基于双门限梯度模式的图像文字检测方法

doi:10.11896/j.issn.1002-137X.2016.6A.037

摘要/Abstract

摘要： 对复杂自然背景下的图像文字检测技术进行了研究,提出了一种基于双门限梯度模式的图像文字检测方法。首先,在文字粗检测阶段中,该方法抽取了最大极值稳定区域(Maximally Stable Extremal Regions,MSER)作为候选文字区域,避免了对整幅图像进行扫描,极大地提高了检测速度和实时性；其次,在文字精检测阶段的特征提取部分,为了克服文字区域颜色对比反转问题和自然图像的噪声干扰问题,提出了一种双门限梯度模式特征来描述文字区域的纹理特征；最后,在文字精检测的检测器设计中,利用极限学习机构造新的级联型ELM(Extreme Learning Machine)检测器,极大地缩短了分类器的训练时间。实验结果表明,该方法不仅具有优良的检测性能,而且能极大地缩短分类器训练时间和检测时间。

关键词: 图像文字检测,双门限梯度模式,极限学习机,多分类器组合

Abstract: This paper studied the traditional image text detection approaches and proposed a new image text detection method based on double-threshold gradient pattern with a pretty fast speed in both classifier training and implementing.Firstly,in the rough detection phase,the maximally stable extremal regions(MSER) was extracted as a candidate text area,to avoid scanning the whole image,greatly improving the detection speed and real-time.Secondly,in the feature extraction part of refine detection phase,in order to overcome the text area color contrast inversion problem and the problem of noise in natural image,this paper creatively presented a dual threshold gradient mode feature to describe the texture of the text area feature.Finally,to design the detector for text fine detection,this paper designed a new Cascade ELM(Extreme Learning Machine) detector by limit learning machine,which greatly shortens the classifier training time.The experimental results show that this method not only has excellent detection performance,but also greatly shortens the classifier training time and testing time.

Key words: Image text detection,Double-threshold gradient pattern,Extreme learning machine,Multiple classifier combination

蔡文哲,王斌君,李培岳. 基于双门限梯度模式的图像文字检测方法[J]. 计算机科学, 2016, 43(Z6): 156-164. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.037

CAI Wen-zhe, WANG Bin-jun and LI Pei-yue. New Image Text Detection Method Based on Double-threshold Gradient Pattern[J]. Computer Science, 2016, 43(Z6): 156-164. https://doi.org/10.11896/j.issn.1002-137X.2016.6A.037

参考文献

[1] Epstein B,Ofek E,Wexler Y.Detecting text in natural sceneswith stroke width transform[C]∥2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2010:2963-2970
[2] Li Y,Lu H.Scene text detection via stroke width[C]∥201221st International Conference on Pattern Recognition (ICPR).IEEE,2012:681-684
[3] Chen X,Yang L,Zhang J,et al.Automatic detection and recognition of signs from natural scenes[J].IEEE Transactions on Image Processing,2004,13(1):87-99
[4] 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(7):236-239
[5] Kim K I,Jung K,Kim J H.Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(12):1631-1639
[6] Chen X,Yuille A L.Detecting and reading text in natural scenes[C]∥Proceedings of the 2004 IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition(CVPR 2004).IEEE,2004,2:366-373
[7] Pan Y F,Hou X,Liu C L.Robust System to Detect and Localize Texts in Natural Scene Images[C]∥The Eighth IAPR International Workshop on Document Analysis Systems(DAS’08).IEEE,2008:35-42
[8] E Q,Huang Q,Gao W,et al.Fast and robust text detection in images and video frames[J].Image and Vision Computing,2005,23(6):565-576
[9] Goto H.Redefining the DCT-based feature for scene text detection[J].International Journal of Document Analysis and Recognition (IJDAR),2008,11(1):1-8
[10] Gomez L,Karatzas D.MSER-based Real-Time Text Detectionand Tracking[C]∥ 2014 22nd International Conference on Pattern Recognition (ICPR).IEEE,2014:3110-3115
[11] Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]∥IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR 2005).IEEE,2005,1:886-893
[12] Ojala T,Pietikinen M,Harwood D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59
[13] Jun B,Kim D.Robust face detection using local gradient patterns and evidence accumulation[J].Pattern Recognition,2012,45(9):3304-3316
[14] Cui A C,Asari V K,Braun A D.Robust textural features forreal time face recognition[C]∥Proc.SPIE9408.Imaging and Multimedia Analytics in a Web and Mobile World 2015.2015:940806-940806-13
[15] 郑英娟,张有会,王志巍,等.基于八方向Sobel算子的边缘检测算法[J].计算机科学,2013,40(11A):354-356
[16] Shen D H,Zhang L C,Xu E.An improved edge detection algorithm based on Sobel operator[J].Information Technology,2015,347-350(4):3541-3545
[17] Tian Q C,Zhao X L,Wu X J,et al.Iris Classifier Enhanced Algorithm Based on AdaBoost[M]∥Advanced Intelligent Computing Theories and Applications.With Aspects of Contemporary Intelligent Computing Techniques.Springer Berlin Heidelberg,2007:1001-1009
[18] Mori M,Uchida S,Sakano H.Global feature for online character recognition[J].Pattern Recognition Letters,2014,35(1):142-148
[19] Sok P,Taing N.Support Vector Machine (SVM) based classi-fier for Khmer Printed Character-set Recognition[C]∥ Asia-Pacific Signal and Information Processing Association,2014 AnnualSummit and Conference (APSIPA).IEEE,2014:1-9
[20] Huang G B,Wang D H,Lan Y.Extreme learning machines:asurvey[J].International Journal of Machine Learning and Cybernetics,2011,2(2):107-122
[21] Iosifidis A,Tefas A.Ioannis Pitas[J].Pattern Recognition Letters,2015,4:11-17
[22] Jung K,In Kim K,K Jain A.Text information extraction in images and video:a survey[J].Pattern Recognition,2004,37(5):977-997
[23] 何淑琳,张雪英,孙颖,等.基于极限学习机的语音情感识别[J].微电子学与计算机,2015,7(7):50-54
[24] 卢诚波,梅颖.前馈网络的一种高精度鲁棒在线贯序学习算法[J].上海交通大学学报,2015,49(8):1137-1143
[25] Iosifidis A,Tefas A,Pitas I.On the kernel Extreme LearningMachine classifier[J].Pattern Recognition Letters,2015,54:11-17
[26] Cao L L,Huang W B,Sun F C.Optimization-Based ExtremeLearning Machine with Multi-kernel Learning Approach for Classification[C]∥2014 22nd International Conference on Pattern Recognition (ICPR).IEEE Computer Society,2014:3564-3569
[27] Bandarabadi M,Dourado A,Teixeira C A,et al.Seizure prediction with bipolar spectral power features using Adaboost and SVM classifiers[C]∥Annual International Conference of the IEEE Engineering in Medicine and Biology Society.IEEE Engineering in Medicine and Biology Society.2013:6305-6308
[28] 李小冬.核极限学习机的理论与算法及其在图像处理中的应用[D].杭州:浙江大学,2014
[29] 杨彬,夏思宇.自然场景多方向文本检测方法[J].华中科技大学学报(自然科学版),2015(S1):228-232
[30] Yao Cong,Bai Xiang,Liu Wen-yu,et al.Detecing texts of arbitrary orientations in natural images[C]∥Proc of IEEE Confe-rence on computer Vision and Pattern Recognition.Rhode Island:Curran Associates,2012:1083-1090
[31] Kang L,Li Y,Doermann D.Orientation Robust Text Line Detection in Natural Images[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).IEEE,2014:4034-4041
[32] Epshtein B,Ofek E,Wexler Y.Detecting text in natural scenes with stroke width transform[C]∥ 2013 IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2010:2963-2970

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed