Arif Mahmood
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Arif Mahmood has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Ajmal Mian
The University of Western Australia
4 shared publications Muhammad Uzair
3 shared publicationsChris McDonald
2 shared publications- Du. Q. Huynh
The University of Western Australia
2 shared publications - Hossein Rahmani
Lancaster University
2 shared publications - M. Shahid Farid
University of the Punjab
2 shared publications
Latest Publications
- 1 February 2015
- Published by Elsevier in Neurocomputing
- Vol. 149, 854-867
Periocular region-based person identification in the visible, infrared and hyperspectral imagery
- 1 February 2015
- Published by Elsevier in Neurocomputing
- Vol. 149, 854-867
Periocular region-based person identification in the visible, infrared and hyperspectral imagery
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505790,p. 626-633
Real time action recognition using histograms of depth gradients and random decision forests
We propose an algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal variations of depth and depth gradients at a specific space-time location in the action volume. Moreover, we encode the dominant skeleton movements by computing a local 3D joint position difference histogram. For each joint, we compute a 3D space-time motion volume which we use as an importance indicator and incorporate in the feature vector for improved action discrimination. To retain only the discriminant features, we train a random decision forest (RDF). The proposed algorithm is evaluated on three standard datasets and compared with nine state-of-the-art algorithms. Experimental results show that, on the average, the proposed algorithm outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second.
- 1 March 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505790,p. 626-633
Real time action recognition using histograms of depth gradients and random decision forests
We propose an algorithm which combines the discriminative information from depth images as well as from 3D joint positions to achieve high action recognition accuracy. To avoid the suppression of subtle discriminative information and also to handle local occlusions, we compute a vector of many independent local features. Each feature encodes spatiotemporal variations of depth and depth gradients at a specific space-time location in the action volume. Moreover, we encode the dominant skeleton movements by computing a local 3D joint position difference histogram. For each joint, we compute a 3D space-time motion volume which we use as an importance indicator and incorporate in the feature vector for improved action discrimination. To retain only the discriminant features, we train a random decision forest (RDF). The proposed algorithm is evaluated on three standard datasets and compared with nine state-of-the-art algorithms. Experimental results show that, on the average, the proposed algorithm outperform all other algorithms in accuracy and have a processing speed of over 112 frames/second.
- 1 January 2014
- Published by Springer Nature
- p. 742-757
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition
- 1 January 2014
- Published by Springer Nature
- p. 742-757
HOPC: Histogram of Oriented Principal Components of 3D Pointclouds for Action Recognition
- 1 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
A compact discriminative representation for efficient image-set classification with application to biometric recognition
We present a simple yet compact and discriminative representation for image sets which can efficiently be used for image-set based object classification. For each image-set we compute a global covariance matrix which captures correlated variations in all image-set dimensions. Without loss of information, we compact the covariance matrix into a lower triangular matrix by using Cholesky decomposition. While preserving discrimination capability of the representation, we obtain further compression by applying Multiple Discriminant Analysis. As a result, we are able to represent image sets containing N samples each of dimensionality d by a single vector whose dimensionality is ≪ N d. We apply the proposed representation to various biometric applications such as image-set based face recognition and person identification using image-sets of periocular regions. To show that our representation is generic, we also report results for image-set based object categorization. We observe improved accuracy and significant speedup over the current state-of-the-art techniques on standard datasets.
- 1 June 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
A compact discriminative representation for efficient image-set classification with application to biometric recognition
We present a simple yet compact and discriminative representation for image sets which can efficiently be used for image-set based object classification. For each image-set we compute a global covariance matrix which captures correlated variations in all image-set dimensions. Without loss of information, we compact the covariance matrix into a lower triangular matrix by using Cholesky decomposition. While preserving discrimination capability of the representation, we obtain further compression by applying Multiple Discriminant Analysis. As a result, we are able to represent image sets containing N samples each of dimensionality d by a single vector whose dimensionality is ≪ N d. We apply the proposed representation to various biometric applications such as image-set based face recognition and person identification using image-sets of periocular regions. To show that our representation is generic, we also report results for image-set based object categorization. We observe improved accuracy and significant speedup over the current state-of-the-art techniques on standard datasets.
- 1 January 2013
- Published by British Machine Vision Association and Society for Pattern Recognition
- p. 57.1-57.11
Hyperspectral Face Recognition using 3D-DCT and Partial Least Squares
BMVC 2013 - Homepage of the 24th British Machine Vision Conference, Bristol (UK), 9-13 Sept 2013
- 1 January 2013
- Published by British Machine Vision Association and Society for Pattern Recognition
- p. 57.1-57.11
Hyperspectral Face Recognition using 3D-DCT and Partial Least Squares
BMVC 2013 - Homepage of the 24th British Machine Vision Conference, Bristol (UK), 9-13 Sept 2013
- 30 November 2012
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 71 (3) , 1699-1716
An image composition algorithm for handling global visual effects
- 30 November 2012
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 71 (3) , 1699-1716
An image composition algorithm for handling global visual effects
- 13 October 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 21 (4) , 2099-2108
Correlation-Coefficient-Based Fast Template Matching Through Partial Elimination
Partial computation elimination techniques are often used for fast template matching. At a particular search location, computations are prematurely terminated as soon as it is found that this location cannot compete with an already known best match location. Due to the nonmonotonic growth pattern of the correlation-based similarity measures, partial computation elimination techniques have been traditionally considered inapplicable to speed up these measures. In this paper, we show that partial elimination techniques may be applied to a correlation coefficient by using a monotonic formulation, and we propose basic-mode and extended-mode partial correlation elimination algorithms for fast template matching. The basic-mode algorithm is more efficient on small template sizes, whereas the extended mode is faster on medium and larger templates. We also propose a strategy to decide which algorithm to use for a given data set. To achieve a high speedup, elimination algorithms require an initial guess of the peak correlation value. We propose two initialization schemes including a coarse-to-fine scheme for larger templates and a two-stage technique for small- and medium-sized templates. Our proposed algorithms are exact, i.e., having exhaustive equivalent accuracy, and are compared with the existing fast techniques using real image data sets on a wide variety of template sizes. While the actual speedups are data dependent, in most cases, our proposed algorithms have been found to be significantly faster than the other algorithms.
- 13 October 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 21 (4) , 2099-2108
Correlation-Coefficient-Based Fast Template Matching Through Partial Elimination
Partial computation elimination techniques are often used for fast template matching. At a particular search location, computations are prematurely terminated as soon as it is found that this location cannot compete with an already known best match location. Due to the nonmonotonic growth pattern of the correlation-based similarity measures, partial computation elimination techniques have been traditionally considered inapplicable to speed up these measures. In this paper, we show that partial elimination techniques may be applied to a correlation coefficient by using a monotonic formulation, and we propose basic-mode and extended-mode partial correlation elimination algorithms for fast template matching. The basic-mode algorithm is more efficient on small template sizes, whereas the extended mode is faster on medium and larger templates. We also propose a strategy to decide which algorithm to use for a given data set. To achieve a high speedup, elimination algorithms require an initial guess of the peak correlation value. We propose two initialization schemes including a coarse-to-fine scheme for larger templates and a two-stage technique for small- and medium-sized templates. Our proposed algorithms are exact, i.e., having exhaustive equivalent accuracy, and are compared with the existing fast techniques using real image data sets on a wide variety of template sizes. While the actual speedups are data dependent, in most cases, our proposed algorithms have been found to be significantly faster than the other algorithms.
- 24 March 2011
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 42 (1) , 50-63
Image Morphing in Frequency Domain
- 24 March 2011
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 42 (1) , 50-63
Image Morphing in Frequency Domain
- 1 October 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 10 (21645221) , 711-715
Image inpainting based on pyramids
Image inpainting is a technique used to automatically recover the damaged or missing regions in digital images or used to remove the unwanted objects from images. This paper presents a novel approach for recovering the damaged regions of digital images based on pyramids. The idea is to generate the pyramids of the image to the level where all the damaged pixels are fully eliminated. Then the damaged pixels are filled in from the bottom pyramid to the top. In pyramid image at level i, the damaged pixels are filled in from the EXPANDED pyramid image at level i -1, and so on up to the level 0 pyramid. The proposed technique has been tested over a large verity of images and shown excellent results to restore small damaged regions and satisfactory results for large damaged regions.
- 1 October 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 10 (21645221) , 711-715
Image inpainting based on pyramids
Image inpainting is a technique used to automatically recover the damaged or missing regions in digital images or used to remove the unwanted objects from images. This paper presents a novel approach for recovering the damaged regions of digital images based on pyramids. The idea is to generate the pyramids of the image to the level where all the damaged pixels are fully eliminated. Then the damaged pixels are filled in from the bottom pyramid to the top. In pyramid image at level i, the damaged pixels are filled in from the EXPANDED pyramid image at level i -1, and so on up to the level 0 pyramid. The proposed technique has been tested over a large verity of images and shown excellent results to restore small damaged regions and satisfactory results for large damaged regions.
- 1 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 1209-1212
Early terminating algorithms for Adaboost based detectors
In this paper we propose an early termination algorithm for speeding up the detection phase of the Adaboost based detectors. In the basic algorithm, at a specific search location, the AdaBoost ensemble response is computed as monotonic decreasing function of weak learners. As more weak learners are evaluated, the response either decreases or remains the same. As soon as the current response becomes lower than the AdaBoost global threshold, remaining computations may be skipped without any loss of accuracy. We further extend the basic algorithm by integrating it with the Non Maxima Suppression (NMS) process. Any candidate location may be discarded, as soon as its current response becomes lower than another candidate location, within the same non-maxima suppression window. In our experiments, our proposed algorithm has been found to be an order of magnitude faster than the traditionally used AdaBoost detector, for the application of edge-corner detection. Speedup comparisons are also done with other three well known edge corner detectors. The early terminated AdaBoost detector has been found to be significantly faster than all three of these detectors.
- 1 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 1209-1212
Early terminating algorithms for Adaboost based detectors
In this paper we propose an early termination algorithm for speeding up the detection phase of the Adaboost based detectors. In the basic algorithm, at a specific search location, the AdaBoost ensemble response is computed as monotonic decreasing function of weak learners. As more weak learners are evaluated, the response either decreases or remains the same. As soon as the current response becomes lower than the AdaBoost global threshold, remaining computations may be skipped without any loss of accuracy. We further extend the basic algorithm by integrating it with the Non Maxima Suppression (NMS) process. Any candidate location may be discarded, as soon as its current response becomes lower than another candidate location, within the same non-maxima suppression window. In our experiments, our proposed algorithm has been found to be an order of magnitude faster than the traditionally used AdaBoost detector, for the application of edge-corner detection. Speedup comparisons are also done with other three well known edge corner detectors. The early terminated AdaBoost detector has been found to be significantly faster than all three of these detectors.