The digital mammogram is a reliable technique to detect early breast cancer without any symptoms. The main aim objective is to classify the mammogram microcalcifications images either benign or malignant. This system consist of three stage that is mammogram enhancement, statistical texture feature extraction and classification. The mammogram images are enhanced by shift-invariant transform which consist of shiftinvariant multi-scale, multi-direction property and classify mammogram pixels into strong edges, weak edges and noise edges. It clearly distinguishes weak edges and noise edges. The moment based statistical texture features are extracted from enhanced images and stored. Finally, these features are fed into SVM classifier to classify the mammogram images.

Databases containing huge amount of genetic information about diseases related to cancer are beyond our capability to analyze and predict the discriminative characteristics of the genes involved. But, this kind of analysis helps to find the cause and subsequent treatment for any disease. In this work, a hybrid model has been developed combining the characteristics of Rough set theory (RST) and Correlation based feature subset (CFS) selection technique which is capable of identifying discriminative genes from the microarray dataset. The model is tested with two publicly available multi-category microarray dataset such as Lung and Leukemia cancer. The study reveals that Rough set theory (RST) is capable of extracting predictive genes in the form of reducts from the subset of genes which are highly correlated with the class but having low interaction with each other. The performance of the model has been evaluated via three learning algorithms using 10-fold cross validation. This experiment has established that the hybrid supervised correlation based reduct set (CFS-RST) method is able to identify the hidden relationships among the genes which cause diseases as well as help to automate medical diagnosis. Finally, the functions of identified genes are analysed and validated with gene ontology website DAVID which shows the relationship of genes with the disease.

Segmentation is a major step in image processing. Segmentation subdivides an image into its constituent regions or objects. Image segmentation segments the object from the background to understand the quality of the image properly and to identify the content of the image carefully. Segmentation can be done as Edge-based segmentation or Region based segmentation. Edge based segmentation considerably reduces the amount of data and filters out useless information, while preserving the important structural properties in an image. Since it is very much needed to have a good understanding of Edge based segmentation. In this paper an attempt is made to study the performance of most commonly used edge detection techniques for edge based image segmentation. The comparisons of these techniques are carried out with a tiles image as an experiment by using MATLAB software.

Human facial expression recognition plays important role in the human mood analysis. Human mood classification is done based on the facial features such as eyes, nose and mouth. The eyes plays dominant role in facial expression.Hence in this paper, instead of considering the features of the whole face, only eyes are considered for human mood classification such as surprise, neutral, sad and happybased on the Susan edge operator.

Image compression is a demanding research area in the field of visual communication, in entertainment, medical and business applications. A new method is proposed using unsupervised learning neural networks and wavelet transformations, since the wavelet transformation uses subband decomposition of an image, it provides enhanced picture quality at higher compression ratios, Also our new algorithm avoids blocking artifacts. In this paper, the performances of haar and DB2 wavelet family are compared with MSE and PSNR. The experiment was carried out with .jpeg images. It is a good reference for application developers to select a good wavelet transformation system.

Extracting Building features from satellite imagery is a vital research area in digital remote sensing field. Building detection & extraction is one of the complex and challenging task in GIS database. But this technique is useful for urban planning and obtaining more timely and accurate information during natural disasters like Earth quakes, Cyclone etc..At the first appearance, buildings are visible as easiest objects to detect and extract. But many difficulties meet on extracting buildings accurately, comprising various outlook angles, roof top complexity, environmental objects(Trees, Roads, vehicles etc) and additional objects which ambiguous the boundaries of the buildings that can be detected. Because of these reasons many algorithms deliver less quality of building extraction and also much time taken for detection. To solve this problem, integrating many efficient algorithms provides better results than individual algorithms. In this study, an enhanced approach for rising the quality and accuracy in detecting & extracting building textures with various and complex angles of roofs from urban area satellite images is proposed. First, an unsupervised image segmentation approach based on SOM(Self organizing maps) is applied to detect roof top regions. Then, the SOM combines with MRF(Markov Random field) spatial constraints for improved segmentation outcomes. This Hybrid approach of SOM and MRF used less data samples in training set. Experimental results obtained that the proposed method achieved excellent result in detecting and extracting rooftops in complex satellite images.

A person’s face provides a lot of information such as age, gender and identity. Faces play an important role in the prediction of gender. In this research, an attempt is made to classify human gender using two level decision based on Neural Networks. In this paper a feed forward propagation neural networks are constructed for human gender classification system for male and female. The performance of the system is further improved by employing second level decision using three sigma control limits applied on the output of the neural network classifier. The efficiency of the system is demonstrated through the experimental results using benchmark database images.

Data mining is the method of extracting the data from large database. Various data mining techniques are clustering, classification, association analysis, regression, summarization, time series analysis and sequence analysis, etc. Clustering is one of the important tasks in mining and is said to be unsupervised classification. Clustering is the techniques which is used to group similar objects or processes. In this work four clustering algorithms namely K-Means, Farthest first, EM, and Hierarchical are analyzedby the performance factors clustering accuracy, number of outliers detected and execution time. This performance analysis is carried out in BUPA (liver disorder) dataset. This work is performed in WEKA data mining tool.

Data Mining extracts the knowledge or interesting information from large set of structured data that are from different sources. Data mining applications are used in a range of areas; they are financial data analysis, retail and telecommunication industries, banking, health care and medicine. In health care, the data mining is mainly used for disease prediction. In data mining, there are several techniques have been developed and used for predicting the diseases that includes data preprocessing, classification, clustering, association rules and sequential patterns. This paper analyses the performance of two classification techniques such as Bayesian and Lazy classifiers for hepatitis and thyroiddataset.This classification task helps to classify the hepatitis dataset into two classes namely live and die and also to classify the thyroid dataset into two classes hyperthyroid or hypothyroid. In Bayesian classifier, two algorithms namely Bayes Net and Naive Bayes are considered. In Lazy classifier we used two algorithms namely IBK and KStar. Comparative analysis is done by using the WEKA tool. It is open source software which consists of the collection of machine learning algorithms for data mining tasks.

Today data mining has become a vital role in all fields. This is because they discover interesting patterns and relationship in a data repository. Data mining is suitable for various fields such as image processing, artificial intelligence, machine learning, statistics and computation capabilities. Image segmentation is the fundamental step in various image processing tasks such as image analysis, visualization, and object representation and so on. The goal of image segmentation is to simplify, to partition image into meaningful regions and easier to analyze. This paper presents an overview of various data mining techniques associated with image segmentation. The data mining techniques such as clustering, classification and association are very easy to implement image segmentation that delivers valuable results. The above techniques are helpful to retrieve information from the images that are used to diagnose diseases, face detection, to improve the segmentation quality and so on. This paper provides crispy report about the data mining techniques and how they fetch the information from the images.

The digital mammogram is a reliable technique to detect early breast cancer without any symptoms. The main aim objective is to classify the mammogram microcalcifications images either benign or malignant. This system consist of three stage that is mammogram enhancement, statistical texture feature extraction and classification. The mammogram images are enhanced by shift-invariant transform which consist of shiftinvariant multi-scale, multi-direction property and classify mammogram pixels into strong edges, weak edges and noise edges. It clearly distinguishes weak edges and noise edges. The moment based statistical texture features are extracted from enhanced images and stored. Finally, these features are fed into SVM classifier to classify the mammogram images.

Databases containing huge amount of genetic information about diseases related to cancer are beyond our capability to analyze and predict the discriminative characteristics of the genes involved. But, this kind of analysis helps to find the cause and subsequent treatment for any disease. In this work, a hybrid model has been developed combining the characteristics of Rough set theory (RST) and Correlation based feature subset (CFS) selection technique which is capable of identifying discriminative genes from the microarray dataset. The model is tested with two publicly available multi-category microarray dataset such as Lung and Leukemia cancer. The study reveals that Rough set theory (RST) is capable of extracting predictive genes in the form of reducts from the subset of genes which are highly correlated with the class but having low interaction with each other. The performance of the model has been evaluated via three learning algorithms using 10-fold cross validation. This experiment has established that the hybrid supervised correlation based reduct set (CFS-RST) method is able to identify the hidden relationships among the genes which cause diseases as well as help to automate medical diagnosis. Finally, the functions of identified genes are analysed and validated with gene ontology website DAVID which shows the relationship of genes with the disease.

Segmentation is a major step in image processing. Segmentation subdivides an image into its constituent regions or objects. Image segmentation segments the object from the background to understand the quality of the image properly and to identify the content of the image carefully. Segmentation can be done as Edge-based segmentation or Region based segmentation. Edge based segmentation considerably reduces the amount of data and filters out useless information, while preserving the important structural properties in an image. Since it is very much needed to have a good understanding of Edge based segmentation. In this paper an attempt is made to study the performance of most commonly used edge detection techniques for edge based image segmentation. The comparisons of these techniques are carried out with a tiles image as an experiment by using MATLAB software.

Extracting Building features from satellite imagery is a vital research area in digital remote sensing field. Building detection & extraction is one of the complex and challenging task in GIS database. But this technique is useful for urban planning and obtaining more timely and accurate information during natural disasters like Earth quakes, Cyclone etc..At the first appearance, buildings are visible as easiest objects to detect and extract. But many difficulties meet on extracting buildings accurately, comprising various outlook angles, roof top complexity, environmental objects(Trees, Roads, vehicles etc) and additional objects which ambiguous the boundaries of the buildings that can be detected. Because of these reasons many algorithms deliver less quality of building extraction and also much time taken for detection. To solve this problem, integrating many efficient algorithms provides better results than individual algorithms. In this study, an enhanced approach for rising the quality and accuracy in detecting & extracting building textures with various and complex angles of roofs from urban area satellite images is proposed. First, an unsupervised image segmentation approach based on SOM(Self organizing maps) is applied to detect roof top regions. Then, the SOM combines with MRF(Markov Random field) spatial constraints for improved segmentation outcomes. This Hybrid approach of SOM and MRF used less data samples in training set. Experimental results obtained that the proposed method achieved excellent result in detecting and extracting rooftops in complex satellite images.

several tools, software and algorithms are proposed by the researchers to develop effective medical decision support systems. New software, algorithms and tools are continuously emerging and upgraded depending on the real time situations. Detecting the heart disease is one of the major issues and it is investigated by many researchers. They have developed many intelligent DSS to improve the diagnosis of medical practitioners. Neural network is one among the tools to predict the heart disease. In this research paper, prediction of heart disease using Neural Network is presented. The proposed system used 13 attributes plus 2 additional attributes obesity and smoking for the heart disease prediction. The experiments conducted have shown a good performance.

Manufacturing, being referred to, as an integrated management process has been radically transformed with the advent of latest technologies and advancements. Data generated by machines are continuously encapsulated and archived in storage systems for analysis and futuristic applications.Such storage necessitates enormous warehouse capacities thus vitalizing methods deployed for storage. Apart from vitality, they serve as critical parameters in improving efficiency, as well. With regard to engine assembly plants, these data can comprehend subtle characteristics of the engine assembly and further their testing processes, as well.Simply put, each engine assembly comprises a minimum of 50 major assembly process parameters and 15 pivotal testing parameters meant for observation and record. Of course, they are of great significance to restore lineage and traceability.Competition demands the use of such legacy data repositories of automotive engine manufacturing companies owing to market demand. Hence trigger the need to deploy appropriate techniques to secure business insights for effective decision-making.Data Mining (DM) is one such subject that mandates a thorough and detailed study. Here in this paper it is handled with the clustering analysis of the subject DM with a sample data volume of five hundred engines’ performance test result files.

several tools, software and algorithms are proposed by the researchers to develop effective medical decision support systems. New software, algorithms and tools are continuously emerging and upgraded depending on the real time situations. Detecting the heart disease is one of the major issues and it is investigated by many researchers. They have developed many intelligent DSS to improve the diagnosis of medical practitioners. Neural network is one among the tools to predict the heart disease. In this research paper, prediction of heart disease using Neural Network is presented. The proposed system used 13 attributes plus 2 additional attributes obesity and smoking for the heart disease prediction. The experiments conducted have shown a good performance.

Human facial expression recognition plays important role in the human mood analysis. Human mood classification is done based on the facial features such as eyes, nose and mouth. The eyes plays dominant role in facial expression.Hence in this paper, instead of considering the features of the whole face, only eyes are considered for human mood classification such as surprise, neutral, sad and happybased on the Susan edge operator.