A Multi-Object Feature Selection Based Text Detection and Extraction Using Skeletonized Region Optical Character Recognition in-Text Images

  • Authors

    • K R. Sanjuna
    • K Dinakaran
    2018-07-04
    https://doi.org/10.14419/ijet.v7i3.6.16009
  • Text detection, segmentation, text localization, Edge Smoothing, the bounding box.

  • Abstract

    Information or content extraction from image is crucial task for obtaining text in natural scene images. The problem arise due to variation in images contains differential object to explore values like, background filling, saturation ,color etc. text projections from different styles varies the essential information which is for wrong understand for detecting characters.so detection of region text need more accuracy to identify the exact object. To consider this problem, to propose a multi-objective feature for text detection and localization based on skeletonized text bound box region of text confidence score. This contributes the intra edge detection, segmentation along skeleton of object reflective. the impact of multi-objective region selection model (MSOR) is to recognize the exact character of style matches using the bounding box region analysis which is to identify the object portion to accomplish the candidate extraction model.To enclose the text region localization of text resolution and hazy image be well identified edge smoothing quick guided filter methods. Further the region are skeletonized to morphing the segmented region of inter segmentation to extract the text.

     

     

  • References

    1. [1] Kim KI, Jung K & Kim H, “Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithmâ€, IEEE Trans. Pattern Anal. Mach. Intell., Vol.25, No.12, (2003), pp.1631–1639.

      [2] Jung K, Kim KI & Jain AK, “Text information extraction in images and video: A surveyâ€, Pattern Recognit., Vol.37, (2004), pp.977-997.

      [3] Liu C, Wang C & Dai R, “Text detection in images based on the unsupervised classification of edge-based featuresâ€, Proc. IEEE Int. Conf. Doc. Anal. Recognit, (2005), pp.610–614.

      [4] Ye Q, Huang Q, Gao W & Zhao D, “Fast and robust text detection in images and video framesâ€, Image Vis. Comput., Vol.23, (2005), pp.565–576.

      [5] Mancas-Thillou C & Gosselin B, “Spatial and color spaces combination for natural scene text extractionâ€, Proc. IEEE Int. Conf. Image Process, (2006), pp.985–988.

      [6] Lim J, Park J & Medioni G, “Text segmentation in color images using tensor votingâ€, Image Vis. Comput., Vol.25, No.5, (2007), pp.671–685.

      [7] Zhou P, Li L & Tan CL, “Character recognition under severe perspective distortionâ€, Proc. IEEE Int. Conf. Pattern Recognit., (2008).

      [8] Kim W & Kim C, “A new approach for overlay text detection and extraction from complex video sceneâ€, IEEE Trans. Image Process, Vol.18, No.2, (2009), pp.401–411.

      [9] Weinman JJ, Learned-Miller E & Hanson A, “Scene text recognition using similarity and a lexicon with sparse belief propagationâ€, IEEE Trans. Pattern Anal. Mach. Intell., Vol.31, No.10, (2009), pp.1733–1746.

      [10] Chiang Y & Knoblock CA, “An approach for recognizing text labels in raster mapsâ€, Proc. IEEE Int. Conf. Pattern Recognition, (2010), pp.3199–3202.

      [11] Pan Y, Liu CL & Hou X, “Fast scene text localization by learning-based filtering and verificationâ€, Proc. IEEE Int. Conf. Image Process, (2012), pp.2269–2272.

      [12] Wakahara T & Kita K, “Binarization of color character strings in scene images using K-means clustering and support vector machinesâ€, Proc. IEEE Int, Conf. Doc. Anal.Recognition., (2011), pp.3183–3186.

      [13] Zhao X, Lin KH, Fu Y, Hu Y, Liu Y & Huang TS, “Text from corners: A novel approach to detect text and caption in videosâ€, IEEE Trans. Image Process., Vol.20, No.3, (2011), pp.790-799.

      [14] Zhou G, Liu, Y Meng Q & Zhang Y, “Detecting multilingual text in the natural sceneâ€, Proc. IEEE 1st Int. Symp. Access Spaces, (2011), pp.116–120.

      [15] Bai B, Yin F & Liu CL, “A fast stroke-based method for text detection in videoâ€, Proc. IAPR Int. Workshop Doc. Anal. Syst., (2012), pp.69–73.

      [16] Yi C & Tian Y, “Localizing text in scene images by boundary clustering, stroke segmentation and string fragment classificationâ€, IEEE Trans. Image Process., Vol.21, No.9, (2012), pp.4256-4268.

      [17] Yi C &Tian Y, “Text extraction from scene images by character apperance and structure modelingâ€, Comput. Vis. Image Understanding, Vol.117, No.2, (2013), pp.182–194.

      [18] Wang H, Landa, Y Fallon MF & Teller SJ, “Spatially prioritized and persistent text detection and decodingâ€, Proc. Int. Workshop Camera-Based Doc. Anal. Recognit., (2013), pp.3–17.

      [19] Kang L & Doermann D, “Orientation robust text line detection in natural imagesâ€, Proc. IEEE Int. Conf. Comput. Vis. PatternRecognit., (2014), pp.4034–4041.

      [20] Lu S, Chen T, Tian S, Lim JH & Tan CL, “Scene text extraction based on edges and support vector regressionâ€, International Journal on Document Analysis and Recognition (IJDAR), Vol.18, No.2, (2015), pp.125-135.

      [21] Weinman JJ, Butler Z, Knoll D & Feild J, “Toward integrated scene text readingâ€, IEEE Trans. Pattern Anal. Mach. Intell., Vol. 3, No.2, (2014), pp.375–387.

      [22] Yin XC, Pei WY, Zhang J & Hao HW, “Multi-orientation scene text detection with adaptive clusteringâ€, IEEE transactions on pattern analysis and machine intelligence, Vol.37, No.9, (2015), pp.1930-1937.

      [23] Wang Q, Lu Y & Sun S, “Text detection in nature scene images using two-stage nontext filteringâ€, 13th International Conference on.IEEE Document Analysis and Recognition, (2015), pp.106–110.

      [24] Liao M, Shi B, Bai X, Wang X & Liu W, “TextBoxes: A Fast Text Detector with a Single Deep Neural Networkâ€, AAAI, (2017), pp. 4161-4167.

      [25] Soni R, Kumar B & Chand S, Text detection and localization in natural scene images using MSER and fast guided filterâ€, Fourth International Conference on Image Information Processing (ICIIP), (2017), pp.1-6.

      [26] Liu Z, Li Y, Qi X, Yang Y, Nian M, Zhang H & Xiamixiding R, “Method for unconstrained text detection in natural scene imageâ€, IET Computer Vision, Vol.11, No.7, (2017), pp.596-604.

  • Downloads

  • How to Cite

    R. Sanjuna, K., & Dinakaran, K. (2018). A Multi-Object Feature Selection Based Text Detection and Extraction Using Skeletonized Region Optical Character Recognition in-Text Images. International Journal of Engineering & Technology, 7(3.6), 386-393. https://doi.org/10.14419/ijet.v7i3.6.16009

    Received date: 2018-07-22

    Accepted date: 2018-07-22

    Published date: 2018-07-04