Rashid Minhas

Human face recognition based on multidimensional PCA and extreme learning machine

In this work, a new human face recognition algorithm based on bidirectional two dimensional principal component analysis (B2DPCA) and extreme learning machine (ELM) is introduced. The proposed method is based on curvelet image decomposition of human faces and a subband that exhibits a maximum standard deviation is dimensionally reduced using an improved dimensionality reduction technique. Discriminative feature sets are generated using B2DPCA to ascertain classification accuracy. Other notable contributions of the proposed work include significant improvements in classification rate, up to hundred folds reduction in training time and minimal dependence on the number of prototypes. Extensive experiments are performed using challenging databases and results are compared against state of the art techniques.

Incremental Learning in Human Action Recognition Based on Snippets

In this paper, we present a systematic framework for recognizing human actions without relying on impractical assumptions, such as processing of an entire video or requiring a large look-ahead of frames to label an incoming video. As a secondary goal, we examine incremental learning as an overlooked obstruction to the implementation of reliable real-time recognition. Assuming weak appearance constancy, the shape of an actor is approximated by adaptively changing intensity histograms to extract pyramid histograms of oriented gradient features. As action progresses, the shape update is carried out by adjustment of a few blocks within a tracking window to closely track evolving contours. The nonlinear dynamics of an action are learned using a recursive analytic approach, which transforms training into a simple linear representation. Such a learning strategy has two advantages: 1) minimized error rates, and significant savings in computational time; and 2) elimination of the widely accepted limitations of batch-mode training for action recognition. The effectiveness of our proposed framework is corroborated by experimental validation against the state of the art.

Shape from focus using fast discrete curvelet transform

A new method for focus measure computation is proposed to reconstruct 3D shape using image sequence acquired under varying focus plane. Adaptive histogram equalization is applied to enhance varying contrast across different image regions for better detection of sharp intensity variations. Fast discrete curvelet transform (FDCT) is employed for enhanced representation of singularities along curves in an input image followed by noise removal using bivariate shrinkage scheme based on locally estimated variance. The FDCT coefficients with high activity are exploited to detect high frequency variations of pixel intensities in a sequence of images. Finally, focus measure is computed utilizing neighborhood support of these coefficients to reconstruct the shape and a well-focused image of the scene being probed.

3D Shape from Focus and Depth Map Computation Using Steerable Filters

The technique utilized to retrieve spatial information from a sequence of images with varying focus plane is termed as shape from focus (SFF). Traditional SFF techniques perform inadequately due to their inability to deal with images that contain high contrast variations between different regions, shadows, defocused points, noise, and oriented edges. A novel technique to compute SFF and depth map is proposed using steerable filters. Steerable filters, designed in quadrature pairs for better control over phase and orientation, have successfully been applied in many image analysis and pattern recognition schemes. Steerable filters represent architecture to synthesize filters of arbitrary orientation using linear combination of basis filters. Such synthesis is used to determine analytically the filter output as a function of orientation. SFF is computed using steerable filters on variety of image sequences. Quantitative and qualitative performance analyses validate enhanced performance of our proposed scheme.

A fast recognition framework based on extreme learning machine using hybrid object information

This paper presents a new supervised learning scheme, which uses hybrid information i.e. global and local object information, for accurate identification and classification at considerably high speed both in training and testing phase. The first contribution of this paper is a unique image representation using bidirectional two-dimensional PCA and Ferns style approach to represent global and local information, respectively, of an object. Secondly, the application of extreme learning machine supports reliable recognition with minimum error and learning speed approximately thousands of times faster than traditional neural networks. The proposed method is capable of classifying various datasets in a fraction of second compared to other modern algorithms that require at least 2-3s per image [14].

An Efficient Algorithm for Focus Measure Computation in Constant Time

This letter presents an efficient algorithm for focus measure computation, in constant time, to estimate depth map using image sequences acquired at varying focus. Two major factors that complicate focus measure computation include neighborhood support and gradient detection for oriented intensity variations. We present a distinct focus measure based on steerable filters that is invariant to neighborhood size and accomplishes fast depth map estimation at a considerably faster speed compared to other well-documented methods. Steerable filters represent architecture to synthesize filters of arbitrary orientation using a linear combination of basis filters. Such synthesis is helpful to analytically determine the filter output as a function of orientation. Steerable filters remove inherent limitations of traditional gradient detection techniques which perform inadequately for oriented intensity variations and low textured regions.

An efficient fingerprint image compression technique based on wave atoms decomposition and multistage vector quantization

Modern fingerprint image compression and reconstruction standards used by the US Federal Bureau of Investigation (FBI) are based upon the popular biorthogonal 9-7 discrete wavelet transform. Multiresolution analysis tools have been successfully applied to fingerprint image compression for more than a decade; we propose a novel fingerprint image compression technique based on wave atoms decomposition and multistage vector quantization. Wave atoms decomposition has been specifically designed for enhanced representation of oscillatory patterns and to convey precise temporal and spatial information. Our proposed compression scheme is based upon multistage vector quantization of processed wave atoms representation of fingerprint images. Wave atoms expansion is processed using mathematical morphological operators to emphasize and retain significant coefficients for transmission. Quantized information is encoded using arithmetic entropy scheme. The proposed image compression standard outperforms other well established methods and achieves PSNR gain up to 8.07 dB in comparison to FBIs wavelet scalar quantization. Data mining, law enforcement, border security, and forensic applications can potentially benefit from our compression scheme.

Invariant feature set in convex hull for fast image registration

In this paper, a novel feature set in images for registration is identified. Unique, geometrically invariant and easily extractable features in images called convex diagonal, convex quadrilateral are used for accurate image registration. Convex diagonals, convex quadrilaterals have attractive properties like easy extraction, geometric invariance and frequent occurrence. Coordinates, length and orientation information of corresponding convex diagonals in different images is used for initial transformation estimate. Corresponding convex hulls of scene objects are matched using Hausdorff distance as similarity measure operator. Coarse level estimate facilitates efficient, real time computation for final registration process. Initial transformation estimate based on convex diagonals, extracted from convex hull of scene objects, is refined using fine level image details to minimize errors originating from quantization and same convex hull information for different object shapes. The behavior of reference quadrilateral is robust against noise, outliers and broken edges.

Depth map estimation using exponentially decaying focus measure based on SUSAN operator

This paper presents a novel technique for depth map estimation using a sequence of images acquired at varying focus. In depth map estimation noise, illumination variations and types of extracted features significantly affect the performance of a focus measure. This paper proposes the use of SUSAN operator, to extract features, because of its structure preserving noise filtering which plays a pivotal role in depth estimation of a scene. We introduce a new focus measure based on exponentially decaying function to use neighborhood information of an extracted feature point that assigns more weight to the closer pixel points. Experiments validate superior performance of our proposed algorithm in comparison to other well-documented methods.

A Novel Technique for Human Face Recognition Using Nonlinear Curvelet Feature Subspace

This paper proposes a novel human face recognition system using curvelet transform and Kernel based principal component analysis. Traditionally multiresolution analysis tools namely wavelets and curvelets have been used in the past for extracting and analyzing still images for recognition and classification tasks. Curvelet transform has gained significant popularity over wavelet based techniques due to its improved directional and edge representation capability. In the past features extracted from curvelet subbands were dimensionally reduced using principal component analysis for obtaining an enhanced representative feature set. In this work we propose to use an improved scheme using kernel based principal component analysis (KPCA) for a comprehensive feature set generation. KPCA performs a nonlinear principal component analysis (PCA) using an integral kernel operator function and obtains features that are more meaningful than the ones extracted using a linear PCA. Extensive experiments were performed on a comprehensive database of face images and superior performance of KPCA based human face recognition in comparison with state-of-the-art recognition is established.