Ishtiaq Khan

University of Jeddah, Computer science, Undergraduate

Followers

Following

Public Views

Interests

Uploads

Papers by Ishtiaq Khan

A comparative study of medical image enhancement algorithms and quality assessment metrics on COVID-19 CT images

Signal, Image and Video Processing

Medical imaging can help doctors in better diagnosis of several conditions. During the present CO... more Medical imaging can help doctors in better diagnosis of several conditions. During the present COVID-19 pandemic, timely detection of novel coronavirus is crucial, which can help in curing the disease at an early stage. Image enhancement techniques can improve the visual appearance of COVID-19 CT scans and speed-up the process of diagnosis. In this study, we analyze some state-of-the-art image enhancement techniques for their suitability in enhancing the CT scans of COVID-19 patients. Six quantitative metrics, Entropy, SSIM, AMBE, PSNR, EME, and EMEE, are used to evaluate the enhanced images. Two experienced radiologists were involved in the study to evaluate the performance of the enhancement techniques and the quantitative metrics used to assess them.

Download

Unified implementation of global high dynamic range image tone-mapping algorithms

Mathematical Biosciences and Engineering, 2022

High dynamic range (HDR) images and video require tone-mapping for display on low dynamic range (... more High dynamic range (HDR) images and video require tone-mapping for display on low dynamic range (LDR) screens. Many tone-mapping operators have been proposed to convert HDR content to LDR, but almost each has a different implementation structure and requires a different execution time. We propose a unified structure that can represent any global tone-mapping algorithm with an array of just 256 coefficients. These coefficients extracted offline for every HDR image or video frame can be used to convert them to LDR in real time using linear interpolation. The produced LDR images are identical to the images produced by the original implementation of the algorithm. This unified implementation can replicate any global tone-mapping function and requires very low and fixed execution time, which is independent of algorithm and type of content and depends only on image size. Experimental studies are presented to show the accuracy and time efficiency of the proposed implementation.

Real-Time Human-Machine Interaction System Based on Face Authentication and Arm Posture Recognition

Studies in Computational Intelligence, 2010

In this article we present a system for secure human-machine interaction. User verification is do... more In this article we present a system for secure human-machine interaction. User verification is done based on face matching, and commands to machine are delivered by arm gesture. Algorithms used in our system for face matching and arm posture detection get some inspiration from brain visual functions and architecture. Higher complexity modules are implemented in hardware to achieve higher computational

A Mixed Reality Virtual Clothes Try-On System

IEEE Transactions on Multimedia, 2013

Virtual try-on of clothes has received much attention recently due to its commercial potential. I... more Virtual try-on of clothes has received much attention recently due to its commercial potential. It can be used for online shopping or intelligent recommendation to narrow down the selections to a few designs and sizes. In this paper, we present a mixed reality system for 3D virtual clothes try-on that enables a user to see herself wearing virtual clothes while looking at a mirror display, without taking off her actual clothes. The user can select various virtual clothes for trying-on. The system physically simulates the selected virtual clothes on the user's body in real-time and the user can see virtual clothes fitting on the her mirror image from various angles as she moves. The major contribution of this paper is that we automatically customize an invisible (or partially visible) avatar based on the user's body size and the skin color and use it for proper clothes fitting, alignment and clothes simulation in our virtual try-on system. We present three scenarios: i) virtual clothes on the avatar, ii) virtual clothes on the user's image and iii) virtual clothes on the avatar blended with the user's face image. We have conducted a user study to evaluate the effectiveness of these three solutions from the end user's perception of quality attributes, cognitive attributes and attitude towards using. The user study shows that among these three scenarios, the second one is most preferred by the users and for 50% of them the experience they had with our system was sufficient to make the purchase decision for the outfits they virtually tried-on.

Download

Narrow Transition Band FIR Hilbert Transformers With Flat Magnitude Response

IEEE Signal Processing Letters, 2007

MAXIMALLY FLAT (MAXFLAT) finite-impulse response digital filters, including the Hilbert transform... more MAXIMALLY FLAT (MAXFLAT) finite-impulse response digital filters, including the Hilbert transformers (HTs), have the smoothest magnitude responses among the available types of FIR digital filters. However, the transition bands of MAXFLAT filters are relatively wider, and this makes them unattractive in certain applications. We present new designs of even and odd length HTs by transforming a design of digital differentiators satisfying maximal linearity constraints at = 2. The resultant even and odd length HTs have highly smooth magnitude responses around = 2 and = (4 3 4) respectively, and have relatively narrow transition bands compared to the existing MAXFLAT designs.

Download

Finite-Impulse-Response Digital Differentiators for Midband Frequencies Based on Maximal Linearity Constraints

IEEE Transactions on Circuits and Systems II: Express Briefs, 2007

Maximally linear digital differentiators (DDs) are known for high accuracy in narrow frequency ba... more Maximally linear digital differentiators (DDs) are known for high accuracy in narrow frequency bands centered at the frequency for which they are designed. In this paper, designs of DDs of odd and even lengths having maximal linearity at the middle of the frequency band are presented. Applying the maximal linearity constraints to the magnitude response of a differentiator gives a system of linear equations, which can be solved for the impulse response coefficients of the differentiator. It is observed that the coefficient matrices of these equations are Vandermonde matrices, and this helps in finding the solution of the equations in closed form. Design examples are presented to show the accuracy of the presented designs, and it is observed that even-length designs are more accurate in a significantly wider frequency band as compared with odd-length designs.

Download

New finite difference formulas for numerical differentiation

Conventional numerical differentiation formulas based on interpolating polynomials, operators and... more Conventional numerical differentiation formulas based on interpolating polynomials, operators and lozenge diagrams can be simplified to one of the finite difference approximations based on Taylor series, and closed-form expressions of these finite difference formulas have already been presented. In this paper, we present new finite difference formulas, which are more accurate than the available ones, especially for the oscillating functions having frequency components near the Nyquist frequency. Closed-form expressions of the new formulas are given for arbitrary order. A comparison of the previously available three types of approximations is given with the presented formulas. A computer program written in MATHEMATICA, based on new formulas is given in the appendix for numerical di erentiation of a function at a

Download

A non-uniform quantization scheme for visualization of CT images

Mathematical Biosciences and Engineering

Medical science heavily depends on image acquisition and post-processing for accurate diagnosis a... more Medical science heavily depends on image acquisition and post-processing for accurate diagnosis and treatment planning. The introduction of noise degrades the visual quality of the medical images during the capturing process, which may result in false perception. Therefore, medical image enhancement is an essential topic of research for the improvement of image quality. In this paper, a clustering-based contrast enhancement technique is presented for computed tomography (CT) images. Our approach uses the recursive splitting of data into clusters targeting the maximum error reduction in each cluster. This leads to grouping similar pixels in every cluster, maximizing inter-cluster and minimizing intra-cluster similarities. A suitable number of clusters can be chosen to represent high precision data with the desired bit-depth. We use 256 clusters to convert 16-bit CT scans to 8-bit images suitable for visualization on standard low dynamic range displays. We compare our method with several existing contrast enhancement algorithms and show that the proposed technique provides better results in terms of execution efficiency and quality of enhanced images.

Tone-Mapping Using Perceptual-Quantizer and Image Histogram

IEEE Access

A new tone-mapping algorithm is presented for visualization of high dynamic range (HDR) images on... more A new tone-mapping algorithm is presented for visualization of high dynamic range (HDR) images on low dynamic range (LDR) displays. In the first step, the real-world pixel intensities of the HDR image are transformed to a perceptual domain using the perceptual-quantizer (PQ). This is followed by construction of the histogram of the luminance channel. Tone-mapping curve is generated from the cumulative histogram. It is known that histogram-based tone-mapping approaches can lead to excessive stretching of contrast in highly populated bins, whereas the pixels in sparse bins can suffer from excessive compression of contrast. We handle these issues by restricting the pixel counts in the histogram to remain below a defined limit, determined by a uniform distribution model. The proposed method is compared with state-of-the-art algorithms, using some well-known metrics that quantify the quality of tone-mapped images, and is found to have the best performance. INDEX TERMS Image enhancement, high dynamic range imaging, tone-mapping, image visualization.

Download

New nite dierence formulas for numerical dierentiation

Conventional numerical di erentiation formulas based on interpolating polynomials, operators and ... more Conventional numerical di erentiation formulas based on interpolating polynomials, operators and lozenge diagrams can be simpliÿed to one of the ÿnite di erence approximations based on Taylor series, and closed-form expressions of these ÿnite di erence formulas have already been presented. In this paper, we present new ÿnite di erence formulas, which are more accurate than the available ones, especially for the oscillating functions having frequency components near the Nyquist frequency. Closed-form expressions of the new formulas are given for arbitrary order. A comparison of the previously available three types of approximations is given with the presented formulas. A computer program written in MATHEMATICA, based on new formulas is given in the appendix for numerical di erentiation of a function at a speciÿed mesh point.

Download

Maximally linear FIR digital differentiators for midband frequencies

3D Avatar Modeling and Transmission Using Cylinder Mapping

Wseas Transactions on Electronics, Mar 1, 2008

In this paper, we propose a real time 3D imaging system. Existing techniques for construction of ... more In this paper, we propose a real time 3D imaging system. Existing techniques for construction of 3D models require multiple cameras and complex calculations. In our proposed system, the 3D shape is captured by integrating multiple range images obtained simultaneously from different directions. It can accomplish the real time processing by generating the range images quickly and continuously. Moreover, the obtained 3D shape is treated as "Point Cloud", and therefore, the connectivity information of vertices and the calculation of connection topology become unnecessary. Giving importance to transmission efficiency is the advantage of our system. The obtained 3D shape is transmitted to the remote location, and it is reconstructed and depicted immediately. By repeating this procedure continuously, a 3D sequence can be generated in real time. The 3D shape is constructed by integration of multiple range images, causing overlap and annoying artifacts between adjacent images. We apply a cylindrical method to each frame of the 3D sequence to get rid of the artifact and improve the image quality. Our algorithm can remove the invalid points quickly and efficiently, and can be implemented in real time.

Download

A nonlinear quantization scheme for two-layer HDR image encoding

Signal, Image and Video Processing, 2015

Two-layer schemes provide an effective method of encoding high dynamic range images with backward... more Two-layer schemes provide an effective method of encoding high dynamic range images with backward compatibility. The first layer is the tone-mapped low dynamic range version of the original image, used for visualization. The residual information that cannot be preserved in the first layer is stored in the second layer, which itself is generally encoded as an image of a fixed bit-depth. Any further details that cannot be preserved in the second layer are discarded. In this paper, we present a nonlinear quantization algorithm that can significantly enhance the amount of details that can be preserved in the second layer, and therefore improve the encoding efficiency. The proposed technique can be incorporated in any existing two-layer encoding method and leads to significant improvement in their performance.

New Designs of MAXFLAT FIR Halfband Low/High Pass Digital Filters with Narrow Transition Bands

2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings, 2006

MAXFLAT FIR digital filters have smoothest and the most accurate magnitude responses among all th... more MAXFLAT FIR digital filters have smoothest and the most accurate magnitude responses among all the available types of FIR digital filters. However, the transition bands of MAXFLAT filters are relatively wider, and this makes them unattractive in certain applications. Traditionally, low/high pass MAXFLAT FIR filters are designed to satisfy MAXFLAT constraints at ends of the frequency band. In this paper, we present two new designs of halfband low/high pass filters that satisfy these constraints at the middle of the pass and stop bands. The first design is obtained by solving a system of linear equations obtained by applying MAXFLAT constraints to the magnitude response of the filter, while the second design is a transformation of one of our previous designs of maximally linear digital differentiators. Design examples show that the transition bands of the presented designs are narrower as compared to traditional designs. I.

Download

New design of FIR digital differentiators having maximally linearity at middle of the frequency band

IEEE International Symposium on Communications and Information Technology, 2004. ISCIT 2004., 2004

Maximal linear FIR digital differentiators are preferred over others, like minimax designs, for n... more Maximal linear FIR digital differentiators are preferred over others, like minimax designs, for narrow band applications. Most of the existing maximally linear designs achieve maximal linearity at zero frequency, and relatively lower attention has been given to the designs accurate in mid and higher frequency bands. We present a simple design accurate for midband frequencies, by forcing the maximal linearity

Higher degree FIR digital differentiators based on taylor series

The 2004 47th Midwest Symposium on Circuits and Systems, 2004. MWSCAS '04., 2004

... Ishtiaq Rasool Khan', Masahiro Okuda' and Ryoji Ohba2 ... IEEE, vol. 76, no. 3, pp.... more

New designs of frequency selective FIR digital filters

Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03., 2003

Fourier series expansion is used to explore the relationship between the coefficients of halfband... more Fourier series expansion is used to explore the relationship between the coefficients of halfband lowpass and general bandpass FIR digital filters. This relationship is used to derive new designs of band pass/stop and low/high pass MAXFLAT FIR digital filters, from an available design of halfband lowpass MAXFLAT FIR digital filters. The presented designs have explicit formulas for the filter coefficients,

HDR image tone mapping using histogram adjustment adapted to human visual system

2009 7th International Conference on Information, Communications and Signal Processing (ICICS), 2009

Tone-mapping operators are used to produce low dynamic range versions of the high dynamic range i... more Tone-mapping operators are used to produce low dynamic range versions of the high dynamic range images, while preserving as much details as possible. We have proposed a tonemapping operator which is built on an existing histogram adjustment technique. It incorporates certain characteristics of the human visual system, to restrain the problem of extreme contrast enhancement of certain segments and intensive compression of others, associated with histogram equalization based techniques. Test results show significant improvement over traditional histogram adjustment. The proposed method also does quite well compared to the other state of the art tonemapping operators.

Download

Effect of smooth inverse tone-mapping functions on performance of two-layer high dynamic range encoding schemes

Journal of Electronic Imaging, 2015

Abstract. Two-layer schemes provide an effective method of encoding high dynamic range images, wh... more Abstract. Two-layer schemes provide an effective method of encoding high dynamic range images, while maintaining backward compatibility with the legacy JPEG encoding format. The first layer is the tone-mapped low dynamic range version of the original image, whereas the residual information that cannot be preserved in the first layer is stored in the second layer. Additionally, an inverse tone-mapping function can be used which can reduce the information content in the second layer if designed and used carefully. In this research, we investigate the effect of using the inverse functions on the coding efficiency. We show that just by using a smooth function and hence ensuring that extra energy is not induced in the residual data as the result of inverse tone mapping, significant improvement can be expected in the coding efficiency, i.e., more information can be stored at the same bitrates.

Real Time 3D Avatar Transmission using Cylinder Mapping

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07, 2007

In this paper, we propose a client-sever system, which accomplishes acquisition, transmission and... more In this paper, we propose a client-sever system, which accomplishes acquisition, transmission and reconstruction of the 3D shape at a remote location in real time. The server consists of stereo cameras and a PC cluster, in which each PC creates a range image using multiple color images obtained from the stereo cameras connected to it. All PCs on the server side work in synchronization and generate range images in parallel with each other, which are then transmitted to the client as point cloud. On client side, the 3D model is reconstructed using the received point cloud by the point-based rendering method. We propose a cylindrical mapping method, which removes the overlap and annoying artifacts efficiently before the rendering process. All the procedure of generation, transmission, and reconstruction of successive range images is done in real time.

Download

Ishtiaq Khan

Uploads

Papers by Ishtiaq Khan

Log In