Prem Natarajan, PhD

There is an ongoing need to develop image denoising approaches that suppress noise while maintaining edge information. The non-local means (NLM) algorithm, a widely used patch-based method, is a highly effective edge-preserving technique but is sensitive to parameter tuning. We use a variational approach to combine multiple NLM estimates, seeking a solution that balances positivity constraints and gradient penalties against Stein's Unbiased Risk Estimate (SURE). This method greatly reduces… Show more

There is an ongoing need to develop image denoising approaches that suppress noise while maintaining edge information. The non-local means (NLM) algorithm, a widely used patch-based method, is a highly effective edge-preserving technique but is sensitive to parameter tuning. We use a variational approach to combine multiple NLM estimates, seeking a solution that balances positivity constraints and gradient penalties against Stein's Unbiased Risk Estimate (SURE). This method greatly reduces parameter sensitivity and improves denoising performance vs. other NLM variants. Show less

In this paper, we focus on information extraction from optical character recognition (OCR) output. Since the content from OCR inherently has many errors, we present robust algorithms for information extraction from OCR lattices instead of merely looking them up in the top-choice (1-best) OCR output. Specifically, we address the challenge of named entity detection in noisy OCR output and show that searching for named entities in the recognition lattice significantly improves detection accuracy… Show more

In this paper, we focus on information extraction from optical character recognition (OCR) output. Since the content from OCR inherently has many errors, we present robust algorithms for information extraction from OCR lattices instead of merely looking them up in the top-choice (1-best) OCR output. Specifically, we address the challenge of named entity detection in noisy OCR output and show that searching for named entities in the recognition lattice significantly improves detection accuracy over 1-best search. While lattice-based named entity (NE) detection improves NE recall from OCR output, there are two problems with this approach: (1) the number of false alarms can be prohibitive for certain applications and (2) lattice-based search is computationally more expensive than 1-best NE lookup. To mitigate the above challenges, we present techniques for reducing false alarms using confidence measures and for reducing the amount of computation involved in performing the NE search. Furthermore, to demonstrate that our techniques are applicable across multiple domains and languages, we experiment with optical character recognition systems for videotext in English and scanned handwritten text in Arabic. Show less

In this paper, we present a novel approach for incorporating structural information into the hidden Markov modeling (HMM) framework for offline handwriting recognition. Traditionally, structural features have been used in recognition approaches that rely on accurate segmentation of words into smaller units (sub-words or characters). However, such segmentation based approaches do not perform well on real-world handwritten images, because breaks and merges in glyphs typically create new connected… Show more

In this paper, we present a novel approach for incorporating structural information into the hidden Markov modeling (HMM) framework for offline handwriting recognition. Traditionally, structural features have been used in recognition approaches that rely on accurate segmentation of words into smaller units (sub-words or characters). However, such segmentation based approaches do not perform well on real-world handwritten images, because breaks and merges in glyphs typically create new connected components that are not observed in the training data. To mitigate the problem of having to derive accurate segmentation from connected components, we present a novel framework where the HMM based recognition system trained on shorter-span features is used to generate the 2D character images (the ldquostochastic segmentsrdquo), and then another classifier that uses structural features extracted from the stochastic character segments generates a new set of scores. Finally, the scores from the HMM system and from structural matching are used in combination to generate a hypothesis that is better than the results from either the HMM or from structural matching alone. We demonstrate the efficacy of our approach by reporting experimental results on a large corpus of handwritten Arabic documents. Show less

We present a wearable, headset integrated eyes- and hands-free speech-to-speech (S2S) translation system. It employs an n-gram speech recognition engine, a rudimentary phrase-based translator for translating recognized text, and a rudimentary text-to speech (TTS) synthesis engine for playing back the English translation. [Pretty good for 2008, if I do say so myself.]

We present a new approach for analysis of images for text localization and extraction. Our approach puts very few constraints on the font, size and color of text and is capable of handling both scene text and artificial text well. In this paper, we exploit two well-known features of text: approximately constant stroke width and local contrast, and develop a fast, simple, and effective algorithm to detect character strokes. We also show how these can be used for accurate extraction and motivate… Show more

We present a new approach for analysis of images for text localization and extraction. Our approach puts very few constraints on the font, size and color of text and is capable of handling both scene text and artificial text well. In this paper, we exploit two well-known features of text: approximately constant stroke width and local contrast, and develop a fast, simple, and effective algorithm to detect character strokes. We also show how these can be used for accurate extraction and motivate some advantages of using this approach for text localization over other color-space segmentation based approaches. We analyze the performance of our stroke detection algorithm on images col- lected for the robust-reading competitions at ICDAR 2003. Show less

In many applications of topic spotting technology, especially those that require a human review of in-topic documents, a low false alarm rate is a key requirement. Topic spotting techniques typically include a rejection scheme to filter out off-topic documents. In this paper we present a robust methodology for rejecting off-topic messages that, in addition to modeling the topics of interest, uses a so-called alternate model for topics that are not included in the set of topics of interest… Show more

In many applications of topic spotting technology, especially those that require a human review of in-topic documents, a low false alarm rate is a key requirement. Topic spotting techniques typically include a rejection scheme to filter out off-topic documents. In this paper we present a robust methodology for rejecting off-topic messages that, in addition to modeling the topics of interest, uses a so-called alternate model for topics that are not included in the set of topics of interest. Specifically, we introduce two novel techniques for estimating topic-specific rejection thresholds - a parametric technique that can be viewed as transformation of topic-independent thresholds, and a nonparametric technique based on constrained optimization of false rejections subject to a pre-specified number of false acceptances. Our experiments on newsgroup messages demonstrate that when adequate training data is available topic-specific threshold estimation techniques can outperform topic-independent thresholds in terms of the ROC curve. Show less