Abstract

In order to perform speech summmarization it is necessary to identify important segments in speech signal. The importance of a speech segment can be effectively determined by using infomation from lexical and prosodic features. Standard speech summarization systems depend on ASR transcripts or gold standard human reference summaries to train a supervised system which combines lexical and prosodic features to choose a segment into summary. We propose a method which uses prominence values of syllables in a speech segment to rank the segment for summarization. The proposed method does not depend on ASR transcripts or gold standard human summaries. Evaluation results showed that summaries generated by the proposed method are as good as the summaries generated using tf* idf scores and supervised system trained on gold standard summaries.

Abstract

An important pre-requisite for many tasks like Visual Servoing and visual SLAM is the task of tracking the underlying features. The use of planar features for these purposes has gained importance recently. Complementing current planar tracking works in the robotics literature, which use multiple features, we formulate the tracking problem using multiple planes. Inspired by the maturity in understanding of geometric quantities like the homography in computer vision, we develop a system based on the Unscented Kalman Filter (UKF) that localizes the camera and estimates the plane parameters of a scene, using homographies as measurement. Homographies are estimated using tracked feature points. We show that this framework provides significant robustness and stability to the system under significant changes of illumination, occlusion etc. Finally, we also propose a Convex optimization based solution for the initialization of this system, which is capable of producing globally optimal estimates, and is a useful algorithm in its own right. Several synthetic and real results are presented to demonstrate the efficacy of our approach.

Abstract

Kernel methods yield state-of-the-art performance in certain applications such as image classification and object detection. However, large scale problems require machine learning techniques of at most linear complexity and these are usually limited to linear kernels. This unfortunately rules out gold-standard kernels such as the generalized RBF kernels (e.g. exponential-χ 2 ). Recently, Maji and Berg [13] and Vedaldi and Zisserman [20] proposed explicit feature maps to approximate the additive kernels (intersection, χ 2 , etc.) by linear ones, thus enabling the use of fast machine learning technique in a non-linear context. An analogous technique was proposed by Rahimi and Recht [14] for the translation invariant RBF kernels. In this paper, we complete the construction and combine the two techniques to obtain explicit feature maps for the generalized RBF kernels. Furthermore, we investigate a learning method using l 1 regularization to encourage sparsity in the final vector representation, and thus reduce its dimension. We evaluate this technique on the VOC 2007 detection challenge, showing when it can improve on fast additive kernels, and the trade-offs in complexity and accuracy

Abstract

Most of the Indian scripts do not have any robust commercial OCRs. Many of the laboratory prototypes report reasonable results at recognition/classification stage. However, word level accuracies are still poor. It is well known that word accuracy decreases as the number of characters in a word increase. For Malayalam, the average number of characters in a word is almost twice that of English. Moreover, the number of words required to cover 80% of the Malayalam language is more than forty times that of other Indian languages such as Hindi. Hence a direct dictionary based post-processing scheme is not suitable for Malayalam. In this paper, we propose a post-processing scheme which uses statistical language models at the sub-character level to boost word level recognition results. We use a multi-stage graph representation and formulate the recognition task as an optimization problem. Edges of the graph encode the language information and nodes represent the visual similarities. An optimal path from source node to destination node represents the recognized text. We validate our method on more than 10,000 words from a Malayalam corpus.

Abstract

Conventional optical character recognition (OCR) systems operate on individual characters and words, and do not normally exploit document or collection context. We describe a Collection OCR which takes advantage of the fact that multiple examples of the same word (often in the same font) may occur in a document or collection. The idea here is that an OCR or a reCAPTCHA like process generates a partial set of recognized words. In the second stage, a nearest neighbor algorithm compares the remaining word-images to those already recognized and propagates labels from the nearest neighbors. It is shown that by using an approximate fast nearest neighbor algorithm based on Hierarchical K-Means (HKM), we can do this accurately and efficiently. It is also shown that profile based features perform much better than SIFT and Pyramid Histogram of Gradient (PHOG) features. We believe that this is because profile features are more robust to word degradations (common in our documents). This approach is applied to a collection of Telugu books - a language for which no commercial OCR exists. We show from a selection of 33 Telugu books that starting with OCR labels for only 30% of the collection we can recognize the remaining 70% of the words in the collection with 70% accuracy using this approach. Since the approach makes no language specific assumptions, it should be applicable to a large number of languages. In particular we are interested in its applicability to Indic languages and scripts.

Abstract

We present a scalable and incremental approach for creating interactive image-based walkthroughs from a dynamically growing collection of photographs of a scene. Prior approaches, such as [16], perform a global scene reconstruction as they require the knowledge of all the camera poses. These are recovered via batch processing involving pairwise image matching and structure from motion (Sfm), on collections of photographs. Both steps can become computational bottlenecks for large image collections. Instead of computing a global reconstruction and all the camera poses, our system utilizes several partial reconstructions, each of which is computed from only a small subset of overlapping images. These subsets are efficiently determined using a Bag of Words-based matching technique. Our framework easily allows an incoming stream of new photographs to be incrementally inserted into an existing reconstruction. We demonstrate that an imagebased rendering framework based on only partial scene reconstructions can be used to navigate large collections containing thousands of images without sacrificing the navigation experience. As our system is designed for incremental construction from a stream of photographs, it is well suited for processing the ever-growing photo collections.

Abstract

Optimal control theory is used to design a laser pulse for the multiphoton dissociation of the Fe– CO bond in the CO-heme compounds. The study uses a hexacoordinated iron–porphyrin– imidazole–CO complex in its ground electronic state as a model for CO liganded to the heme group. The potential energy and dipole moment surfaces for the interaction of the CO ligand with the heme group are calculated using density functional theory. Optimal control theory, combined with a timedependent quantum dynamical treatment of the laser-molecule interaction, is then used to design a laser pulse capable of efficiently dissociating the CO-heme complex model. The genetic algorithm method is used within the mathematical framework of optimal control theory to perform the optimization process. This method provides good control over the parameters of the laser pulse, allowing optimized pulses with simple time and frequency structures to be designed. The dependence of photodissociation yield on the choice of initial vibrational state and of initial laser field parameters is also investigated. The current work uses a reduced dimensionality model in which only the Fe–C and C–O stretching coordinates are explicitly taken into account in the timedependent quantum dynamical calculations. The limitations arising from this are discussed in Sec. IV.

Abstract

Structural and electronic properties of diastereomers of tetrahydrofuran amino acids (TAA) derived tripeptide, Boc-TAA-Leu-Val-OMe, are studied using density functional theory. Predicted secondary folding patterns with hydrogen bonded pseudocycles of different sizes in peptides containing (2R,5S)-cis-TAA and (2S,5R)-cis-TAA are confirmed by detailed NMR studies of both, and single crystal X-ray analysis of the former. A novel unusual folding pattern emanating from three-centered hydrogen bond is found in peptide with (2R,5S)-cis relationship. Stereochemical control on the orientation of interacting sites is substantiated by structural analysis of the peptides. Using natural bonding orbital and atoms in molecules analyses, charge transfer interactions are analyzed.

Abstract

Conventionally optimal control theory has been used in the theoretical design of laser pulses through the direct variation in the electric field of the laser pulse as a function of time. This often leads to designed laser pulses which contain a broad and seemingly arbitrary frequency structure that varies in time in a manner which may be difficult to realize experimentally. In contrast, the experimental design of laser pulses has used a genetic algorithm (GA) approach, varying only those laser parameters actually available to the experimentalist. We investigate in this paper the possibility of using GA optimization methods in the theoretical design of laser pulses to bring about quantum state transitions in molecules. This allows us to select only a small limited number of parameters to vary and to choose these parameters so that they correspond to those available to the experimentalist. In the paper we apply our methods to the vibrational-rotational excitation of the HF molecule. We choose a small limited number of frequencies and vary only the associated electric field amplitudes and pulse envelopes. We show that laser pulses designed in this way can lead to very high transition probabilities.

Abstract

IISc Bangalore has developed a recognition engine for Tamil printed text, which has been tested on 1000 document images of pages scanned from books printed between 1950 and 2000. IIIT Hyderabad has developed a XML based annotated database for storing the 5000 images of scanned pages and the corresponding typed text in Unicode. CDAC, Noida has developed an efficient evaluation tool, which compares the OCR output text to the reference typed text (ground truth) and flashes the substitution, deletion and insertion errors in different colours on the screen, so that the design team can quickly identify the issues with the OCR and make corrective steps for improving the performance. IIT Delhi has proposed and developed a novel scheme for segmenting only the text regions from document images containing pictures. The OCRs uses Karhunen-Louve transform (KLT) as features and a support vector machine (SVM) classifier with RBF kernel in a discriminative directed acyclic graph (DDAG) configuration. They assume an uncompressed input image of the document page, scanned at a minimum of 300 dpi with 256 gray levels (not binary or two-level). Tamil OCR currently gives over 94% recognition accuracy at the Unicode level, evaluated on over 1000 printed pages, some of them also containing old Tamil letters.