少特征的重复提取并提高训练速度.需要处理的图像输入无需固定格式,只需输入原始图像即可,可减少图像预处理过程及其对原始图像数据的不良影响,提高图像识别的精度.基于谷歌街景数据集(SVHN)与MSRA-TD500、ICDAR 2013数据集的数字字符识别验证结果表明,该方法的识别效果优于其他已有的识别方法.
Abstract:
 Extracting text information from a complex background image has been a hot topic and difficulty in computer vision. With the breakthrough of Convolutional Neural Network ( CNN) in image recognition in recent years,the field of computer vision has gradually a-bandoned the way of extracting image features by manual methods,instead of using the deep network to automatically learn features. U-sing of scene text recognition of CNN is paid more and more attention. Therefore,an improved number recognition method of network structure convolution in natural scenes is proposed. It achieves the goal area detection and digital character recognition end-to-end train-ing,and recognized feature can be used to initialize the network portion of target detection so as to reduce duplication feature extraction and improve the training speed. The image input needs to be processed does not require a fixed format but original image,which reduces the poor influence of image preprocessing on its original image data and improves the recognition accuracy. It is showed in the verification based on SVHN,MSRA-TD500 as well as the ICDAR 2013 that it is superior to other recognition methods in recognition performance.

相似文献/References:

[1]张志宏,吴庆波,邵立松,等.基于飞腾平台TOE协议栈的设计与实现[J].计算机技术与发展,2014,24(07):1.
　ZHANG Zhi-hong,WU Qing-bo,SHAO Li-song,et al. Design and Implementation of TCP/IP Offload Engine Protocol Stack Based on FT Platform[J].,2014,24(11):1.
[2]梁文快,李毅. 改进的基因表达算法对航班优化排序问题研究[J].计算机技术与发展,2014,24(07):5.
　LIANG Wen-kuai,LI Yi. Research on Optimization of Flight Scheduling Problem Based on Improved Gene Expression Algorithm[J].,2014,24(11):5.
[3]黄静,王枫,谢志新,等. EAST文档管理系统的设计与实现[J].计算机技术与发展,2014,24(07):13.
　HUANG Jing,WANG Feng,XIE Zhi-xin,et al. Design and Implementation of EAST Document Management System[J].,2014,24(11):13.
[4]侯善江[],张代远[][][]. 基于样条权函数神经网络P2P流量识别方法[J].计算机技术与发展,2014,24(07):21.
　HOU Shan-jiang[],ZHANG Dai-yuan[][][]. P2P Traffic Identification Based on Spline Weight Function Neural Network[J].,2014,24(11):21.
[5]李璨,耿国华,李康,等. 一种基于三维模型的文物碎片线图生成方法[J].计算机技术与发展,2014,24(07):25.
　LI Can,GENG Guo-hua,LI Kang,et al. A Method of Obtaining Cultural Debris’ s Line Chart Based on Three-dimensional Model[J].,2014,24(11):25.
[6]翁鹤,皮德常. 混沌RBF神经网络异常检测算法[J].计算机技术与发展,2014,24(07):29.
　WENG He,PI De-chang. Chaotic RBF Neural Network Anomaly Detection Algorithm[J].,2014,24(11):29.
[7]刘茜[],荆晓远[],李文倩[],等. 基于流形学习的正交稀疏保留投影[J].计算机技术与发展,2014,24(07):34.
　LIU Qian[],JING Xiao-yuan[,LI Wen-qian[],et al. Orthogonal Sparsity Preserving Projections Based on Manifold Learning[J].,2014,24(11):34.
[8]尚福华,李想,巩淼. 基于模糊框架-产生式知识表示及推理研究[J].计算机技术与发展,2014,24(07):38.
　SHANG Fu-hua,LI Xiang,GONG Miao. Research on Knowledge Representation and Inference Based on Fuzzy Framework-production[J].,2014,24(11):38.
[9]叶偲,李良福,肖樟树. 一种去除运动目标重影的图像镶嵌方法研究[J].计算机技术与发展,2014,24(07):43.
　YE Si,LI Liang-fu,XIAO Zhang-shu. Research of an Image Mosaic Method for Removing Ghost of Moving Targets[J].,2014,24(11):43.
[10]余松平[][],蔡志平[],吴建进[],等. GSM-R信令监测选择录音系统设计与实现[J].计算机技术与发展,2014,24(07):47.
　YU Song-ping[][],CAI Zhi-ping[] WU Jian-jin[],GU Feng-zhi[]. Design and Implementation of an Optional Voice Recording System Based on GSM-R Signaling Monitoring[J].,2014,24(11):47.
[11]张丹丹,李雷. 基于PCANet-RF的人脸检测系统[J].计算机技术与发展,2016,26(02):31.
　ZHANG Dan-dan,LI Lei. Face Detection System Based on PCANet-RF[J].,2016,26(11):31.
[12]邓宗平,赵启军,陈虎. 基于深度学习的人脸姿态分类方法[J].计算机技术与发展,2016,26(07):11.
　DEND Zong-ping,ZHAO Qi-jun,CHEN Hu. Face Pose Classification Method Based on Deep Learning[J].,2016,26(11):11.
[13]戴晓薇,赵启军. 基于回归的指纹方向场估计[J].计算机技术与发展,2017,27(01):1.
　DAI Xiao-wei,ZHAO Qi-jun. Fingerprint Orientation Field Estimation Based on Regression[J].,2017,27(11):1.
[14]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(11):7.

更新日期/Last Update: 2017-12-26