Search

The detection of biological RNA from sputum has a comparatively poor positive rate in the initial/early stages of discovering COVID‐19, as per the World Health Organization. It has a different morphological structure as compared to healthy images, manifested by computer tomography (CT). COVID‐19 diagnosis at an early stage can aid in the timely cure of patients, lowering the mortality rate. In this reported research, three‐phase model is proposed for COVID‐19 detection. In Phase I, noise is removed from CT images using a denoise convolutional neural network (DnCNN). In the Phase II, the actual lesion region is segmented from the enhanced CT images by using deeplabv3 and ResNet‐18. In Phase III, segmented images are passed to the stack sparse autoencoder (SSAE) deep learning model having two stack auto‐encoders (SAE) with the selected hidden layers. The designed SSAE model is based on both SAE and softmax layers for COVID19 classification. The proposed method is evaluated on actual patient data of Pakistan Ordinance Factories and other public benchmark data sets with different scanners/mediums. The proposed method achieved global segmentation accuracy of 0.96 and 0.97 for classification., Denoise convolutional neural network regression model used for noise removal to enhance images quality. Model deeplabv3 is used as a backbone of the ResNet‐18 model to segment infected lungs region. Segmented images are further supplied to stack sparse autoencoder model for COVID‐19 classification.

White blood cells (WBC) are an important component of immune mechanism, as they protect human body from parasites, viruses, fungi, and bacteria. The number of blood cells provides significant information related to infections such as AIDS, leukemia, deficiencies of immune and autoimmune infections. To heal an infection in a timely manner, it is critical to recognize it early on. Therefore, a method is proposed to accurately segment and classify WBC at an early stage. The RGB image is converted into HSV after which dual thresholding is applied to the saturation component to segment WBC. The 1000 features are extracted from Alexnet to FC8 layer, Logits layer is selected for feature extraction from mobilenetv2, node_202 layer is utilized to extract the features from shuffle net and FC1000 layer is chosen from Resnet-18 model. Four feature vectors are obtained from transfer learning models; these feature vectors are combined serially and create the final optimized vector by non-dominated sorting genetic algorithm (NSGA). The classification results are investigated on the fusion of Alexnet, shuffle net, Resnet-18, mobilenetv2 and the fusion of mobilenetv2, shuffle net and Resnet-18 whereas mobilenetv2 features are fused independently. The method is tested on three publicly available datasets such as LISC, ALL_IDB1, and ALL_IDB2. The method achieved maximum 1.00 accuracy to classify the blast/non-blast cells, 0.9992 accuracy on Basophil cells, and 1.00 accuracy on Lymphocyte, Neutrophil, Monocyte, Eosinophil, and mixture of these cells. When compared to existing modern approaches, the proposed method produces better outcomes.

Coronavirus 19 (COVID-19) can cause severe pneumonia that may be fatal. Correct diagnosis is essential. Computed tomography (CT) usefully detects symptoms of COVID-19 infection. In this retrospective study, we present an improved framework for detection of COVID-19 infection on CT images;the steps include pre-processing, segmentation, feature extraction/ fusion/selection, and classification. In the pre-processing phase, a Gabor wavelet filter is applied to enhance image intensities. A marker-based, watershed controlled approach with thresholding is used to isolate the lung region. In the segmentation phase,COVID-19 lesions are segmented using an encoder- /decoder-based deep learning model in which deepLabv3 serves as the bottleneck and mobilenetv2 as the classification head. DeepLabv3 is an effective decoder that helps to refine segmentation of lesion boundaries. The model was trained using fine-tuned hyperparameters selected after extensive experimentation. Subsequently, the Gray Level Co-occurrence Matrix (GLCM) features and statistical features including circularity, area, and perimeters were computed for each segmented image. The computed features were serially fused and the best features (those that were optimally discriminatory) selected using a Genetic Algorithm (GA) for classification. The performance of the method was evaluated using two benchmark datasets: The COVID-19 Segmentation and the POF Hospital datasets. The results were better than those of existing methods. © 2021 Tech Science Press. All rights reserved.

The common fatal type of skin cancer is melanoma. Recently, numerous intelligent systems are used to detect skin cancer at an early stage. These systems are helpful for a dermatologist as a preliminary judgment to diagnose skin cancer. However, accurate skin lesion detection is an intricate task. This work comprises three main phases, firstly perform preprocessing to resize the images to 240 × 240 × 3 and convert RGB into L^* a^* b^* in which the luminance channel is selected. Secondly, Biorthogonal 2-D wavelet transform, Otsu algorithm are used to segment the skin lesion. Thirdly, deep features extracted from pre-trained Alex net and VGG16 and serially fused. The applied PCA for optimal features selection for classification into benign and malignant. The publically available datasets (PH2, ISBI 2016- 2017) are merged to form a single large dataset for the validated of proposed method. The results comparison is performed with the existing work which confirms that the proposed method classifies the skin lesion more accurately.

Gliomas are dreadful and common type of brain tumor. Therefore, treatment planning is significant to increase the survival rate of gliomas patients. The large structural and spatial variation between tumors makes an automated detection more challenging. Brain magnetic resonance imaging is utilized for tumor evaluation on the basis of automated segmentation and classification methods. In this work, triangular fuzzy median filtering is applied for image enhancement that helps in accurate segmentation based on unsupervised fuzzy set method. Gabor features are extracted across each candidate’s lesions, and similar texture (ST) features are calculated. These ST features are supplied to extreme learning machine (ELM), and regression ELM leaves one out for tumor classification. The technique is evaluated on BRATS 2012, 2013, 2014 and 2015 challenging datasets as well as on 2013 Leader board. The proposed approach shows better results and less computational time.

Purpose This paper aims to present a framework to detect phishing websites using stacking model. Phishing is a type of fraud to access users’ credentials. The attackers access users’ personal and sensitive information for monetary purposes. Phishing affects diverse fields, such as e-commerce, online business, banking and digital marketing, and is ordinarily carried out by sending spam emails and developing identical websites resembling the original websites. As people surf the targeted website, the phishers hijack their personal information. Design/methodology/approach Features of phishing data set are analysed by using feature selection techniques including information gain, gain ratio, Relief-F and recursive feature elimination (RFE) for feature selection. Two features are proposed combining the strongest and weakest attributes. Principal component analysis with diverse machine learning algorithms including (random forest [RF], neural network [NN], bagging, support vector machine, Naïve Bayes and k-nearest neighbour) is applied on proposed and remaining features. Afterwards, two stacking models: Stacking1 (RF + NN + Bagging) and Stacking2 (kNN + RF + Bagging) are applied by combining highest scoring classifiers to improve the classification accuracy. Findings The proposed features played an important role in improving the accuracy of all the classifiers. The results show that RFE plays an important role to remove the least important feature from the data set. Furthermore, Stacking1 (RF + NN + Bagging) outperformed all other classifiers in terms of classification accuracy to detect phishing website with 97.4% accuracy. Originality/value This research is novel in this regard that no previous research focusses on using feed forward NN and ensemble learners for detecting phishing websites.

Skin cancer is developed due to abnormal cell growth. These cells are grown rapidly and destroy the normal skin cells. However, it's curable at an initial stage to reduce the patient's mortality rate. In this article, the method is proposed for localization, segmentation and classification of the skin lesion at an early stage. The proposed method contains three phases. In phase I, different types of the skin lesion are localized using tinyYOLOv2 model in which open neural network (ONNX) and squeeze Net model are used as a backbone. The features are extracted from depthconcat7 layer of squeeze Net and passed as an input to the tinyYOLOv2. The propose model accurately localize the affected part of the skin. In Phase II, 13-layer 3D-semantic segmentation model (01 input, 04 convolutional, 03 batch-normalization, 03 ReLU, softmax and pixel classification) is used for segmentation. In the proposed segmentation model, pixel classification layer is used for computing the overlap region between the segmented and ground truth images. Later in Phase III, extract deep features using ResNet-18 model and optimized features are selected using ant colony optimization (ACO) method. The optimized features vector is passed to the classifiers such as optimized (O)-SVM and O-NB. The proposed method is evaluated on the top MICCAI ISIC challenging 2017, 2018 and 2019 datasets. The proposed method accurately localized, segmented and classified the skin lesion at an early stage. Qatar University [IRCC-2020-009].

The manuscript authenticates the effectiveness of fusing texture and geometrical (GEO) features in magnetic resonance imaging (MRI) for tumor classification. The presented technique is evaluated on two MRI including T2 and FLAIR. The tumor region is enhanced using fast non-local mean (FNLM) method with 4 × 4 patch size. Otsu algorithm is used for tumor segmentation. Moreover, multiple features are extracted for example local binary pattern (LBP), histogram of oriented gradients (HOG) and GEO (area, circularity, filled area, and perimeter) across each segmented image. These acquired features are merged into a single dimensional vector for prediction. In the end, the fused vector is used with multiple classifiers which proved that features fusion provides good results as compared with individual features.

Accurate glioma detection using magnetic resonance imaging (MRI) is a complicated job. In this research, deep learning model is presented for glioma and stroke lesion detection. The proposed architecture consists of 14 layers. The first input layer is followed by three convolutional layers while 5th, 6th and 7th layers correspond to batch normalization, followed by next three layers of rectified linear unit (ReLU). Eleventh layer is average pooling 2D which is followed by fully connected (FC), softmax and classification layers respectively. The presented method is verified on six MICCAI databases namely multimodal brain tumor segmentation (BRATS) 2013, 2014, 2015, 2016, 2017 and sub-acute ischemic stroke lesion segmentation (SISS-ISLES) 2015. The computational time is also measured across each benchmark dataset such as 53 s on BRATS 2013, 26 s on BRATS 2014, 41 s on BRATS 2015, 36 s on BRATS 2016, and 38 s on BRATS 2017 and 4.13 s on ISLES 2015 proving that the proposed technique has less processing time. The proposed method achieved 0.9943 ACC, 1.00 SP, 0.9839 SE on BRATS 2013, 0.9538 ACC, 0.9991 SP, 0.7196 SE on BRATS 2014, 0.9978 ACC, 1.00 SP, 0.9919 SE on BRATS 2015, 0.9569 ACC, 0.9491 SP, 0.9755 SE on BRAST 2016, 0.9778 ACC, 0.9770 SP, 0.9789 SE on BRATS 2017 and 0.9227 ACC, 1.00 SP, 0.8814 SP on ISLES 2015 datasets respectively.

Transportation sector in Pakistan has been rapidly growing, leading to an increase in diesel and petroleum consumption, heightened energy import bill, air pollution, and traffic congestion. The China-Pakistan economic corridor (CPEC) is a cluster of different multi-billion-dollar projects with a significant emphasis on enhancing regional connectivity, and the transportation sector is considered its backbone. Electric road transportation appears to be a game-changer to tackle energy, economy, and environmental issues of a country. This research paper is focused on a scheme and valuation of deploying electric transportation (e-trans) for mass transit under the CPEC umbrella in Pakistan. This paper identifies barriers and challenges and explores various technological options for adopting suitable electric vehicles (EVs) for mass transportation. The paper investigates technical infrastructural requirements, financial, and policy implications for the successful deployment of the proposed electric transportation. In particular, it proposes an EV charging infrastructure based on solar power generation to avoid any electricity burden to recharge EVs from the national power grid. In order to be comprehensive, it presents a case study to develop an EV charging station network with an estimation of the cost for accommodating charging requirements of one thousand electric trucks and hundred mobile charging trucks. Obtained results demonstrate that merely 0.29% of the CPEC's energy sector approved budget will be incurred for deploying the proposed charging station network to support e-trans over the studies road segment, which appears to be a feasible initiative. Important factors which may influence the proposed scheme for implementation of e-trans under the CPEC is analyzed using SWOT analysis. The recommended set of policies for deploying electric transportation and its quantitative financial analysis will help the concerned stakeholders to discover and execute the necessary steps to ensure sustainable electric transportation under the CPEC in Pakistan.

Summary COVID‐19 is a quickly spreading over 10 million persons globally. The overall number of infected patients worldwide is estimated to be around 133,381,413 people. Infection rate is being increased on daily basis. It has also caused a devastating effect on the world economy and public health. Early stage detection of this disease is mandatory to reduce the mortality rate. Artificial intelligence performs a vital role for COVID‐19 detection at an initial stage using chest radiographs. The proposed methods comprise of the two phases. Deep features (DFs) are derived from its last fully connected layers of pre‐trained models like AlexNet and MobileNet in phase‐I. Later these feature vectors are fused serially. Best features are selected through feature selection method of PCA and passed to the SVM and KNN for classification. In phase‐II, quantum transfer learning model is utilized, in which a pre‐trained ResNet‐18 model is applied for DF collection and then these features are supplied as an input to the 4‐qubit quantum circuit for model training with the tuned hyperparameters. The proposed technique is evaluated on two publicly available x‐ray imaging datasets. The proposed methodology achieved an accuracy index of 99.0% with three classes including corona virus‐positive images, normal images, and pneumonia radiographs. In comparison to other recently published work, the experimental findings show that the proposed approach outperforms it.

Coronavirus19 is caused due to infection in the respiratory system. It is the type of RNA virus that might infect animal and human species. In the severe stage, it causes pneumonia in human beings. In this research, hand‐crafted and deep microscopic features are used to classify lung infection. The proposed work consists of two phases; in phase I, infected lung region is segmented using proposed U‐Net deep learning model. The hand‐crafted features are extracted such as histogram orientation gradient (HOG), noise to the harmonic ratio (NHr), and segmentation based fractal texture analysis (SFTA) from the segmented image, and optimum features are selected from each feature vector using entropy. In phase II, local binary patterns (LBPs), speeded up robust feature (Surf), and deep learning features are extracted using a pretrained network such as inceptionv3, ResNet101 from the input CT images, and select optimum features based on entropy. Finally, the optimum selected features using entropy are fused in two ways, (i) The hand‐crafted features (HOG, NHr, SFTA, LBP, SURF) are horizontally concatenated/fused (ii) The hand‐crafted features (HOG, NHr, SFTA, LBP, SURF) are combined/fused with deep features. The fused optimum features vector is passed to the ensemble models (Boosted tree, bagged tree, and RUSBoosted tree) in two ways for the COVID19 classification, (i) classification using fused hand‐crafted features (ii) classification using fusion of hand‐crafted features and deep features. The proposed methodology is tested /evaluated on three benchmark datasets. Two datasets employed for experiments and results show that hand‐crafted & deep microscopic feature's fusion provide better results compared to only hand‐crafted fused features., The affected lung region is segmented using a modified U‐Net deep learning model. The extracted hand‐crafted deep features and selected optimized features using entropy are fused serially and supplied to the ensemble learning. COVID19 detection process.

Brain tumor detection depicts a tough job because of its shape, size and appearance variations. In this manuscript, a deep learning model is deployed to predict input slices as a tumor (unhealthy)/non-tumor (healthy). This manuscript employs a high pass filter image to prominent the inhomogeneities field effect of the MR slices and fused with the input slices. Moreover, the median filter is applied to the fused slices. The resultant slices quality is improved with smoothen and highlighted edges of the input slices. After that, based on these slices' intensity, a 4-connected seed growing algorithm is applied, where optimal threshold clusters the similar pixels from the input slices. The segmented slices are then supplied to the fine-tuned two layers proposed stacked sparse autoencoder (SSAE) model. The hyperparameters of the model are selected after extensive experiments. At the first layer, 200 hidden units and at the second layer 400 hidden units are utilized. The testing is performed on the softmax layer for the prediction of the images having tumors and no tumors. The suggested model is trained and checked on BRATS datasets i.e., 2012(challenge and synthetic), 2013, and 2013 Leaderboard, 2014, and 2015 datasets. The presented model is evaluated with a number of performance metrics which demonstrates the improved performance.

Brain tumor is one of the most death defying diseases nowadays. The tumor contains a cluster of abnormal cells grouped around the inner portion of human brain. It affects the brain by squeezing/ damaging healthy tissues. It also amplifies intra cranial pressure and as a result tumor cells growth increases rapidly which may lead to death. It is, therefore desirable to diagnose/ detect brain tumor at an early stage that may increase the patient survival rate. The major objective of this research work is to present a new technique for the detection of tumor. The proposed architecture accurately segments and classifies the benign and malignant tumor cases. Different spatial domain methods are applied to enhance and accurately segment the input images. Moreover Alex and Google networks are utilized for classification in which two score vectors are obtained after the softmax layer. Further, both score vectors are fused and supplied to multiple classifiers along with softmax layer. Evaluation of proposed model is done on top medical image computing and computer-assisted intervention (MICCAI) challenge datasets i.e., multimodal brain tumor segmentation (BRATS) 2013, 2014, 2015, 2016 and ischemic stroke lesion segmentation (ISLES) 2018 respectively.

Vibration and acoustic emission have received great attention of the research community for condition-based maintenance in rotating machinery. Several signal processing algorithms were either developed or used efficiently to detect and classify faults in bearings and gears. These signals are recorded, using sensors like tachometer or accelerometer, connected directly or mounted very close to the system under observation. This is not a feasible option in case of complex machinery and/or temperature and humidity. Therefore, it is required to sense the signals remotely, in order to reduce installation and maintenance cost. However, its installation far away from the intended device may pollute the required signal with other unwanted signals. In an attempt to address these issues, sound signal-based fault detection and classification in rotating bearings is presented. In this research work, audible sound of machine under test is captured using a single microphone and different statistical, spectral and spectro-temporal features are extracted. The selected features are then analyzed using different machine learning techniques, such as K-nearest neighbor (KNN) classifier, support vector machine (SVM), kernel liner discriminant analysis (KLDA) and sparse discriminant analysis (SDA). Simulation results show successful classification of faults into ball fault, inner and outer race faults. Best results were achieved using the KLDA followed by SDA, KNN and SVM. As far as features are concerned, the average FFT outperformed all the other features, followed by average PSD, RMS values of PSD, PSD and STFT. Refereed/Peer-reviewed

Background and Objective Brain tumor occurs because of anomalous development of cells. It is one of the major reasons of death in adults around the globe. Millions of deaths can be prevented through early detection of brain tumor. Earlier brain tumor detection using Magnetic Resonance Imaging (MRI) may increase patient's survival rate. In MRI, tumor is shown more clearly that helps in the process of further treatment. This work aims to detect tumor at an early phase. Methods In this manuscript, Weiner filter with different wavelet bands is used to de-noise and enhance the input slices. Subsets of tumor pixels are found with Potential Field (PF) clustering. Furthermore, global threshold and different mathematical morphology operations are used to isolate the tumor region in Fluid Attenuated Inversion Recovery (Flair) and T2 MRI. For accurate classification, Local Binary Pattern (LBP) and Gabor Wavelet Transform (GWT) features are fused. Results The proposed approach is evaluated in terms of peak signal to noise ratio (PSNR), mean squared error (MSE) and structured similarity index (SSIM) yielding results as 76.38, 0.037 and 0.98 on T2 and 76.2, 0.039 and 0.98 on Flair respectively. The segmentation results have been evaluated based on pixels, individual features and fused features. At pixels level, the comparison of proposed approach is done with ground truth slices and also validated in terms of foreground (FG) pixels, background (BG) pixels, error region (ER) and pixel quality (Q). The approach achieved 0.93 FG and 0.98 BG precision and 0.010 ER on a local dataset. On multimodal brain tumor segmentation challenge dataset BRATS 2013, 0.93 FG and 0.99 BG precision and 0.005 ER are acquired. Similarly on BRATS 2015, 0.97 FG and 0.98 BG precision and 0.015 ER are obtained. In terms of quality, the average Q value and deviation are 0.88 and 0.017. At the fused feature based level, specificity, sensitivity, accuracy, area under the curve (AUC) and dice similarity coefficient (DSC) are 1.00, 0.92, 0.93, 0.96 and 0.96 on BRATS 2013, 0.90, 1.00, 0.97, 0.98 and 0.98 on BRATS 2015 and 0.90, 0.91, 0.90, 0.77 and 0.95 on local dataset respectively. Conclusion The presented approach outperformed as compared to existing approaches.

Sign language recognition (SLR) has got wide applicability. SLR system is considered to be a challenging one. This paper presents empirical analysis of different mathematical models for Pakistan SLR (PSLR). The proposed method is using the parameterization of sign signature. Each sign is represented with a mathematical function and then coefficients of these functions are used as the feature vector. This approach is based on exhaustive experimentation and analysis for getting the best suitable mathematical representation for each sign. This extensive empirical analysis, results in a very small feature vector and hence to a very efficient system. The robust proposed method has got general applicability as it just need a new training set and it can work equally good for any other dataset. Sign set used is quite complex in the sense that intersign similarity distance is very small but even then proposed methodology has given quite promising results.

Wireless Sensor Networks have attained extensive interest since the last few decades. Especially Wireless Multimedia sensor networks are being used in surveillances, health, traffic monitoring and entertainment where these sensors are deployed at different views for capturing the finer details of a given region. With their extensive use and benefits, they have many issues such as battery life, storage capacity, and bandwidth consumption. The aim of the research paper is to study the existing spatial correlation models in multi view videos and propose an approach which reduces battery consumption by minimizing the compression time of video frames based on the specific correlation model. This paper discusses the novel OPI model that is designed on the basis of correlation between sensor nodes. Experimental results have been derived using OPI model and the results depict that by using this approach, compression time of processed video frames is reduced as compared to the compression time of originally frames.

Human beings are commonly identified by biometric schemes which are concerned with identifying individuals by their unique physical characteristics. The use of passwords and personal identification numbers for detecting humans are being used for years now. Disadvantages of these schemes are that someone else may use them or can easily be forgotten. Keeping in view of these problems, biometrics approaches such as face recognition, fingerprint, iris/retina and voice recognition have been developed which provide a far better solution when identifying individuals. A number of methods have been developed for face recognition. This paper illustrates employment of Gabor filters for extracting facial features by constructing a sliding window frame. Classification is done by assigning class label to the unknown image that has maximum features similar to the image stored in the database of that class. The proposed system gives a recognition rate of 96% which is better than many of the similar techniques being used for face recognition.

In this paper a new approach to face recognition is presented which is based on processing of face images in hexagonal lattice. The importance of the hexagonal representation is that it possesses special computational features that are pertinent to the Human Vision process. Few advantages of processing images on hexagonal lattice are higher degree of circular symmetry, uniform connectivity, greater angular resolution, and a reduced need of storage and computation in image processing operations. Proposed methodology is a hybrid approach to face recognition. DCT is being applied to hexagonally converted images for dimensionality reduction and feature extraction. These features are stored in a database for recognition purpose. Artificial Neural Network (ANN) is being used for recognition. Experiments and testing were conducted over ORL, Yale and FERET databases. The proposed methodology has given better results in recognition over square pixel based approaches.

Retinal images are used for automated diagnosis of Diabetic Retinopathy. Preprocessing of retinal image is required prior to detection of features and abnormalities. The objective of preprocessing segmentation is to separate the background and noisy area from the overall image to enhance the quality of acquired retinal image. We present a method for colored retinal image preprocessing and enhancement. Our technique creates a binary mask to preprocess the retinal image using morphological operations.The preprocessing technique is tested on standard retinal images databases Diaretdb0 and Diaretdb1. The validity of our technique is checked against the experimental results.

The paper presents two invisible approaches for hiding data in frequency and spatial domain. Both schemes were exposed to different watermarking attacks. Though the techniques used in spatial domain is not robust against many attacks but it will give useless information to the attacker unless he has the decoding key. In frequency domain, fast Fourier transform has been adopted for digital image watermarking. Central frequencies are selected to insert the data in a ring. In spatial domain, encrypted data will be inserted in the least significant bits. Also, it has been observed that the scheme in frequency domain is robust against a number of attacks. Both schemes do not require the original image for extracting the embedded data mark. Description of the frequency domain method has been discussed in detail along with the results.

In iris recognition, accurate Iris segmentation is the most crucial step. Iris recognition systems are highly affected by the performance of iris segmentation processing. In this paper a robust and efficient method of iris segmentation is proposed. In the proposed scheme, the inner boundary of iris is calculated by finding the pupil center and radius using first derivative of the image. For outer iris boundary, a band is calculated within which iris outer boundary lies. One dimensional signals are picked along radial direction from the determined band in a sequence at different angles to obtain the outer circle of the iris. Points for upper and lower eyelids are found in the same way as the iris outer boundary followed by the statistically fit parabolas to completely localize the iris. Experimental results show that proposed method is very efficient.

In this paper the effects of image resolution on recognition have been discussed using linear dimension reduction face recognition technique and image scale normalization is carried out through Automatic Cropping Algorithm (ACA). Linear dimension technique is based on the verity that a specific pattern of interest could reside in a low dimensional sub manifold in original input data and at the same time varying image resolution affect the pattern / face recognition results but reaching at a specific level few features of face become so prominent that it provides best matching with template image on same resolution and in return gives best success rate.. The experiments have been carried out on ORL, Yale, FERET and EME color databases and it is established that for each database there is always an optimal image resolution exits where the recognition performance is always best. This model consists of two parts, first part is preprocessing of the image, which includes conversion of a color image to gray scale image and then sobel edge detector mask is applied to detect the outer curvature of the face. Later on Automatic Cropping Algorithm is applied to carry out automatic face normalization. In Second part, the Gaussian pyramid of varying image resolution is obtained and effects of resolution on recognition are discussed.

In this paper, an efficient method for personal identification based on the pattern of human iris is proposed. The system initially detects boundaries of iris, and then unwraps it into rectangular strip. A single vector is obtained corresponding to maximum eigen value and it is used as distinct feature of the iris. In the next step training is done and recognition decision is carried out by comparing the Euclidean distances with other feature vectors which determine whether two irises are similar or not. The results show that the success rate of the proposed method is 95.91%.

This paper proposes a face recognition scheme that enhances the correct face recognition rate as compared to conventional Principal Component Analysis (PCA). The proposed scheme, Sub-Holistic PCA (SH-PCA), was tested using ORL database and out performed PCA for all test scenarios. SH-PCA requires more computational power and memory as compared to PCA however it yields an improvement of 6% correct recognition on the complete ORL database of 400 images. The correct recognition rate for the complete ORL database is 90% for the SH-PCA technique.

The biometric schemes are commonly used for the identification of human beings. Face recognition approach has been employed using different algorithms for the purpose of identification of individuals. This paper describes utilization of Gabor filters for selecting feature vectors/coefficients. It explains construction of Gabor filters, selection of peaks, feature storage and classification of faces. Standard and improved classifier schemes have been used to evaluate the developed face recognition system in terms of detection rate and speed by using 20 to 60 Gabor filters. Evaluation results have been obtained through ORL database where 200 images have been used for training and 200 images for testing (i.e. first five images of each person for training and remaining five images for testing). The results show that the improved classifier extracts 8878 feature vectors for a bank of 40 Gabor filters and provides detection rate of 92.5 % whereas a bank of 30 Gabor filters provided detection rate of 93% by extracting 8700 feature vectors. It has also been noted that training and time for a single image using 30 Gabor filters is 5.35 and 14.5 seconds respectively which is less as compared to 40 Gabor filter-based system

Localization of human eye (iris) in a non invasive fashion with accuracy has great significance. Iris localization is the back bone of iris recognition systems. In this paper a novel method to localize the eyelid is presented. Iris is localized by applying the texture analysis approach. To find the upper eyelid, a rectangular average filter (size two by five) is applied to the segment above iris center and between left and right boundaries of iris. It is followed by sobel horizontal filter. Points of pupil and iris boundaries are removed and a parabola which best fit among the remaining points. This parabola is the required upper eyelid. Lower eyelid is obtained using the same method. Experimental results show that proposed method is very effective

In this paper facial tilt and varying background challenges to face recognition in frequency domain have been addressed and maximum possible compensation to these problems is provided in image pre processing through image reverse rotation and gray scale morphological operations. Facial features through two distinct techniques are extracted by applying discrete Fourier transform (DFT) on images. In this face recognition model only real part of DFT coefficients with maximum information is retained for recognition which not only provides considerable dimension reduction with improved computational speed but also better recognition results. Experiments on ORL and YALE datasets have been performed with success rate up to 98.78%

LDA's between class scatter matrix is confronted with small sample size problem. In order to avoid this problem, PCA subspace is used which reduces the dimensions of images to such an extent that small sample size problem can be avoided. This approach is called as LDA using PCA subspace. Robust LDA by sub-sampling is a modification of LDA using PCA subspace and is designed to work in non-ideal conditions, in conditions where images are occluded. Robust LDA uses sub-sampling to avoid occluded pixels and use only true image pixels of the occluded image. The complexity efface recognition under non-ideal conditions is dependent upon number of classes used and percentage of occlusion applied to test image. In this paper comparison has been made and found that robust LDA by subsampling remains a better classifier than LDA using PCA subspace for occlusion of 50 percent using 17 classes

Medical image analysis is a very popular research area these days in which digital images are analyzed for the diagnosis and screening of different medical problems. Diabetic retinopathy (DR) is an eye disease caused by the increase of insulin in blood and may cause blindness. An automated system for early detection of DR can save a patient's vision and can also help the ophthalmologists in screening of DR. The background or nonproliferative DR contains four types of lesions, i.e., microaneurysms, hemorrhages, hard exudates, and soft exudates. This paper presents a method for detection and classification of exudates in colored retinal images. We present a novel technique that uses filter banks to extract the candidate regions for possible exudates. It eliminates the spurious exudate regions by removing the optic disc region. Then it applies a Bayesian classifier as a combination of Gaussian functions to detect exudate and nonexudate regions. The proposed system is evaluated and tested on publicly available retinal image databases using performance parameters such as sensitivity, specificity, and accuracy. We further compare our system with already proposed and published methods to show the validity of the proposed system.