Zahid Mahmood

Blind data hiding technique using the Fresnelet transform.

AbstractA new blind data hiding scheme is proposed in which data is decomposed using the Fresnelet transform. The inverse Fresnelet transform is performed on decomposed subbands by choosing different key parameters, and the coded pattern of the information data is obtained. This coded pattern is embedded into particular subbands of the cover image using the wavelets. The proposed method has good imperceptibility and large capacity of the information embedded data. Using the Fresnelet transform with a family of wavelet transforms makes the scheme more efficient in terms of extracted accuracy of hidden information. Moreover, the hidden data can be recovered without access to the original cover data. The proposed method is used to resolve privacy and security issues raised with respect to emerging internet applications for the effective handling of confidential data.

Automatic player detection and recognition in images using AdaBoost

In this work we developed an augmented reality sports broadcasting application for enhanced end-user experience. The proposed system consists of three major steps. In the first step each player is detected using AdaBoost Algorithm. In second step, same algorithm is used to detect face in each player image. In third step, a robust face recognition algorithm is applied to match face of each player with an online database of players face images which also stores statistics of each player. The application can be used to show the users the statistics of players captured in still image using camera or smart phone. Useful statistics can be name of the player, height, age, sports record etc in specific game. For player and subsequent face detection we use Haar-like features and AdaBoost algorithm for both feature selection and classification. The employed face recognition system uses AdaBoost algorithm with Liner Discriminant Analysis as a week learner for feature selection in LDA subspace while classification is performed using a classic nearest center classifier. Detailed experimental results are shown on general player face database as well as on real baseball game images containing different number of players at various poses and lighting conditions.

Reversible integer wavelet transform for blind image hiding method

In this article, a blind data hiding reversible methodology to embed the secret data for hiding purpose into cover image is proposed. The key advantage of this research work is to resolve the privacy and secrecy issues raised during the data transmission over the internet. Firstly, data is decomposed into sub-bands using the integer wavelets. For decomposition, the Fresnelet transform is utilized which encrypts the secret data by choosing a unique key parameter to construct a dummy pattern. The dummy pattern is then embedded into an approximated sub-band of the cover image. Our proposed method reveals high-capacity and great imperceptibility of the secret embedded data. With the utilization of family of integer wavelets, the proposed novel approach becomes more efficient for hiding and retrieving process. It retrieved the secret hidden data from the embedded data blindly, without the requirement of original cover image.

A REVIEW ON STATE-OF-THE-ART FACE RECOGNITION APPROACHES

Automatic Face Recognition (FR) presents a challenging task in the field of pattern recognition and despite the huge research in the past several decades; it still remains an open research problem. This is primarily due to the variability in the facial images, such as non-uniform illuminations, low resolution, occlusion, and/or variation in poses. Due to its non-intrusive nature, the FR is an attractive biometric modality and has gained a lot of attention in the biometric research community. Driven by the enormous number of potential application domains, many algorithms have been proposed for the FR. This paper presents an overview of the state-of-the-art FR algorithms, focusing their performances on publicly available databases. We highlight the conditions of the image databases with regard to the recognition rate of each approach. This is useful as a quick research overview and for practitioners as well to choose an algorithm for their specified FR application. To provide a comprehensive survey, the paper divides the FR algorithms into three categories: (1) intensity-based, (2) video-based, and (3) 3D based FR algorithms. In each category, the most commonly used algorithms and their performance is reported on standard face databases and a brief critical discussion is carried out.

Automatic player detection and identification for sports entertainment applications

In this paper, we develop an augmented reality sports broadcasting application for automatic detection, recognition of players during play, followed by display of personal information of players. The proposed application can be divided into four major steps. In first step, each player in the image is detected. In the second step, a face detection algorithm detects face of each player. In third step, we use a face recognition algorithm to match the faces of players with a database of players’ faces which also stores personal information of each player. In step four, personal information of each player is retrieved based on the face matching result. This application can be used to show the viewers’ information about players such as name of the player, sports record, age, highest score, and country of belonging. We develop this system for baseball game, however, it can be deployed in any sports where the audience can take a live video or images using smart phones. For the task of player and subsequent face detection, we use AdaBoost algorithm with haar-like features for both feature selection and classification while player face recognition system uses AdaBoost algorithm with linear discriminant analysis for feature selection and nearest neighbor classifier for classification. Detailed experiments are performed using 412 diverse images taken using a digital camera during baseball match. These images contain players in different sizes, facial expressions, lighting conditions and pose. The player and face detection accuracy is high in all situations, however, the face recognition module requires detected players’ faces to be frontal or near frontal. In general, restricting the head rotation to ±30° gives a high accuracy of overall system

Digital watermarking using Hall property image decomposition method

AbstractMost of the existing singular value decomposition-based digital watermarking methods are not robust to geometric rotation, which change the pixels’ locations without maintaining the corresponding changes to the pixel’s intensity values of entire image and yield high computational cost. To answer this, we propose a digital image watermarking algorithm using the Hall property. In the proposed method, a digital watermark image is factorized into lower-triangular, upper-triangular, and permutation matrices. The permutation matrix is used as the valid key matrix for authentication of the rightful ownership of the watermark image. The product of the lower and upper triangular matrices is processed with a few iterations of the Arnold transformation to obtain the scrambled data. The scrambled data are embedded into particular sub-bands of a cover image using Wavelet transform. Our experiments show that the proposed algorithm is highly reliable and computationally efficient compared with state-of-the-art methods that are based on singular value decomposition.

Image de-noising with subband replacement and fusion process using bayes estimators, ☆ ☆☆

Abstract A hybrid image de-noising framework with an automatic parameter selection scheme is proposed to handle substantially high noise with an unknown variance. The impetus of the framework is to preserve the latent detail information of the noisy image while removing the noise with an appropriate smoothing and feasible sharpening. The proposed method is executed in two steps. First, the sub-band replacement and fusion process based on accelerated version of the Bayesian non local means method are implemented to enhance the weak edges that often result in low gradient magnitude and fade out during the de-noising process. Then, a truncated beta-Bernoulli process is employed to infer an appropriate dictionary of the edge enhanced data to obtain de-noising results precisely. Numerical simulations are performed to substantiate the restoration of the weak edges through sub-band replacement and fusion process. The proposed de-noising scheme is validated through visual and quantitative results using well established metrics.

Effects of pose and image resolution on automatic face recognition

The popularity of face recognition systems have increased due to their use in widespread applications. Driven by the enormous number of potential application domains, several algorithms have been proposed for face recognition. Face pose and image resolutions are among the two important factors that influence the performance of face recognition algorithms. In this study, the authors present a comparative study of three baseline face recognition algorithms to analyse the effects of two aforementioned factors. The algorithms studied include (a) the adaptive boosting (AdaBoost) with linear discriminant analysis as weak learner, (b) the principal component analysis (PCA)-based approach, and (c) the local binary pattern (LBP)-based approach. They perform an empirical study using the images with systematic pose variation and resolution from multi-pose, illumination, and expression database to explore the recognition accuracy. This evaluation is useful for practical applications because most engineers start development of a face recognition application using these baseline algorithms. Simulation results revealed that the PCA is more accurate in classifying the pose variation, whereas the AdaBoost is more robust in identifying low-resolution images. The LBP does not classify face images of size 20 × 20 pixels and below and has lower recognition accuracy than PCA and AdaBoost.

Image denoising with norm weighted fusion estimators

In recent era, the weighted matrix rank minimization is used to reduce image noise, promisingly. However, low-rank weighted conditions may cause oversmoothing or oversharpening of the denoised image. This demands a clever engineering algorithm. Particularly, to remove heavy noise in image is always a challenging task, specially, when there is need to preserve the fine edge structures. To attain a reliable estimate of heavy noise image, a norm weighted fusion estimators method is proposed in wavelet domain. This holds the significant geometric structure of the given noisy image during the denoising process. Proposed method is applied on standard benchmark images, and simulation results outperform the most popular rivals of noise reduction approaches, such as BM3D, EPLL, LSSC, NCSR, SAIST, and WNNM in terms of the quality measurement metric PSNR (dB) and structural analysis SSIM indices.

Agriculture land resources and food security nexus in Punjab, Pakistan: an empirical ascertainment

Agriculture is the backbone of Pakistans economy. It employs 45% of the labor force, contributes 21.4% to the gross domestic product and provides food to more than 180 million people of the country. The required plethoric resources to produce food correspondingly protect the population against food insecurity. This study explores the distribution of land resources, their ranking and relationships with food security in all districts of Punjab province of Pakistan. The Gini Coefficient and multiple linear regression were employed. The results showed positive relationships between the Gini of operational land holdings and the proportion of land ownership titles with the proportion of food-insecure population and food availability while the rest exhibited negative relationships as theoretically and statistically justified, which is contrary to earlier studies. It is strongly recommended that policy-makers must redefine the threshold level of land ownership holdings/operational holdings to produce in abundance not only for food availability for household consumption but for food distribution across regions as well.