[1]陈梓洋,王宇飞,钱侃,等. 自然场景下基于区域检测的文字识别算法[J].计算机技术与发展,2015,25(07):230-233.
　CHEN Zi-yang,WANG Yu-fei,QIAN Kan,et al. Character Recognition Algorithm Based on Region Detection in Natural Scene[J].,2015,25(07):230-233.
点击复制

 自然场景下基于区域检测的文字识别算法()
分享到：

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

卷:
25
期数:
2015年07期
页码:
230-233
栏目:
应用开发研究
出版日期:
2015-07-10

文章信息/Info

Title:
 Character Recognition Algorithm Based on Region Detection in Natural Scene
文章编号:
1673-629X（2015)07-0230-04
作者:
 陈梓洋; 王宇飞; 钱侃; 张超; 孙知信
 南京邮电大学 物联网学院
Author(s):
 CHEN Zi-yang; WANG Yu-fei;  QIAN Kan ; ZHANG Chao ; SUN Zhi-xin
关键词:
 ; 分水岭算法; ISODAtA算法;  基于区域的检测算法; 自然场景; 文字识别
Keywords:
 ; watershed algorithm; ISODATA algorithm; detection algorithm based on region; natural scene; character recognition
分类号:
TP301.6
文献标志码:
A
摘要:
 由于自然场景的图像具有复杂性和不确定性，导致自然场景下文字识别相比于文本识别更加复杂和困难，利用现有识别算法对自然场景图像进行识别，其识别效率较低，识别效果不理想。为提高识别率，文中首先利用分水岭算法对原图像进行初处理，再对预处理后的图像进行特征提取，划分区域，最后利用ISODAtA算法进行第二次处理，最终对图像中的文字进行识别。对提出的算法进行仿真和实验，实验结果表明，采用该算法后，自然场景下文字的识别效果明显，识别率高。
Abstract:
 Because the natural scene text has the characteristic such as the uncertainty and complexity,the natural scene is becoming diffi-cult and important in character recognition. By using the existing recognition algorithm for identification of natural scene images,the rec-ognition rate is low and the recognition effect is not ideal. In order to improve the recognition rate,firstly use watershed algorithm to finish the first original image processing,then extract feature and partition the image after preprocessing,finally utilize ISODATA algorithm to process second times and identify the text in the image. By simulating and experimenting on the proposed algorithm,the experimental re-sults show this algorithm can recognize the text in natural scene efficiently with the high recognition rate.

相似文献/References:

[1]张少娴 俞琼.基于时空相关性预测的运动估计的优化[J].计算机技术与发展,2010,(01):100.
　ZHANG Shao-xian,YU Qiong.An Optimization Method for Spatiotemporal Predictive Motion Estimation[J].,2010,(07):100.
[2]盛仲飙.基于对比度增强的分水岭分割算法[J].计算机技术与发展,2012,(12):90.
　SHENG Zhong-biao.Watershed Segmentation Algorithm Based on Contrast Enhancement[J].,2012,(07):90.
[3]戴丹.基于改进分水岭算法的粘连颗粒图像分割[J].计算机技术与发展,2013,(03):19.
　DAI Dan.Image Segmentation of Adhering Particle Based on Improved Watershed Algorithm[J].,2013,(07):19.
[4]蔡子文,费向东.基于标记的数学形态学滤波分水岭算法[J].计算机技术与发展,2013,(03):38.
　CAI Zi-wen,FEI Xiang-dong.Mathematical-morphological Watershed Algorithm Based on Marking[J].,2013,(07):38.
[5]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(07):1.
[6]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(07):5.
[7]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(07):13.
[8]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(07):21.
[9]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(07):25.
[10]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(07):29.

更新日期/Last Update: 2015-09-08