Search

Hyperspectral image (HSI) usually holds information of land cover classes as a set of many contiguous narrow spectral wavelength bands. For its efficient thematic mapping or classification, band (f...

Subspace detection from high dimensional hyperspectral image (HSI) data cube has become an important area of research for efficient identification of ground objects. Standard feature extraction met...

The hyperspectral remote sensing images (HSIs) are acquired to encompass the essential information of land objects through contiguous narrow spectral wavelength bands. The classification accuracy i...

In recent years, the demand for prompt detection and classification of breast cancer is rising sharply as breast cancer has become leading cancer type among women throughout the world. Convolutional Neural Networks(CNNs) are widely being used for performing mentioned tasks.However, they need a large number of labeled images which may appear to be infeasible for some kinds of medical images data such as mammographic tumor images. To address this difficulty, Transfer Learning becomes convenient. In this paper, we proposed a deep learning model for classifying Benign and Malignant types of breast tumor that trains an InceptionV3 model which pulls out features from the histopathological images of various magnification. These features are then used for classification. Introduced system is validated on BreakHis dataset and gains average validation set accuracy of 99.50%, 98.90%, 98.96% and 98.51% for magnification factor 40X, 100X, 200X and 400X respectively which outperforms all studied baseline models. Different performance metrices such as precision, recall, F 1 score, Specificity have additionally been used for performance estimation purposes.

The remote sensing hyperspectral images (HSIs) usually comprise many important information of the land covers capturing through a set of hundreds of narrow and contiguous spectral wavelength bands....

Lysine formylation is a newly discovered and mostly interested type of post-translational modification (PTM) that is generally found on core and linker histone proteins of prokaryote and eukaryote and plays various important roles on the regulation of various cellular mechanisms. Hence, it is very urgent to properly identify formylation site in protein for understanding the molecular mechanism of formylation deeply and defining drug for relevant diseases. As experimentally identification of formylation site using traditional processes are expensive and time consuming, a simple and high speedy mathematical model for predicting accurately lysine formylation sites is highly desired. A useful computational model named PLF_SVM is deigned and proposed in this study by using binary encoding (BE), amino acid composition (AAC), reverse position relative incidence matrix (RPRIM), position relative incidence matrix (PRIM), and position specific amino acid propensity (PSAAP) feature generation methods for predicting formylated and non-formylated lysine sites. Besides, the Synthetic Minority Oversampling Technique (SMOTE) and a proposed sample selection strategy named EnSVM are applied to handle the imbalance training dataset problem. Thereafter, the optimal number of features are selected by F-score method to train the model. Finally, it has been seen that PLF_SVM outperforms the state-of-the-art approaches in validation and independent test with an accuracy of 98.61% and 98.77% respectively. At https://plf-svm.herokuapp.com/, a user-friendly web tool is also created for identifying formylation sites. Therefore, the proposed method may be helpful guideline for the analysis and prediction of formylated lysine and knowing the process of cellular regulation.

Document images can have numerous noises that should be filtered to eliminate those unutilized objects. Skewness is liable not to understand the texts clearly in the document image. A morphological technique is being conducted to preprocess the image. Connected component analysis along with the bounding box approach is introduced to figure out a line. A number of longest connected components are extracted from numerous illustrations. In order to detect a precise skewed angle, the least square method is applied to the logically selected regions to acquire the best fitting line. The skewed angle is discovered by averaging angles of best-fitting lines. The proposed system is already applied on the printed document image and got tremendous accuracy during execution.

Being electrocardiogram already an established method for analyzing cardiac health, it gained many researchers' interests to classify heartbeats accurately. In spite of having numerous works in this field, it still lacks obtaining high accuracy scores. In this paper, some well-known machine learning approaches are used by tuning and compared with other state-of-the-art related methodologies. The datasets are used in this research work, are highly imbalanced and handled with penalizing the loss value of the Artificial Neural Network (ANN) by assigning class weights. Two different enriched ECG datasets are selected for this research. They are MIT-BIH Arrhythmia which contains five classes and PTB Diagnostic ECG which contains two classes. About 98.06% and 97.664% accuracy are achieved with proposed approaches for MIT-BIH Arrhythmia and PTB Diagnostic ECG dataset respectively. Both cases this research outperforms all the other state-of-the-art methodologies.

Hyperspectral image classification has become a very important area of research in recent years. However the classif cation become very challenging as the input dimension is very high. This is because the cost increases with the number of input features used to describe the pixel vectors. This problem can be addressed by reducing the irrelevant features for the task of classification. Moreover all the features are no equally important for classification. Principal Component Analysis (PCA) extracts feature however it depends on global variance. To overcome these limitations, a class-oriented subspace detection method is proposed which measures the relevancy of the selected subspace using Normalized Mutual Information (NMI) and Cross Cumulative Residual Entropy (CCRE). The application of NMI and CCRE over PCA images maximize the relevance as well as provided an uncorrelated subspace. Experimental analysis was performed to assess the effectiveness of the proposed method and the selected subspace was evaluated using the Support Vector Machine (SVM). Our proposed method achieves 87.61% and 88.57% classification accuracy respectively.

Technological advancement has been developed immensely in two areas over the past few years; these are computer and communication networks. This breakthrough has provided an opportunity for people around the world to access literature and important information. If the database of these manuscripts can be developed and make them available on the internet, the people will access those information as desired. The documents can be well-preserved in digital library so that they cannot be degraded. They are trying to improve the recognition rate in order to get the precise meaning of texts. Distorted character recognition is complicated in contrast with simple plain text images. Sometimes distorted character is seemed to be other character and the accuracy rate drops down drastically. As a result significant information is misplaced. In this paper, we are proposing an algorithm which will improve character recognition rate however it is distorted document image. The accuracy rate of our recommended algorithm is 97%.

In recent years, the classification of Hyper Spectral Image (HSI) has posed a big challenge for the analysis of multidimensional property of the image. So it is of utmost importance to reduce the dimension of HSIs. There are several ways to reduce the dimension of hyperspectral images such as Principle Component Analysis (PCA), Kernel Principal Component Analysis (KPCA), Kernel Entropy Component Analysis (KECA) and so on. Through this article, We proposed an updated variant of KPCA using multiple kernels such as Linear, RBF, Cosine, Sigmoid, etc. We fused their spectral and special properties by classifying the HSIs using Hybrid Spectral Net Model (HybridSN) which is a recently trending modified deep neural network algorithm using Convolutional Neural Network (CNN). This paper presents empirical outcomes of the effects of using different kernels of KPCA algorithm and their performances regarding the classification of well-known hyperspectral data sets.

Brain tumor classification is one of the most important aspects in the fields of medical image analysis. As tumors are regarded as precursor to cancers, efficient brain tumor classification can prove life saving. For this reason, Convolutional Neural Network(CNN) based approaches are widely being used for classifying brain tumors. However there lies a dilemma, CNNs are accustomed to large amount of training data for giving better result. It is where transfer learning comes useful. In this paper, we propose 3-class deep learning model for classifying Glioma, Meningioma and Pituitary tumors which are regarded as three prominent types of brain tumor. Our proposed model by adopting the concept of transfer learning uses a pre-trained InceptionV3model extracts features from the brain MRI images and deploys softmax classifier for classification. The proposed system is tested on CE-MRI dataset from figshare and achieves an average classification accuracy of 99%, outperforming all previous methods. Few other performance measures such as precision, recall, F-score are also considered while assessing the performance.

Remotely sensed images provide unseen characteristics of the earth's surface as they are composed of hundreds of spectral bands of the electromagnetic spectrum. Both spatial and spectral information of hyperspectral image make it possible to categories vegetation and recognize earth's minerals and materials. But analysis of hyperspectral data suffers from curse of dimensionality due to the huge number of spectral bands or features. Not all features contain useful information and additionally, there is redundant information in some features. This paper proposes a model for detecting effective feature subspace from original hyperspectral data using both Segmented Principal Component Analysis and F-score methods. Depending on the correlation of the spectral bands, the data cube is partitioned into subgroups. Then principal component transform is performed on each subgroup. Finally, the most informative feature subspace is selected by considering discriminative characteristics of the features using F-score method. Two real hyperspectral images are used in the implementation of the proposed model. The classification accuracy of the proposed approach shows the superiority over other studied methods.

An architecture is proposed in this paper, which combines both the U-net and Neural Ordinary Differential Equations for semantic segmentation. This method consumes very lower memory and at the same time in many cases outperforms some state-of-the-art methodologies in terms of very well known performance metrics for semantic segmentation. The proposed approach is tested on three datasets, two of them are medical images and another one is self-supervised dataset. For all the datasets, the proposed approach outperforms the state-of-the-art methods with the same environmental setup.

Hyperspectral Image (HSI) is a rich source of information for the analysis of the earth's surface. HSI produces a rich set of both spectral and spatial information for possible recognition of earth materials, minerals and vegetation categories. Since HSI has high dimensional spectral information so that, feature extraction methods has been used to reduce the dimensions. The most widely used feature extraction method Principal Component Analysis (PCA) is applied in HSI for dimension reduction. The aim of this paper is to analyze PCA and its different variants Segmented-PCA (SPCA), Folded-PCA (FPCA), and its nonlinear approach Kernel-PCA (KPCA) for effective feature extraction and classification of HSI. Moreover, the noise adjusted methods Minimum Noise fraction (MNF) and its variants segmented MNF is also studied for comparing the feature extraction methods. For comparing the robustness of the studied methods, two real HSI is used for the experiments. The experiments show that the classification accuracy of the MNF method are 95.94% and 97.61% for AVIRIS and HYDICE datasets respectively which outperforms that other PCA based methods.

In recent years, the classification of Hyper Spectral Image (HSI) is a big challenge for its multidimensional property. So it is burning question to reduce the dimension of HSIs. There are several ways to reduce the dimension of hyperspectral images like Principle Component Analysis (PCA), Kernel Principle Component Analysis (KPCA), Kernel Entropy Component Analysis (KECA) and so on. In this paper, we proposed a modified version of KPCA using multiple kernels like Linear, Radial Basis Function (RBF), Cosine, Sigmoid. Then fused their spectral and special properties by doing the classification of the HSIs using Hybrid Spectral Net (HybridSN) Model which is a recently trending modified deep neural network algorithm of Convolutional Neural Network (CNN). Finally, this paper demonstrates experimental results to show the effects and performance on classification of using different kernels of KPCA algorithm with other algorithms such as Non-negative Matrix Factorization(NMF), Independent Component Analysis (ICA) and Singular Value Decomposition(SVD) on well-known hyperspectral dataset.

This paper is concerned about the detection procedure of drowsiness that causes fatal road accidents leading to death. Increasing lack of awareness of traffic rules is doubling the number of accidents daily. However, detection and indication of driver fatigue is an active area of research. In this concussion, both inside and outside individuals of the car are victimized. However, prevention of drowsiness requires a technique to detect the deterioration legitimately along with a warning mechanism of the vehicle operator. Although the existing solutions are created using some distinctive methods, there are some problems such as costly sensors and handling of information. The objective of this research is to create an improved, innovative, cost efficient and real time strategy for solving this problem of blinking, yawn, and head bending. A pre-trained model by a histogram-oriented gradient (HOG) and a linear vector support machine (SVM) extracts the eye, nose and mouth position and assesses the eye aspect ratio (EAR), moutt opening ratio (MOR) and nose length ratio (NLR). These pieces of information are then compared with the value threshold adapted from the sleeping or drowsy face models aspect ratio data set.

This paper is concerned about the methods of road safety by addressing potential causes such as drowsiness and inebriation maintaining a strict schedule by recognizing the driver's face. Increasing unawareness towards traffic rules yields more and more accidents by the day. Drowsiness results from the monotony towards driving and inebriation results from the unawareness or unwillingness to abide by the traffic rules. This conundrum victimizes both the person inside and outside the vehicle. However, drowsiness prevention requires a method of detecting the deterioration of the vehicle operator's attention in a legitimate way along with an alerting mechanism. Though the existing solutions are developed through some unique methods, there are still some issues addressing yawn, blink issues, and alcoholism which have not been considered in their systems. This study aims to develop an improved and innovative approach to solving this issue. A train model developed by histogram oriented gradient (HOG) and linear support vector machine (SVM) extracts the eye and mouth position and calculates the eye aspect ratio (EAR), mouth aspect ratio (MAR) and MQ-3 sensor for measuring the degree of concentration of alcohol in the air. These data are then compared with the threshold value which is developed from a data-set of the aspect ratio of sleeping or drowsy face models.

Finding an informative subspace of the original in hyperspectral images has become very essential due to its comprehensive applications in ground object recognition. Information extraction from hyperspectral images is a challenging work on account of its high correlation among the image bands in both the spatial and spectral redundancy. A feature reduction approach combining both the feature extraction and feature selection is proposed in this paper. A combination of Minimum Noise Fraction (MNF) and Mutual Information (MI) is proposed to select the subspace of the original datacube with regard to achieve improved classification accuracy. In the proposed method, feature ranking is improved by scaling the mutual information to a specific range in order to avoid redundant features. The proposed technique (MNF-nMI) is tested on two hyperspectral images captured by NASA AVIRIS sensor and HYDICE sensor. The experimental results typically indicate the noticeable improvement pertaining to classification accuracy. The proposed technique shows the classification accuracy of 96.8% and 99.3% on AVIRIS and HYDICE hyperspectral data respectively which is greater than the conventional methods studied.

This paper proposed an improved approach to enhance the quality of underwater images without the aid of any specialized hardware. The proposed method consists of three steps including color correction, contrast synthesis and dehazing. The color correction removes the color cast problem, contrast synthesis removes under-exposure problem and dehazing removes the fuzz problem. In the proposed method, color correction, contrast synthesis and dehazing are developed based on a statistical method, Retinex-model and utilizing the dark channel prior information respectively. After removing these three difficulties the quality of the enhanced underwater images is compared with the baseline approaches based on the value of chroma, contrast and saturation. The proposed method obtains Underwater Color Image Quality Evaluation (UCIQE)value 0.66574 which is the best among the methods compared.

In remote sensing image classification, really it is an intimidating when kernel supervised learning approaches stands in need of adequate amount of training samples. Often there is a vital problem for definition and acquisition of reference data. For Hyperspectral image classification, improved spectral information is required to make it suitable for ground object identification. In this paper, Support Vector Machine with RBF kernel (KSVM) and the spectral angle mapper (SAM) are used for performance comparison in terms of classification accuracy in Hyperspectral image classification. Kernel support vector machine is more preferable for the mastery to generalize better hyperplane when limited availability of training samples and separate the classes competently in a new dimension feature space. Experiments are performed on NASA Airborne Visible Infrared Spectrometer (AVIRIS) image and it shows KSVM outperforms SAM and obtains the highest accuracy. Due to more well-conditioned against the outliers, KSVM significantly reduced the classification complexities than SAM.

Subspace detection is an essential step which is used as a preprocessing for the task of hyperspectral image classification, and ground surface identification. An informative subspace can be obtained through feature extraction/feature selection or using both. This paper proposed an efficient subspace detection technique using a both segmented principal component analysis (SPCA) and normalized mutual information (NMI) measure. At first, the original dataset is partitioned into several groups using NMI measure and then perform the principal component transform (PCT) on each group. Finally, the NMI is utilized to select the most informative images to obtain a resultant subspace and this method is named as (SPCA-nMI). The proposed method is tested on two real hyperspectral images, the experimental results shows the superiority of the proposed approach and obtain 95.47% classification accuracy on dataset 1 and (99.026%) on dataset 2 which is best among the methods studied.

Hyperspectral images are extensively used, now-a-days, for governing several geo-spatial fields. Due to the high number of dimensions or spectral bands the classification accuracy demotes which is known as the “Hughes Phenomenon” or the “Curse of Dimensionality”. To overcome this obstacle dimensionality reduction approaches need to be performed or simply the number of the spectral bands needs to be reduced. As a preprocessing step feature extraction or feature selection can be performed that reduces the computational complexity of the hyperspectral data classification. Highly correlated features are omitted and only the informative ones are considered for the classification. In this paper, we considered the feature extraction approaches, namely, the Principal Component Analysis, the Linear Discriminant Analysis and both of them combined. We have applied these feature extraction methods on the dataset individually and then classified the dataset using Support Vector Machine classifier. The experimental results show that the LDA approach provides the best accuracy (86.53%) among the three dimension reduction techniques applied. All the files and codes used in our work can be found at https://github.com/joybiS31/multiclassSVM classification u sing PCA LDA/

In many computer vision based problems, multiview 3D object retrieval is very useful with many application possibilities. Actually multiview 3D object is represented by a set of different views of 2D images. There are many hand-crafted features extraction techniques. Rather than using them, deep embedding network and autoencoder are used to extract features and calculate Euclidean distance to measure the similarity. This paper emphasizes on the process of retrieving 3D object from multi-view 2D images. Two established deep learning based solutions are used to retrieve images of multi-view 3D object. Finally different evaluation metrics are used to compare image retrieval performance accuracy & compare computation time and space complexity for both autoencoder and deep embedding network techniques. Here, dimension reduction algorithms PCA & t-SNE are also used to interpret the retrieval results. The experimented results show that deep embedding network gained 98% accuracy & autoencoder gained 97% accuracy to retrieve multi-view 2D images using RGB-D dataset.

Information extraction from spatial big data faces challenges in data relevancy analysis and heterogeneous data modeling. When the interested targets are more than one, the relevant analysis is often compromised. In this paper, a one-class oriented approach for effective feature selection and classification of remote sensing images is proposed. Mutual information (MI) is used as the feature selection criterion to cope with a wide range of data types. Then a cluster space (CS) representation is applied to model multimodal data and classifies each target class in turn. Hyperspectral and LiDAR data sets were used in the experiments. The test results demonstrate the advantage in terms of classification accuracies by focusing on one class at a time as compared to considering all classes simultaneously in classification.

Achieving high classification accuracy in hyperspectral image classification is a challenging task. This problem can be addressed by reducing the irrelevant features for the task of classification. Principal Component Analysis (PCA) is a popular feature extraction technique but it depends solely on global variance which makes it limited for some application. To address this, a target class oriented feature reduction method is proposed which incorporates the normalized Mutual Information (NMI) over PCA images to maximize the relevance of the selected subspace. Experimental analysis is performed to assess the effectiveness of the proposed method and the selected subspace is evaluated using kernel Support Vector Machine (KSVM) classifier. The proposed approach can achieve 96.57%classification accuracy on real hyperspectral data which is better than the standard approaches studied.

Tumor is a pre-stage of cancer which has become a serious problem in this era. Researchers are trying to develop methods and treatments to round it. Brain tumor is an exceptional cell enhancement in brain tissue and may not always be seen in imaging tricks. Magnetic Resonance Imaging (MRI) is a technique which is applied to display the detailed image of the attacked brain location. The medical imaging trick plays a significant behavior in identification of the disease. In this paper, the brain MRI image is chosen to investigate and a method is targeted for more clear view of the location attacked by tumor. An MRI abnormal brain images as input in the introduced method, Anisotropic filtering for noise removal, SVM classifier for segmentation and morphological operations for separating the affected area from normal one are the key stages if the presented method. Attaining clear MRI images of the brain are the base of this method. The classification of the intensities of the pixels on the filtered image identifies the tumor. Experimental result showed that the SVM has obtained 83% accuracy in segmentation. Finally, the segmented region of the tumor is put on the original image for a distinct identification.

Brain is the most precious part of the human body. Therefore, it is entirely necessary to substantially distinguish the different regions of the brain for diagnosing any anomalies in medical science. Most recently, data mining provides some clustering algorithms for efficiently detecting the diverse area of the brain. In this paper, different clustering algorithms for division display have been studied. The essential thought of clustering is to assign the similarity between the distance, which refers to the data to measure the similarity of the size of the data is ordered until all the data gathering is finished. But the primary point is to demonstrate the examination of the different clustering algorithms to discover which algorithm will be most reasonable for the users.

Subspace detection for hyperspectral images is getting more interest now days because of the challenges of dealing with high dimensional feature space for reliable classification. The objective of supervised dimension reduction technique is to find a subspace of reliable features that preserves maximal information about the target objects. Principal Component Analysis and Mutual Information are two well-known feature extraction and feature selection method respectively, however, a combination of both could be a better approach which can significantly improve the feature reduction performances. In this paper, a hybrid approach is proposed which combines both the Principal Component Analysis (PCA) and Quadratic Mutual Information (QMI). The proposed method named (PCA-QMI) is tested on two real hyperspectral datasets and finally the classification accuracy is measured using kernel support vector machine classifier. The proposed method can detect subspace effectively and therefore the classification accuracy achieved is more than 99% which is better than the standard benchmark techniques.

Heart disease is one of the most common causes of death around the world nowadays. Often, the enormous amount of information is gathered to detect diseases in medical science. All of the information is not useful but vital in taking the correct decision. Thus, it is not always easy to detect the heart disease because it requires skilled knowledge or experiences about heart failure symptoms for an early prediction. Most of the medical dataset are dispersed, widespread and assorted. However, data mining is a robust technique for extracting invisible, predictive and actionable information from the extensive databases. In this paper, by using info gain feature selection technique and removing unnecessary features, different classification techniques such that KNN, Decision Tree (ID3), Gaussian Naive Bayes, Logistic Regression and Random Forest are used on heart disease dataset for better prediction. Different performance measurement factors such as accuracy, ROC curve, precision, recall, sensitivity, specificity, and F1-score are considered to determine the performance of the classification techniques. Among them, Logistic Regression performed better, and the classification accuracy is 92.76%.

Remote sensing hyperspectral image (HSI) contains important information of ground surface as a set of hundreds of narrow and contiguous spectral bands. For effective classification of hyperspectral images, feature reduction techniques through feature extraction and feature selection approaches are applied to improve the classification performance. Principal Component Analysis (PCA) is the widely used feature extraction method for dimensionality reduction. In this paper, PCA and its linear variants such as segmented-PCA (SPCA) and folded-PCA (FPCA) together with nonlinear variants kernel-PCA (KPCA) and Kernel Entropy Component Analysis (KECA) have been studied to effectively extract the features for classification task. The feature selection over the new transformed features was carried out using cumulative-variance accumulation based approach except for KECA that employs Renyi entropy based feature selection. The studied methods are compared using real hyperspectral image. The experimental result shows that the classification accuracy of KPCA (95.9245%) and KECA (95.6262%) outperforms FPCA (95.1292%). However, the FPCA provides the less space complexity.

Remote sensing hyperspectral image (HSI) retains significant information of ground surface which is actually acquired as a set of hundreds narrow and contiguous spectral bands. Though it is quite difficult to extract features from these bands, dimensionality reduction techniques through feature extraction and feature selection are used to improve the classification performance of the HSI. Principal Component Analysis (PCA) is the commonly adopted feature extraction technique for dimensionality reduction of HSI. However, PCA can be failure to extract local characteristics of the HSI due to considering global variance. Thus, segmented-PCA (SPCA) and folded-PCA (FPCA) are introduced to effectively extract the local structures in different ways. In this paper, feature extraction using FPCA, termed as segmented FPCA (SFPCA), has been improved through applying it on the highly correlated bands' segments of the real HSI rather than not applying on the whole dataset directly. The feature selection over the new transformed features was carried out using cumulative-variance accumulation based approach. The experimental result shows that the classification accuracy of SFPCA (95.6262%) outperforms conventional FPCA (95.1292%), SPCA (93.837%) and PCA (93.7376%). Moreover, it provides the least space complexity.

Remote sensing hyperspectral image (HSI) contains significant information of ground surface which is actually acquired as a set of immense narrow and contiguous spectral bands. Proper classification approach can only give us the required knowledge from the hundreds of bands of HSI. Though it is quite difficult to extract features from these bands, dimensionality reduction techniques through feature extraction and feature selection are used to improve the classification performance of the HSI. Principal Component Analysis (PCA) is usually adopted as unsupervised linear feature extraction method for feature reduction. However, PCA can be failure to extract local characteristics of the HSI due to considering global variance. Thus, segmented-PCA (SPCA) and folded-PCA (FPCA) are used to efficiently extract the local structures in different ways. In this paper, feature extraction using FPCA, termed as segmented FPCA (SFPCA), has been improved through applying it on the highly correlated bands' segments of the real HSI rather than not applying on the whole dataset directly. The effectiveness of SFPCA is additionally compared with the unsupervised nonlinear feature extraction methods kernel-PCA (KPCA) and Kernel Entropy Component Analysis (KECA). The experimental result shows that the classification accuracy of SFPCA (95.6262%) outperforms conventional FPCA (95.1292%), SPCA (93.837%) and PCA (93.7376%) providing the least space complexity. Moreover, it attempts to fix the nonlinearity like very similar to KPCA (95.9245%) and KECA (95.6262%).

Today's life entirely depends on information, and security in information system is an essential term. Now a days various biometric feature like fingerprint, gait, iris, face etc. are used to secure any system and it is more powerful to use biometric feature instead of using other traditional techniques like password, PIN number etc. In automated personal identification system iris recognition technique is the most reliable authentication technique and iris image segmentation step is important to acquire good accuracy in this technique. But noisy image decrease the accuracy and most of the errors occur in non-iris region. So it is better to avoid segmentation errors by excluding non-iris regions from iris image. On the other hand cluster analysis one of the data mining concepts, is very useful for finding similar groups from a data set. So cluster analysis can be used for finding relevant groups from iris image. Basically k-means clustering algorithm used on segmentation step. In this thesis work another two clustering algorithms has been used for iris image preprocessing on segmentation step to cluster most similar objects together so that non-iris region can be reduced and compare their performance with k-means algorithm to find out the better one.

Multi-temporal Image Compression is now an immerging field considering the fact that terabytes of data is now available for download every day. Evantualy temporal data compression is becoming a critical issue for fast data transmission. Many works have been done regarding compression in the field of satellite images that utilizes the spectral and spatial redundancies using predictive and transformed based procedures for lossless data compression, but, most of the contributions are on individual data or on single data. The main objective of this paper is to exploit the temporal correlation between the images. The recent image will be predicted from the historical image that is already available to the user. This will substantially reduce the load in transmitting the images. This paper actually emphasis on the process of increasing temporal correlation, which consequently improves the compression gain. In sequential transmission, the transmitted data will be used in future as a reference. Therefore, a new lossless approach has been introduced where reversible integer wavelet transformation is used to improve the temporal correlation. The experimented results show that the proposed method outperformed many state of art lossless approaches including JPEG2000.

Hyperspectral image analysis is becoming an important field of research interest because of its wide range of applications in ground surface identification. New technology is being developed to capture hyperspectral images to cover more spectral bands and finer spectral resolution but also increases challenges to process those images for high correlation among data and both the spectral and spatial redundancy. This paper proposed a feature mining approach for the relevant feature selection as well as efficient classification of the hyperspectral dataset. Principal Component analysis and Mutual Information is two widely used feature reduction techniques utilized in conjunction for the feature reduction of the remote sensing data set. The kernel support vector machine classifier is used to assess the effectiveness of the detected subspace for classification. The proposed feature mining approach is able to achieve 99.3% classification accuracy on real hyperspectral data which higher than the standard approaches studied.

Remote sensing hyperspectral images are blessings of technology through which the ground objects can be detected effectively with the cost of computer processing. For classification of hyperspectral images finding an effective subspace is very important to classify them efficiently. In recent years, many researchers have drawn their interest to extract data more effectively from hyperspectral dataset. In this research, an approach has been proposed to find the effective subspace by measuring the relevance of individual features through Cross Cumulative Residual Entropy from the Principal Component images. The Support Vector Machine has been used as the classifier for the assessment of the feature reduction performance. Experiment has been completed on real hyperspectral dataset and achieved 97% of accuracy which is better than the standard approaches studied.

Change detection (CD) of any surface using multitemporal remote sensing images is an important research topic since up-to-date information about earth surface is of great value. Abrupt changes are occurring in different earth surfaces due to natural disasters or man-made activities which cause damage to that place. Therefore, it is necessary to observe the changes for taking necessary steps to recover the subsequent damage. This paper is concerned with this issue and analyzes statistical similarity measure to perform CD using remote sensing images of the same scene taken at two different dates. A variation of normalized mutual information (NMI) as a similarity measure has been developed here using sliding window of different sizes. In sliding window approach, pixels’ local neighborhood plays a significant role in computing the similarity compared to the whole image. Thus the insignificant global characteristics containing noise and sparse samples can be avoided when evaluating the probability density function. Therefore, NMI with different window sizes is proposed here to identify changes using multitemporal data. Experiments have been carried out using two separate multitemporal remote sensing images captured one year apart and one month apart, respectively. Experimental analysis reveals that the proposed technique can detect up to 97.71% of changes which outperforms the traditional approaches.

Change detection from remote sensing images is getting more interest now a days because of abrupt changes in earth surface due to natural disasters or man-made activities. So it's an important research question of how to extract relevant information about the changes due to rainfall, droughts, flooding, destroying land cover areas and so on. This problem has been studied in some research however many of these did not consider the nonlinear relationship while detecting the changes. In this research, above limitation has been addressed and Weighted Normalized Mutual Information (WNMI) is utilized for the improvement. The WNMI technique has been applied between the reference and target images to find out the changes. Thus the changes between every object of the given dataset have been identified and able to observe the damage of any specific area as well as its subsequent recovery. Weighting has been done to count significance at the pixel level. The proposed technique can detect the changes more effectively than the traditional mutual information approach. Experimental analysis is carried on real remote sensing images and it is found that the proposed method can detect more than 96% of changes which is much better than the standard benchmark techniques.

Modern world has become more dependent on electronics and hence speed is a major factor in the field of their functionalities. Modern CPUs work lot faster and efficiently than older versions. Still humans require more and more time efficiency in their daily computational works. In this paper, the main focus is on the increase of time efficiency in computing. Hence this paper shows a time performance comparison between FPGA and CPU implementation. In this regard, Booth's multiplication algorithm has been implemented on both CPU and FPGA to compare the running time. The FPGA implementation is found out to be around 9 times faster than that of a modern CPU implementation.

Finding the most informative features from high dimensional space for reliable class data modeling is one of the most challenging problems in hyperspectral image classification. The problem can be address using two basic techniques: feature selection and feature extraction. One of the most popular feature extraction methods is Principal Component Analysis (PCA), however its components are not always suitable for classification. In this paper, we present a feature reduction method (MI-PCA) which uses a nonparametric mutual information (MI) measure on the components obtained via PCA. Supervised classification results using a hyperspectral data set confirm that the new MI-PCA technique provides better classification accuracy by selecting more relevant features than when using either PCA or MI on the original data.

Nowadays it is obvious that speakers can be identified from their voices. In this paper detail of speaker identification from the real-time system point of view is described. Firstly, it have been reviewed the well-known techniques used in speaker identification then the details of every step in identification process and explains the ideas, which leaded to these techniques. We start from the basic definitions used in DSP, then we move to the feature extraction step. Being widely used in pattern recognition tasks, neural networks have also been applied in speaker recognition. In this study, we developed a text-independent speaker identification system based on Back-propagation Neural Network (BPN). BPNs supply flexibility and straightforward design which make the system easily operable along with the successful classification results. In order to analyze the system in practice we made appropriate software and using real data we ran several tests. Empirical results show that proposed approach greatly improves identification speed in feature matching step. From the experiment it is found that the system correctly identify 96% of the speakers, using less then one second of test samples from each speaker.