Shoab Ahmad Khan

Identification and classification of microaneurysms for early detection of diabetic retinopathy

Diabetic retinopathy is a progressive eye disease which may cause blindness if not detected and treated in time. The early detection and diagnosis of diabetic retinopathy is important to protect the patients vision. The accurate detection of microaneurysms (MAs) is a critical step for early detection of diabetic retinopathy because they appear as the first sign of disease. In this paper, we propose a three-stage system for early detection of MAs using filter banks. In the first stage, the system extracts all possible candidate regions for MAs present in retinal image. In order to classify a candidate region as MA or non-MA, the system formulates a feature vector for each region depending upon certain properties, i.e. shape, color, intensity and statistics. We present a hybrid classifier which combines the Gaussian mixture model (GMM), support vector machine (SVM) and an extension of multimodel mediod based modeling approach in an ensemble to improve the accuracy of classification. The proposed system is evaluated using publicly available retinal image databases and achieved higher accuracy which is better than previously published methods.

Multilayered thresholding-based blood vessel segmentation for screening of diabetic retinopathy

Diabetic retinopathy screening involves assessment of the retina with attention to a series of indicative features, i.e., blood vessels, optic disk and macula etc. The detection of changes in blood vessel structure and flow due to either vessel narrowing, complete occlusions or neovascularization is of great importance. Blood vessel segmentation is the basic foundation while developing retinal screening systems since vessels serve as one of the main retinal landmark features. This article presents an automated method for enhancement and segmentation of blood vessels in retinal images. We present a method that uses 2-D Gabor wavelet for vessel enhancement due to their ability to enhance directional structures and a new multilayered thresholding technique for accurate vessel segmentation. The strength of proposed segmentation technique is that it performs well for large variations in illumination and even for capturing the thinnest vessels. The system is tested on publicly available retinal images databases of manually labeled images, i.e., DRIVE and STARE. The proposed method for blood vessel segmentation achieves an average accuracy of 94.85% and an average area under the receiver operating characteristic curve of 0.9669. We compare our method with recently published methods and experimental results show that proposed method gives better results.

Detection and classification of retinal lesions for grading of diabetic retinopathy

Diabetic Retinopathy (DR) is an eye abnormality in which the human retina is affected due to an increasing amount of insulin in blood. The early detection and diagnosis of DR is vital to save the vision of diabetes patients. The early signs of DR which appear on the surface of the retina are microaneurysms, haemorrhages, and exudates. In this paper, we propose a system consisting of a novel hybrid classifier for the detection of retinal lesions. The proposed system consists of preprocessing, extraction of candidate lesions, feature set formulation, and classification. In preprocessing, the system eliminates background pixels and extracts the blood vessels and optic disc from the digital retinal image. The candidate lesion detection phase extracts, using filter banks, all regions which may possibly have any type of lesion. A feature set based on different descriptors, such as shape, intensity, and statistics, is formulated for each possible candidate region: this further helps in classifying that region. This paper presents an extension of the m-Mediods based modeling approach, and combines it with a Gaussian Mixture Model in an ensemble to form a hybrid classifier to improve the accuracy of the classification. The proposed system is assessed using standard fundus image databases with the help of performance parameters, such as, sensitivity, specificity, accuracy, and the Receiver Operating Characteristics curves for statistical analysis.

Automated Detection of Dark and Bright Lesions in Retinal Images for Early Detection of Diabetic Retinopathy

There is an ever-increasing interest in the development of automatic medical diagnosis systems due to the advancement in computing technology and also to improve the service by medical community. The knowledge about health and disease is required for reliable and accurate medical diagnosis. Diabetic Retinopathy (DR) is one of the most common causes of blindness and it can be prevented if detected and treated early. DR has different signs and the most distinctive are microaneurysm and haemorrhage which are dark lesions and hard exudates and cotton wool spots which are bright lesions. Location and structure of blood vessels and optic disk play important role in accurate detection and classification of dark and bright lesions for early detection of DR. In this article, we propose a computer aided system for the early detection of DR. The article presents algorithms for retinal image preprocessing, blood vessel enhancement and segmentation and optic disk localization and detection which eventually lead to detection of different DR lesions using proposed hybrid fuzzy classifier. The developed methods are tested on four different publicly available databases. The presented methods are compared with recently published methods and the results show that presented methods outperform all others.

Automated Detection and Grading of Diabetic Maculopathy in Digital Retinal Images

Diabetic maculopathy is one of the retinal abnormalities in which a diabetic patient suffers from severe vision loss due to the affected macula. It affects the central vision of the person and causes blindness in severe cases. In this article, we propose an automated medical system for the grading of diabetic maculopathy that will assist the ophthalmologists in early detection of the disease. The proposed system extracts the macula from digital retinal image using the vascular structure and optic disc location. It creates a binary map for possible exudate regions using filter banks and formulates a detailed feature vector for all regions. The system uses a Gaussian Mixture Model-based classifier to the retinal image in different stages of maculopathy by using the macula coordinates and exudate feature set. The evaluation of proposed system is performed by using publicly available standard retinal image databases. The results of our system have been compared with other methods in the literature in terms of sensitivity, specificity, positive predictive value and accuracy. Our system gives higher values as compared to others on the same databases which makes it suitable for an automated medical system for grading of diabetic maculopathy.

Fingerprint image: pre- and post-processing

Automatic Fingerprint Identification Systems (AFIS) are widely used for personal identification due to uniqueness of fingerprints. Minutiae-based fingerprint matching techniques are normally used for fingerprint matching. Fingerprint matching results and their accuracy depends on presence of valid minutiae. In this paper, we present a new technique for fingerprint image post-processing. This post-processing is used to eliminate a large number of false extracted minutiae from skeletonised fingerprint images. We propose a windowing post-processing method that takes into account the neighbourhood of each minutia within defined window and check for minutia validation and invalidation. We also present a complete pre-processing system including new segmentation technique that is required to extract region of interest (ROI) accurately from a fingerprint image. The results are confirmed by visual inspections of validated minutiae of the FVC2004 reference fingerprint image database. Experimental results obtained by the proposed approach show efficient reduction of false minutiae.

Blood Vessel Enhancement and Segmentation Using Wavelet Transform

Retinal vessel segmentation is an essential step for the diagnoses of various eye diseases. An automated tool for blood vessel segmentation is useful to eye specialists for purpose of patient screening and clinical study. Vascular pattern is normally not visible in retinal images. In this paper, we present a method forenhancing, locating and segmenting blood vessels in images of retina. We present a method that uses 2-D Gabor wavelet and sharpening filter to enhance and sharpen the vascular pattern respectively. This technique locates and segments the blood vessels using edge detection algorithm and morphological operations. This technique is tested on publicly available STARE database of manually labeled images which has been established to facilitate comparative studies on segmentation of blood vessels in retinal images. The validation of our retinal image vessel segmentation technique is supported by experimental results.

Satellite-based land use mapping: comparative analysis of Landsat-8, Advanced Land Imager, and big data Hyperion imagery

Abstract. Until recently, Landsat technology has suffered from low signal-to-noise ratio (SNR) and comparatively poor radiometric resolution, which resulted in limited application for inland water and land use/cover mapping. The new generation of Landsat, the Landsat Data Continuity Mission carrying the Operational Land Imager (OLI), has improved SNR and high radiometric resolution. This study evaluated the utility of orthoimagery from OLI in comparison with the Advanced Land Imager (ALI) and hyperspectral Hyperion (after preprocessing) with respect to spectral profiling of classes, land use/cover classification, classification accuracy assessment, classifier selection, study area selection, and other applications. For each data source, the support vector machine (SVM) model outperformed the spectral angle mapper (SAM) classifier in terms of class discrimination accuracy (i.e., water, built-up area, mixed forest, shrub, and bare soil). Using the SVM classifier, Hyperion hyperspectral orthoimagery achieved higher overall accuracy than OLI and ALI. However, OLI outperformed both hyperspectral Hyperion and multispectral ALI using the SAM classifier, and with the SVM classifier outperformed ALI in terms of overall accuracy and individual classes. The results show that the new generation of Landsat achieved higher accuracies in mapping compared with the previous Landsat multispectral satellite series.

Letters: A hierarchical k-means clustering based fingerprint quality classification

This paper presents a novel technique that employs a hierarchical k-means clustering for quality based classification of fingerprints for subsequent improvement in fingerprint matching results. A set of statistical and frequency features have been calculated from a fingerprint image. A hierarchical k-means clustering algorithm has been utilized to classify the fingerprint image into one of four quality classes, i.e. good, dry, normal or wet. An objective method has also been proposed to evaluate the performance of fingerprint quality classification. It has been shown through experimental results that the performance of minutiae based matcher improves when the quality of fingerprint image is incorporated in the matching stage. The false accept rate and false reject rate of minutiae based fingerprint matcher are 1.8 on FVC 2002 db1 database without utilizing fingerprint quality information. False accept rate has been reduced from 1.8 to 0.79 whereas the false reject rate is at 1.8 when fingerprint quality based threshold value is utilized. This significant improvement in the performance of the fingerprint matching system shows the effectiveness of hierarchical k-means clustering technique in quality based classification of fingerprints.

Moment Invariants Based Human Mistrustful and Suspicious Motion Detection, Recognition and Classification

In this paper, we present human mistrustful motion detection & classification using Hu Moment Invariants feature descriptions. A new method for recognition & classification that is Moment Invariant based Classifier (MIBC) has been proposed. The basis of the MIBC is the different seven φ values of Hu Moment Invariants itself and the Euclidean Distance measure between these φ values of all image frames of each type of motion. These values of Moment Invariants and Euclidean Distances are compared with other values and Euclidean Distances of all image frames of different or same type of motion. The performance of MIBC is evaluated with other types of methodologies & classifiers like Mahalanobis Distance (MD) classifier, Linear Bayes Gaussian (LBG) classifier, Quadratic Bayes Gaussian (QBG) classifier and Fuzzy K-Nearest Neighbor (FKNN) classifier using temporal template motion detection technique. The performance evaluation is done in the context of accuracy, time and speed. Experiments are conducted on five types of suspicious motions: Bending down, Gun Shot, Jumping up, Kicking front and Punching forward.