Adil Masood Siddiqui

A locally constrained radial basis function for registration and warping of images

The work in this paper presents a non-rigid registration approach using proposed radial basis function (RBF). The RBF is based on locally constrained cosines. The proposed function is designed to overcome the weaknesses, observed in previous RBFs. The criteria to evaluate the accuracy of transformation functions are also proposed in this paper. Results of the proposed RBF are analyzed and compared with the existing RBFs, based on the proposed evaluation criteria and some other similarity measures. We demonstrate the applicability of proposed approach for registration of medical images and image warping.

Dual-tree complex wavelet transform and SVD based medical image resolution enhancement

Abstract Dual-tree complex wavelet transform, non-local means filter and singular value decomposition based medical image resolution enhancement is proposed. Contrast of the input image is enhanced using proposed singular value decomposition and high frequency subbands are obtained using dual-tree complex wavelet transform. The contrast enhanced low resolution image and high frequency subbands are interpolated using Lanczos interpolator. Non-local means filter is used to cater the artifacts produced by dual-tree complex wavelet transform. Interpolated contrast enhanced low resolution image and filtered high frequency subbands are combined using inverse dual-tree complex wavelet transform to obtain contrast enhanced super resolution image. Quantitative and qualitative analysis is used to justify the significance of the proposed technique.

Image segmentation using multilevel graph cuts and graph development using fuzzy rule-based system

This research work deals with the segmentation of grey scale, colour and texture images using graph-based method. A graph is constructed using intensity, colour and texture profiles of image simultaneously. Based on nature of the image, a fuzzy rule-based system is used to find the weight that should be given to a specific image feature during the graph development. The fuzzy rule-based system provides a valuable approximation to cater the fact of imprecise knowledge (in our case knowledge about the involvement of a particular image feature in image). The graph is further used in multilevel graph-partitioning algorithm based on normalised graph cuts framework where it is iteratively bi-partitioned through normalised cuts to obtain optimum partitions. Multilevel algorithm makes the process fast enough to accommodate large databases as segmentation is often used in high-level image processing-techniques (i.e. object classification and recognition). Partitioned graph then results in segmented image. Berkeley segmentation database is used to experiment on the authors algorithm. The segmentation results are evaluated through probabilistic rand index and global consistency error methods. It is shown that the presented segmentation method provides effective results for most type of images.

Image Dehazing Using Quadtree Decomposition and Entropy-Based Contextual Regularization

In this letter, an improved single image dehazing technique based on quadtree decomposition and entropy-based weighted contextual regularization is proposed. The boundary constraints are computed adaptively using statistical properties of image. The proposed technique produces high-quality dehazed image with better colors and minimal blocking artifacts. Simulation results compared visually and quantitatively with state-of-the-art existing schemes show the significance of proposed technique.

Novel Edge Detection

The purpose of this paper is to develop an algorithm for denoising images corrupted with additive white Gaussian noise (AWGN) with a view to extract objects boundary. The noise degrades quality of the images and makes interpretations, analysis and segmentation of images harder. A pixel is said to be a boundary pixel if its deleted neighborhood contains at least one point from the object and one point from the objects complement. Discrete wavelet transform (DWT) using scale correlation is a denoising approach that reveals boundary pixels more effectively than the simple wavelet decomposition. The detail coefficients in concordant bands are correlated and then synthesized after soft thresholding, which suppresses noise but signifies smooth intensity variations. The wavelet coefficients of noise have much trivial correlation than the wavelet coefficients of boundaries that propagate along the scale. Scale multiplication improves the localization accuracy significantly while keeping high detection efficiency. The combination of noise filtering coupled with boundary detection in a single algorithm enables disconnected boundary detection in a noisy scenario. Curve fitting or cubic spline can then augment the boundaries to estimate missing pixels

A technique for digital watermarking in combined spatial and transform domains using chaotic maps

In this paper, the problems of robustness and quantity of embedded watermark of digital watermarking linked with independent spatial and frequency domains have been analysed. In attempt to overcome these problems to some extent, we have proposed a technique for watermarking in combined spatial and frequency domains based upon chaotic maps. By applying chaos effectively in secure communication, the strength (robustness) of overall anticipated algorithm has been increased to a significant level. In addition, few security statistical analyses such as correlation, entropy, energy, contrast, homogeneity, mean square error and peak signal to noise ratio have also been carried out and it is shown through confidence measure that it can survive against unintentional attacks such as addition of noise, compression and cropping.

Multiclass classification of initial stages of Alzheimer's disease using structural MRI phase images

Alzheimers disease (AD) is the most common type of dementia that is affecting the elderly population worldwide. We present here a novel method based on the progressive two class proximal support vector machine based decision (pTCDC- PSVM) classifier to distinguish between the elderly patients with AD, mild cognitive impairment (MCI) and normal controls (NC). Structural phase images are formed to extract useful features using independent component analysis (ICA) technique which are subsequently used for the classification purposes. The results obtained show the efficacy of our approach and the significant advantages associated with the use of structural magnetic resonance imaging (MRI) phase images in discriminating the early categories of Alzheimers disease.

Sparse representation of image and video using easy path wavelet transform

This paper utilizes a wavelet based image compression technique, Easy Path Wavelet Transform (EPWT), for sparse representation of video. The algorithm has been extended for several aspects including Rigorous EPWT for three dimensional data compression and Relaxed EPWT for cost minimization. The proposed algorithm when applied on sampled frames of a video segment operates along permutations of frame indices exploiting the local correlations efficiently. These arrays of rearranged frame indices, in the case of redundant frames, are then uniquely stored while taking the repetition into consideration. The favorite direction criterion in the encoding process has also been modified to achieve enhanced sparsity for video segments while improving the existing quantitative results for images. The extended EPWT is effective and experimental results are comparable with existing state of the art techniques. Easy Path Wavelet Transform (EPWT), a wavelet based compression technique, is utilized for the sparse representation of video segments.EPWT operates along the permutations of original frame indices exploiting the local correlations in an uncomplicated manner.The comparison of existing techniques with EPWT suggested that EPWT compression requires lesser number of coefficients for reconstruction.The proposed algorithm is implemented on sampled frames such that it results in compression of the entire video segment.

Wavelet based despeckling of multiframe optical coherence tomography data using similarity measure and anisotropic diffusion filtering

We propose a new algorithm for despeckling multiframe Optical Coherence Tomography (OCT) data based on wavelet shrinkage using anisotropic diffusion and similarity comparison between frames. In this algorithm detail coefficients are weighted for noise reduction, where these weights are calculated based on similarity comparison between approximation coefficients. This comparison is based on the assumption that frames have similar structural content while noise is temporally uncorrelated. Approximation coefficients are denoised using Perona Malik anisotropic diffusion. Finally these processed coefficients are averaged to get a denoised image. Experimental results show that the proposed method performs better than the previously formulated denoising algorithms both in terms of noise reduction and structural content preservation.

English to Urdu transliteration: An application of Soundex algorithm

Transliteration algorithms are used to convert Romanized form of Urdu in Urdu script. But the accuracy of such systems is greatly reduced by presence of English words like weak, next etc. in online conversations. In this paper we present dictionary based solution to convert English word to Urdu script. In doing so accent conversion problem may arise that is handled through Soundex based algorithm where relative positions of transcriptions and Urdu language rules are combined to assign codes to English words which are then mapped to Urdu script. We have integrated our work with an existing roman Urdu transliteration system and experimental results have proved the significance of our work both for standalone English transliteration and as a part of roman Urdu transliteration framework.