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.

Feature - No pain, no gain: Pleasure and suffering in technologies of leidenschaft

Training for bodybuilding competition is clearly a serious business that inflicts serious demands on the competitor. Not only did Francis commit time and money to compete, but he also arguably put winning before his physical well-being—enduring pain and suffering from his injury. Bodybuilding may seem like an extreme example, but it is not the only activity in which people suffer in pursuit of their goals. Boxers fight each other in the ring; soccer players risk knee and ankle injuries, sometimes playing despite being hurt; and mountaineers risk their lives in dangerous climbs. In the arts there are many examples of people suffering to achieve their goals: Beethoven kept composing, conducting, and performing despite his hearing loss; van Gogh grappled with depression but kept painting, finding fame only posthumously; and Mozart lived the final years of his life impoverished but still composing. These examples show that many great achievements come at a price: severe suffering...

Evolution of Grain-Boundary Microstructure and Texture in Interstitial-Free Steel Processed by Equal-Channel Angular Extrusion

The equal-channel angular extrusion (ECAE) of Ti-bearing interstitial-free (IF) steel was performed following two different routes, up to four passes, at a temperature of 300 degrees C. The ECAE led to a grain refinement to submicron size. After the second pass, the grain size attained saturation thereafter. The microstructural analysis indicated the presence of coincident-site lattice (CSL) boundaries in significant fraction, in addition to a high volume fraction of high-angle random boundaries and some low-angle boundaries after the deformation. Among the special boundaries, Sigma 3 and Sigma 13 were the most prominent ones and their fraction depended on the processing route followed. A deviation in the misorientation angle distribution from the Mackenzie distribution was noticed. The crystallographic texture after the first pass resembled that of simple shear, with the {112}, {110}, and {123} aligned to the macroscopic shear plane.

Effect of the method of preparation and pretreatment on the texture of alumina and related catalysts

The effect of the method of preparation and pretreatment on catalyst texture was investigated in the case of alumina, silica-alumina, 10 × molecular sieve and thoria catalysts. All the catalysts were characterised with respect to their specific surface area, surface acidity, pore size distribution and pore volume. The above properties were found to reflect the textural changes that might have been undergone by the catalyst surface as a result of the method of preparation and pretreatment. The method of preparation was found to influence markedly the acidity of the surface and to a lesser extent the surface area and pore size distribution. Acid-treatment was found to increase selectively the acidity of the catalyst while heat-treatment was found to decrease proportionally the acidity as well as surface area of the catalyst.

vSpeak: Edge detection based feature extraction for sign to text conversion

This paper presents 'vSpeak', the first initiative taken in Pakistan for ICT enabled conversion of dynamic Sign Urdu gestures into natural language sentences. To realize this, vSpeak has adopted a novel approach for feature extraction using edge detection and image compression which gives input to the Artificial Neural Network that recognizes the gesture. This technique caters for the blurred images as well. The training and testing is currently being performed on a dataset of 200 patterns of 20 words from Sign Urdu with target accuracy of 90% and above.

Analysis of microstructure and texture evolution in pure magnesium during symmetric and asymmetric rolling

Asymmetric rolling of commercially pure magnesium was carried out at three different temperatures: room temperature, 200 degrees C and 350 degrees C. Systematic analysis of microstructures, grain size distributions, texture and misorientation distributions were performed using electron backscattered diffraction in a field emission gun scanning electron microscope. The results were compared with conventional (symmetric) rolling carried out under the same conditions of temperature and strain rate. Simulations of deformation texture evolution were performed using the viscoplastic self-consistent polycrystal plasticity model. The main trends of texture evolution are faithfully reproduced by the simulations for the tests at room temperature. The deviations that appear for the textures obtained at high temperature can be explained by the occurrence of dynamic recrystallization. Finally, the mechanisms of texture evolution in magnesium during asymmetric and symmetric rolling are explained with the help of ideal orientations, grain velocity fields and divergence maps displayed in orientation space.

Automated feature engineering for HTTP tunnel detection

Generating discriminative input features is a key requirement for achieving highly accurate classifiers. The process of generating features from raw data is known as feature engineering and it can take significant manual effort. In this paper we propose automated feature engineering to derive a suite of additional features from a given set of basic features with the aim of both improving classifier accuracy through discriminative features, and to assist data scientists through automation. Our implementation is specific to HTTP computer network traffic. To measure the effectiveness of our proposal, we compare the performance of a supervised machine learning classifier built with automated feature engineering versus one using human-guided features. The classifier addresses a problem in computer network security, namely the detection of HTTP tunnels. We use Bro to process network traffic into base features and then apply automated feature engineering to calculate a larger set of derived features. The derived features are calculated without favour to any base feature and include entropy, length and N-grams for all string features, and counts and averages over time for all numeric features. Feature selection is then used to find the most relevant subset of these features. Testing showed that both classifiers achieved a detection rate above 99.93% at a false positive rate below 0.01%. For our datasets, we conclude that automated feature engineering can provide the advantages of increasing classifier development speed and reducing development technical difficulties through the removal of manual feature engineering. These are achieved while also maintaining classification accuracy.

Tailoring texture of γ-Y2Si2O7 by strong magnetic field alignment and two-step sintering

In this study, a well-dispersed γ-Y2Si2O 7 ethanol-based suspension with 30 vol% solid loading was prepared by adding 1 dwb% polyethylene imine dispersant, which allows feeble magnetic γ-Y2Si2O7 particles with anisotropic magnetic susceptibility to rotate in a 12 T strong magnetic field during slip casting, resulting in the development of a strong texture in green bodies. Pressureless sintering gives rise to more pronounced grain growth in the textured sample than in the untextured sample prepared without the magnetic field due to the rapid migration of the grain boundaries of the well-oriented grains, which was revealed by constant-heating-rate sintering kinetics. It was found that the use of two-step sintering is very efficient not only for inhibiting the grain growth but also for enhancing the texture. This implies that controlled grain growth is crucial for enhancing texture development in γ-Y2Si2O7.

Influence of roughness parameters and surface texture on friction during sliding of pure lead over 080 M40 steel

In the present investigation, tests were conducted on a tribological couple made of cylindrical lead pin with spherical tip against 080 M40 steel plates of different textures with varying roughness under both dry and lubricated conditions using an inclined pin-on-plate sliding tester. Surface roughness parameters of the steel plates were measured using optical profilometer. The morphologies of the worn surfaces of the pins and the formation of transfer layer on the counter surfaces were observed using a scanning electron microscope. It was observed that the coefficient of friction and the formation of transfer layer depend primarily on the surface texture of hard surfaces. A newly formulated non-dimensional hybrid roughness parameter called 'xi' (a product of number of peaks and maximum profile peak height) of the tool surface plays an important role in determining the frictional behaviour of the surfaces studied. The effect of surfaces texture on coefficient of friction was attributed to the variation of plowing component of friction, which in turn depends on the roughness parameter 'xi'.

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.

Influence of surface texture and roughness parameters on friction and transfer layer formation during sliding of aluminium pin on steel plate

Surface texture of harder mating surfaces plays an important role during sliding against softer materials and hence the importance of characterizing the surfaces in terms of roughness parameters. In the present investigation, basic studies were conducted using inclined pin-on-plate sliding tester to understand the surface texture effect of hard surfaces on coefficient of friction and transfer layer formation. A tribological couple made of a super purity aluminium pin against steel plate was used in the tests. Two surface parameters of steel plates, namely roughness and texture, were varied in the tests. It was observed that the transfer layer formation and the coefficient of friction along with its two components, namely, the adhesion and plowing, are controlled by the surface texture and are independent of surface roughness (R-a). Among the various surface roughness parameters, the average or the mean slope of the profile was found to explain the variations best. Under lubricated conditions, stick-slip phenomena was observed, the amplitude of which depends on the plowing component of friction. The presence of stick-slip motion under lubricated conditions could be attributed to the molecular deformation of the lubricant component confined between asperities. (C) 2009 Elsevier B. V. All rights reserved.

Automatic Road Extraction using High Resolution Satellite Image Based on Texture Progressive Analysis and Normalized Cut Method

In this paper the approach for automatic road extraction for an urban region using structural, spectral and geometric characteristics of roads has been presented. Roads have been extracted based on two levels: Pre-processing and road extraction methods. Initially, the image is pre-processed to improve the tolerance by reducing the clutter (that mostly represents the buildings, parking lots, vegetation regions and other open spaces). The road segments are then extracted using Texture Progressive Analysis (TPA) and Normalized cut algorithm. The TPA technique uses binary segmentation based on three levels of texture statistical evaluation to extract road segments where as, Normalizedcut method for road extraction is a graph based method that generates optimal partition of road segments. The performance evaluation (quality measures) for road extraction using TPA and normalized cut method is compared. Thus the experimental result show that normalized cut method is efficient in extracting road segments in urban region from high resolution satellite image.

Efficient content-based image retrieval based on multi-feature fusion

The increased availability of image capturing devices has enabled collections of digital images to rapidly expand in both size and diversity. This has created a constantly growing need for efficient and effective image browsing, searching, and retrieval tools. Pseudo-relevance feedback (PRF) has proven to be an effective mechanism for improving retrieval accuracy. An original, simple yet effective rank-based PRF mechanism (RB-PRF) that takes into account the initial rank order of each image to improve retrieval accuracy is proposed. This RB-PRF mechanism innovates by making use of binary image signatures to improve retrieval precision by promoting images similar to highly ranked images and demoting images similar to lower ranked images. Empirical evaluations based on standard benchmarks, namely Wang, Oliva & Torralba, and Corel datasets demonstrate the effectiveness of the proposed RB-PRF mechanism in image retrieval.

A model based factorization approach for dense 3D recovery from monocular video

Feature track matrix factorization based methods have been attractive solutions to the Structure-front-motion (Sfnl) problem. Group motion of the feature points is analyzed to get the 3D information. It is well known that the factorization formulations give rise to rank deficient system of equations. Even when enough constraints exist, the extracted models are sparse due the unavailability of pixel level tracks. Pixel level tracking of 3D surfaces is a difficult problem, particularly when the surface has very little texture as in a human face. Only sparsely located feature points can be tracked and tracking error arc inevitable along rotating lose texture surfaces. However, the 3D models of an object class lie in a subspace of the set of all possible 3D models. We propose a novel solution to the Structure-from-motion problem which utilizes the high-resolution 3D obtained from range scanner to compute a basis for this desired subspace. Adding subspace constraints during factorization also facilitates removal of tracking noise which causes distortions outside the subspace. We demonstrate the effectiveness of our formulation by extracting dense 3D structure of a human face and comparing it with a well known Structure-front-motion algorithm due to Brand.