My works Technical

A Few are here

1. Optical Character Recognition for Printed Tamil Text using Unicodes

(Published in Journal of Zejhiang university, China)


Optical Character Recognition (OCR) refers to the process of converting printed Tamil text documents into software translated Unicode Tamil Text. The printed documents available in the form of books, papers, magazines, etc. are scanned using standard scanners which produce an image of the scanned document. As part of the preprocessing phase the image file is checked for skewing. If the image is skewed, it is corrected by a simple rotation technique in the appropriate direction. Then the image is passed through a noise elimination phase and is binarized. The preprocessed image is segmented using an algorithm which decomposes the scanned text into paragraphs using special space detection technique and then the paragraphs into lines using vertical histograms, and lines into words using horizontal histograms, and words into character image glyphs using horizontal histograms. Each image glyph is comprised of 32×32 pixels. Thus a database of character image glyphs is created out of the segmentation phase. Then all the image glyphs are considered for recognition using Unicode mapping. Each image glyph is passed through various routines which extract the features of the glyph. The various features that are considered for classification are the character height, character width, the number of horizontal lines (long and short), the number of vertical lines (long and short), the horizontally oriented curves, the vertically oriented curves, the number of circles, number of slope lines, image centroid and special dots. The glyphs are now set ready for classification based on these features. The extracted features are passed to a Support Vector Machine (SVM) where the characters are classified by Supervised Learning Algorithm. These classes are mapped onto Unicode for recognition. Then the text is reconstructed using Unicode fonts. 




2. Image Retrieval from an Image: A Geometrical Approach

(Among Best 21 Research Projects in IISRC <Intel India Student Research Contest>)

(Presented in International conference on Cutting Edge Technology, Bheemawaram)


An “Efficient” and “Easy to Implement” algorithm for an image to be searched inside a given image. This is based mainly on searching the image frame inside the given image. Firstly, the center of the image is guessed and then the edge ratio is taken. The image frame is matched with the required image in hierarchical sequence, fixing the center as constant. As the edge ratio is taken, images of different size can be recognized as well and as the Center is considered constant, the difference due to rotation is optimized.




3. Wavelets for Pattern Recognition: An approach through Splines

(Presented In Techkriti, IIT Kanpur)


Wavelet has created a new but vast area for research not only for Mathematicians but also for the Computer and Communication people. In a very short period it has established its important role in various fields of engineering today. If we talk about Splines, it came in existence around 50 years ago. It also took a very small period to be the favourite of computer people. As Spline itself is a very interesting topic, then what will happen if they both will shake hands. Yes, they did it and the joint name is “Spline Wavelet”. So, there should be no question that how the Splines have strengthened the role and widened the area of the wavelet in computer field. Here, in this paper, we are using spline wavelets in “Pattern Recognition”. We will discuss this topic via image processing which is generally used in various fields. Here we will try to focus our attention mainly to the Cardinal B-splines. We will also try to focus on the benefits of spline wavelets over others.




4. Discrete Wavelet Transform: an efficient way of Digital Watermarking

(Presented in Annamai University)