Feature extraction for fingerprint classification

This paper presents two algorithms for smoothing and feature extraction for fingerprint classification. Deutsch's(2) Thinning algorithm (rectangular array) is used for thinning the digitized fingerprint (binary version). A simple algorithm is also suggested for classifying the fingerprints. Experimental results obtained using such algorithms are presented.

Block-based feature detection and matching for mosaicing of camera-captured document images

In this paper, we present a new feature-based approach for mosaicing of camera-captured document images. A novel block-based scheme is employed to ensure that corners can be reliably detected over a wide range of images. 2-D discrete cosine transform is computed for image blocks defined around each of the detected corners and a small subset of the coefficients is used as a feature vector A 2-pass feature matching is performed to establish point correspondences from which the homography relating the input images could be computed. The algorithm is tested on a number of complex document images casually taken from a hand-held camera yielding convincing results.

Learning Feature Trajectories Using Gabor Filter Bank for Human Activity Segmentation and Recognition

We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, jogging, boxing, hand-waving etc. Since human silhouette can be modeled by a set of rectangles, the elementary human actions can be modeled as a sequence of a set of rectangles with different orientations and scales. The activity segmentation is based on Gabor filter-bank features and normalized spectral clustering. The feature trajectories of an action category are learnt from training example videos using dynamic time warping. The combined segmentation and the recognition processes are very efficient as both the algorithms share the same framework and Gabor features computed for the former can be used for the later. We have also proposed a simple shadow detection technique to extract good silhouette which is necessary for good accuracy of an action recognition technique.

Non-segmented negative sense RNA viruses as vectors for vaccine development

This article intends to cover two aspects of non-segmented negative sense RNA viruses. In the initial section, the strategy employed by these viruses to replicate their genomes is discussed. This would help in understanding the later section in which the use of these viruses as vaccine vectors has been discussed. For the description of the replication strategy which encompasses virus genome transcription and genome replication carried out by the same RNA dependent RNA polymerase complex, a member of the prototype rhabdovirus family - Chandipura virus has been chosen as an example to illustrate the complex nature of the two processes and their regulation. In the discussion on these viruses serving as vectors for carrying vaccine antigen genes, emphasis has been laid on describing the progress made in using the attenuated viruses as vectors and a description of the systems in which the efficiency of immune responses has been tested.

On Guo and Nixon's Criterion for Feature Subset Selection: Assumptions, Implications,and Alternative Options

Guo and Nixon proposed a feature selection method based on maximizing I(x; Y),the multidimensional mutual information between feature vector x and class variable Y. Because computing I(x; Y) can be difficult in practice, Guo and Nixon proposed an approximation of I(x; Y) as the criterion for feature selection. We show that Guo and Nixon's criterion originates from approximating the joint probability distributions in I(x; Y) by second-order product distributions. We remark on the limitations of the approximation and discuss computationally attractive alternatives to compute I(x; Y).

Some experiments on human memory and a new neural model

An associative memory with parallel architecture is presented. The neurons are modelled by perceptrons having only binary, rather than continuous valued input. To store m elements each having n features, m neurons each with n connections are needed. The n features are coded as an n-bit binary vector. The weights of the n connections that store the n features of an element has only two values -1 and 1 corresponding to the absence or presence of a feature. This makes the learning very simple and straightforward. For an input corrupted by binary noise, the associative memory indicates the element that is closest (in terms of Hamming distance) to the noisy input. In the case where the noisy input is equidistant from two or more stored vectors, the associative memory indicates two or more elements simultaneously. From some simple experiments performed on the human memory and also on the associative memory, it can be concluded that the associative memory presented in this paper is in some respect more akin to a human memory than a Hopfield model.

Translational Up-Regulation and High-Level Protein Expression from Plasmid Vectors by mTOR Activation via Different Pathways in PC3 and 293T Cells

Background: Though 293T cells are widely used for expression of proteins from transfected plasmid vectors, the molecular basis for the high-level expression is yet to be understood. We recently identified the prostate carcinoma cell line PC3 to be as efficient as 293T in protein expression. This study was undertaken to decipher the molecular basis of high-level expression in these two cell lines. Methodology/Principal Findings: In a survey of different cell lines for efficient expression of platelet-derived growth factor-B (PDGF-B), beta-galactosidase (beta-gal) and green fluorescent protein (GFP) from plasmid vectors, PC3 was found to express at 5-50-fold higher levels compared to the bone metastatic prostate carcinoma cell line PC3BM and many other cell lines. Further, the efficiency of transfection and level of expression of the reporters in PC3 were comparable to that in 293T. Comparative analyses revealed that the high level expression of the reporters in the two cell lines was due to increased translational efficiency. While phosphatidic acid (PA)-mediated activation of mTOR, as revealed by drastic reduction in reporter expression by n-butanol, primarily contributed to the high level expression in PC3, multiple pathways involving PA, PI3K/Akt and ERK1/2 appear to contribute to the abundant reporter expression in 293T. Thus the extent of translational upregulation attained through the concerted activation of mTOR by multiple pathways in 293T could be achieved through its activation primarily by the PA pathway in PC3. Conclusions/Significance: Our studies reveal that the high-level expression of proteins from plasmid vectors is effected by translational up-regulation through mTOR activation via different signaling pathways in the two cell lines and that PC3 is as efficient as 293T for recombinant protein expression. Further, PC3 offers an advantage in that the level of expression of the protein can be regulated by simple addition of n-butanol to the culture medium.

A Feature-Based Solution to Forward Problem in Electrical Capacitance Tomography of Conductive Materials

A new feature-based technique is introduced to solve the nonlinear forward problem (FP) of the electrical capacitance tomography with the target application of monitoring the metal fill profile in the lost foam casting process. The new technique is based on combining a linear solution to the FP and a correction factor (CF). The CF is estimated using an artificial neural network (ANN) trained using key features extracted from the metal distribution. The CF adjusts the linear solution of the FP to account for the nonlinear effects caused by the shielding effects of the metal. This approach shows promising results and avoids the curse of dimensionality through the use of features and not the actual metal distribution to train the ANN. The ANN is trained using nine features extracted from the metal distributions as input. The expected sensors readings are generated using ANSYS software. The performance of the ANN for the training and testing data was satisfactory, with an average root-mean-square error equal to 2.2%.

Central Limit Theorem for truncated heavy tailed Banach valued random vectors

In this paper the question of the extent to which truncated heavy tailed random vectors, taking values in a Banach space, retain the characteristic features of heavy tailed random vectors, is answered from the point of view of the central limit theorem.

On generating optimal signal probabilities for random tests: A genetic approach

Genetic Algorithms are robust search and optimization techniques. A Genetic Algorithm based approach for determining the optimal input distributions for generating random test vectors is proposed in the paper. A cost function based on the COP testability measure for determining the efficacy of the input distributions is discussed, A brief overview of Genetic Algorithms (GAs) and the specific details of our implementation are described. Experimental results based on ISCAS-85 benchmark circuits are presented. The performance pf our GA-based approach is compared with previous results. While the GA generates more efficient input distributions than the previous methods which are based on gradient descent search, the overheads of the GA in computing the input distributions are larger. To account for the relatively quick convergence of the gradient descent methods, we analyze the landscape of the COP-based cost function. We prove that the cost function is unimodal in the search space. This feature makes the cost function amenable to optimization by gradient-descent techniques as compared to random search methods such as Genetic Algorithms.

Advantage of the ether linkage between the positive charge and the cholesteryl skeleton in cholesterol-based amphiphiles as vectors for gene delivery

Twelve novel cationic cholesterol derivatives with different linkage types between the cationic headgroup and the cholesteryl backbone have been developed. These have been tested for their efficacies as gene transfer agents as mixtures with dioleoyl phosphatidylethanolamine (DOPE). A pronounced improvement in transfection efficiency was observed when the cationic center was linked to the steroid backbone using an ether type bond. Among these, cholest-5-en-3b-oxyethane-N, N,N-trimethylammonium bromide (2a) and cholest-5-en-3b-oxyethane-N, N-dimethyl-N-2-hydroxyethylammonium bromide (3d) showed transfection efficiencies considerably greater than commercially available reagents such as Lipofectin or Lipofectamine. To achieve transfection, 3d did not require DOPE. Increasing hydration at the headgroup level for both ester- and ether-linked amphiphiles resulted in progressive loss of transfection efficiency. Transfection efficiency was also greatly reduced when a 'disorder'-inducing chain like an oleyl (cis-9-octadecenyl) segment was added to these cholesteryl amphiphiles. Importantly, the transfection ability of 2a with DOPE in the presence of serum was significantly greater than for a commercially available reagent, Lipofectamine. This suggests that these novel cholesterol-based amphiphiles might prove promising in applications involving liposome-mediated gene transfection. This investigation demonstrates the importance of structural features at the molecular level for the design of cholesterol-based gene delivery reagents that would aid the development of newer, more efficient formulations based on this class of molecules.

An interesting feature of the vapour pressure curve

There exists a maximum in the products of the saturation properties such as T(p(c) - p) and p(T-c - T) in the vapour-liquid coexistence region for all liquids. The magnitudes of those maxima on the reduced coordinate system provide an insight to the molecular complexity of the liquid. It is shown that the gradients of the vapour pressure curve at temperatures where those maxima occur are directly given by simple relations involving the reduced pressures and temperatures at that point. A linear relation between the maximum values of those products of the form [p(r)(1 - T-r)](max) = 0.2095 - 0.2415 [T-r(1 - p(r))](max) has been found based on a study of 55 liquids ranging from non-polar monatomic cryogenic liquids to polar high boiling point liquids.

Optimal feature extraction for bilingual OCR

Feature extraction in bilingual OCR is handicapped by the increase in the number of classes or characters to be handled. This is evident in the case of Indian languages whose alphabet set is large. It is expected that the complexity of the feature extraction process increases with the number of classes. Though the determination of the best set of features that could be used cannot be ascertained through any quantitative measures, the characteristics of the scripts can help decide on the feature extraction procedure. This paper describes a hierarchical feature extraction scheme for recognition of printed bilingual (Tamil and Roman) text. The scheme divides the combined alphabet set of both the scripts into subsets by the extraction of certain spatial and structural features. Three features viz geometric moments, DCT based features and Wavelet transform based features are extracted from the grouped symbols and a linear transformation is performed on them for the purpose of efficient representation in the feature space. The transformation is obtained by the maximization of certain criterion functions. Three techniques : Principal component analysis, maximization of Fisher's ratio and maximization of divergence measure have been employed to estimate the transformation matrix. It has been observed that the proposed hierarchical scheme allows for easier handling of the alphabets and there is an appreciable rise in the recognition accuracy as a result of the transformations.

An Adaptive Feature Based Low Power Motion Estimation Algorithm

Motion Estimation is one of the most power hungry operations in video coding. While optimal search (eg. full search)methods give best quality, non optimal methods are often used in order to reduce cost and power. Various algorithms have been used in practice that trade off quality vs. complexity. Global elimination is an algorithm based on pixel averaging to reduce complexity of motion search while keeping performance close to that of full search. We propose an adaptive version of the global elimination algorithm that extracts individual macro-block features using Hadamard transform to optimize the search. Performance achieved is close to the full search method and global elimination. Operational complexity and hence power is reduced by 30% to 45% compared to global elimination method.