Chakravarthy Bhagvati

An OCR system for Telugu

Telugu is the language spoken by more than 100 million people of South India. Telugu has a complex orthography with a large number of distinct character shapes (estimated to be of the order of 10,000) composed of simple and compound characters formed from 16 vowels (called achchus) and 36 consonants (called hallus). We present an efficient and practical approach to Telugu OCR which limits the number of templates to be recognized to just 370, avoiding issues of classifier design for thousands of shapes or very complex glyph segmentation. A compositional approach using connected components and fringe distance template matching was tested to give a raw OCR accuracy of about 92%. Several experiments across varying fonts and resolutions showed the approach to be satisfactory.

Texture element feature characterizations for CBIR

Colour and texture are the most common features used in CBIR systems today. In this paper, we wish to investigate structural methods of texture analysis for CBIR in view of their closeness to human perception and description of texture. In structural analysis, local patterns are the key (as is the case with humans), and when used as features may be expected to return more relevant images in CBIR. One method to describe local patterns in computationally simple terms is texture spectrum proposed by He and Wang. In this paper, we propose two additional characterizations of local patterns. The first is an extension of He and Wangs texture spectrum to larger and more meaningful windows, along with new structural features that capture local patterns such as horizontal and vertical stripes, alternating dark and bright spots, etc. The second is a new method that characterizes patterns as contrast variations in 5 /spl times/ 5 windows. We apply the new texture characterizations to develop a CBIR application and tested their performance on two databases containing remote sensing images. Our results show accuracies that range from 60% to 100% depending on the query image and the features contained therein. These results indicate that our texture features are useful in retrieving images appropriate for different remote sensing applications.

Structural Similarity Measure for Color Images

images reveal more meaningful information to the human observers rather than grayscale ones. Regardless of the advantages of the existing well-known objective image quality measures, one of the common and major limitations of these measures is that they evaluate the quality of grayscale images only and dont make use of color information. In this paper we propose an improved method for image quality assessment that adds a color comparison to the criteria of the well-known Multiscale Structural Similarity index (MSSIM). We evaluated the new color image quality measure through human subjective experiments. Our human subjective evaluation data contains 25 reference images and 875 test images produced by five popular color quantization algorithms. Each of the quantized images was evaluated by twenty two subjects and more than 19200 individual human quality judgments were carried out to obtain the final mean opinion scores. We also tested the proposed method on TID2008 image database to further verify our results. These results indicate that adding color comparison improves MSSIM for many distortions in TID2008 and for assessing quantized images in our database. Keywordsquality assessment, Structural similarity index, Color quantization.

A wavelet based multiresolution algorithm for rotation invariant feature extraction

The present work aims at proposing a new wavelet representation formula for rotation invariant feature extraction. The algorithm is a multilevel representation formula involving no wavelet decomposition in standard sense. Using the radial symmetry property, that comes inherently in the new representation formula, we generate the feature vectors that are shown to be rotation invariant. We show that, using a hybrid data mining technique, the algorithm can be used for rotation invariant content based image retrieval (CBIR). The proposed rotation invariant retrieval algorithm, suitable for both texture and nontexture images, avoids missing any relevant images but may retrieve some other images which are not very relevant. We show that the higher precision can however be achieved by pruning out irrelevant images.

Towards Improving the Accuracy of Telugu OCR Systems

Design of a high accuracy OCR system is a challenging task as the system performance is affected by its component modules. Each module has its own impact on the overall accuracy of the OCR system. An improvement in a module reflects upon overall system performance. In the present work, we have developed an OCR system for Telugu. Our experiments on a corpus of about 1000 images has shown that the system performance is degraded due to broken characters caused by the binarization module as well as due to improper character segmentation. Therefore, we address the issues of handling broken characters and poor segmentation. A novel approach which is based on feedback from the distance measure used by the classifier is proposed to handle broken characters. For character segmentation, our proposed approach exploits the orthographic properties of Telugu script. As a result, significant improvement is obtained in the performance of the system. These algorithms are generic and may be applicable to other Indian scripts, especially to south Indian scripts. In our experiments, an end-to-end system performance is evaluated which is not reported in the literature.

A Structure Based Approach for Mathematical Expression Retrieval

Mathematical expression (ME) retrieval problem has currently received much attention due to wide-spread availability of MEs on the World Wide Web. As MEs are two-dimensional in nature, traditional text retrieval techniques used in natural language processing are not sufficient for their retrieval. In this paper, we have proposed a novel structure based approach to ME retrieval problem. In our approach, query given in (mbox{LaTeX}) format is preprocessed to eliminate extraneous keywords (like displaystyle, begin{array} etc.) while retaining the structure information like superscript and subscript relationships. MEs in the database are also preprocessed and stored in the same manner. We have created a database of 829 MEs in (mbox{LaTeX}) form, that covers various branches of mathematics like Algebra, Trigonometry, Calculus etc. Preprocessed query is matched against the database of preprocessed MEs using Longest Common Subsequence (LCS) algorithm. LCS algorithm is used as it preserves the order of keywords in the preprocessed MEs unlike bag of words approach in the traditional text retrieval techniques. We have incorporated structure information into LCS algorithm and proposed a measure based on the modified algorithm, for ranking MEs in the database. As proposed approach exploits structure information, it is closer to human intuition. Retrieval performance has been evaluated using standard precision measure.

Vein Pattern Indexing Using Texture and Hierarchical Decomposition of Delaunay Triangulation

In biometric identification systems, the identity corresponding to the query image is determined by comparing it against all images in the database. This exhaustive matching process increases the response time and the number of false positives of the system; therefore, an effective mechanism is essential to select a small collection of candidates to which the actual matching process is applied. This paper presents an efficient indexing algorithm for vein pattern databases to improve the search speed and accuracy of identification. In this work, we generate a binary code for each image using texture information. A hierarchical decomposition of Delaunay triangulation based approach for minutiae is proposed and used with binary code to narrow down the search space of the database. Experiments are conducted on two vein pattern databases, and the results show that, while maintaining 100% Hit Rate, the proposed method achieves lower penetration rate than what existing methods achieve.

Methods to Solve Discrete Logarithm Problem for Ephemeral Keys

The present study investigates the difficulty of solving the mathematical problem, namely DLP (Discrete Logarithm Problem) for ephemeral keys. DLP is the basis for many public key cryptosystems. The ephemeral keys are used in such systems to ensure the security. The DLP defined on a prime field

Identification of Non-Black Inks Using HSV Colour Space

mathbb Z_p^{*}

A rule-based approach to form mathematical symbols in printed mathematical expressions

of random prime is considered in the present study. The most effective method to solve the DLP is the Index Calculus Method. In the present study, an efficient way of computing the DLP for ephemeral key by using a new variant of ICM when the factors of