Localization of Text in Complex Images Using Haar Wavelet Transform
Neha Gupta1, V.K Banga2
1Neha Gupta, Department of Electronics and Communication, PTU University/ Amritsar College of Engineering and Technology, Amritsar, India.
2Dr. V.K.Banga, Head of Department of Electronics and Communication, PTU University/ Amritsar College of Engineering and Technology, Amritsar, India.
Manuscript received on 15 November 2012 | Revised Manuscript received on 25 November 2012 | Manuscript Published on 30 November 2012 | PP: 111-115 | Volume-1 Issue-6, November 2012 | Retrieval Number: E0345101612/2012©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, a new hybrid approach is developed which locate text in different backgrounds. However, variation of text due to differences in size, style, orientation and alignment, as well as low image contrast and complex background make the problem of automatic text localization extremely challenging. The text localization algorithm system is designed to locate text in different kinds of images and eliminates the need to devise separate method for various kinds of images. Firstly, the color image is converted into grayscale image. After that, Haar Discrete Wavelet Transform (DWT) is employed. Haar DWT decompose image into four sub image coefficients, one is average and other three are detail. Now, Sobel edge detector is applied on three detail components, the resultant edges so obtained are combined to form edge map. The morphological dilation is performed on binary edge map and further label the connected components. Finally, using some specific condition, the text is obtained in bounding box.
Keywords: Bounding box, Discrete Wavelet Transform, Haar wavelet, Sobel edge detector
Scope of the Article: Discrete Wavelet Transform