Systems designed to extract time-critical information from large volumes of unstructured data must include the ability, both from an architectural and algorithmic point of view, to filter out unimportant data that might otherwise overwhelm the available resources. This paper presents an approach for data filtering to reduce computation in the context of a distributed speech processing architecture designed to detect or identify speakers. Here, filtering means either dropping and ignoring data or passing it on for further processing. The goal of the paper is to show that when the filter is designed to select and pass on a subset of the input data that best preserves the ability to recognize a specific desired speaker, or group of speakers, a large percentage of the data can be ignored while being able to preserve most of the accuracy.

This paper presents Content Based Image Retrieval Techniques based on feature vectors in Spatial Domain and Transform Domain. The feature extraction in spatial domain includes the CBIR techniques based on Gaussian Pyramid, Laplacian Pyramid and Steerable Pyramid. The feature extraction in transform

by storing train images in compressed domain and selecting significant features from superset of feature vectors for actual recognition.

This paper explores the use of Support Vector Machines (SVMs) for learning text classifiers from examples. It analyzes the particular properties of learning with text data and identifies, why SVMs are appropriate for this task. Empirical results support the theoretical findings. SVMs achieve

by this semantic criterion we analyze the empirical quality of distributional word feature vectors and its impact on word similarity results, proposing an objective measure for evaluating feature vector quality. Finally, a novel feature weighting and selection function is presented, which yields superior feature

The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special

vector is computed between the local image pattern and the distribution-based model. A trained classifier determines, based on the difference feature vector measurements, whether or not a human face exists at   the current image location. We show empirically that the distance metric we adopt

This work has been performed in collaboration with Simon K.

The goal of this project is to develop computational techniques for analyzing histology images of breast cancer tumors. The computational techniques derive shape and color information from the images and will enable automated evaluation of the tumor. Specifically, the techniques will be used to determine if a patient's breast cancer has spread to nearby lymph nodes by examining a primary tumor that has been excised from the patient. The image analysis capability will obviate the need for exploratory surgical removal of lymph nodes; thus eliminating the associated side effects, e.g. pain, swelling and morbidity, and cost.

A new image feature called Harris feature vector is defined in this paper, which effectively describes the image gradient distribution. By computing the mean and the standard deviation of the Harris feature vector in key point neighborhood, a novel descriptor for key points matching is constructed