Brain tumour is a group of tissue that is prearranged by a slow addition of irregular cells. It occurs when cell get abnormal formation within the brain. Recently it is becoming a major cause of death of many people. The seriousness of brain tumor is very big among all the variety of cancers, so to save a life immediate detection and proper treatment to be done. Detection of these cells is a difficult problem, because of the formation of the tumour cells. It is very essential to compare brain tumor from the MRI treatment. Brain tumor is classified into three types: Normal, Benign and Malignant. The neural network will be used to classify the phase of brain tumor that is benign, malignant or normal. Feature extraction by using the Gray Level Co-Occurrence Matrix (GLCM). Image recognition and image compression is done by using the Principal Component Analysis (PCA) method and also large dimensionality of the data is reduced. Automatic brain tumor stage classification is done by using probabilistic neural network (PNN). Segmentation process is done by using K-means clustering algorithm and also detects the brain tumor spread region. Numbers of defect cells are finding in the spreaded region. PNN is fastest technique and also provide the good classification accuracy. Simulation is done by MATLAB 2013 software.

In Intelligent Transportation System the detection of the number plate of fast moving vehicles is an important part. This paper presents a method for detecting vehicles, which violates rules in real time traffic scenario. One of the problems is to recognize the license plate due to fast motion and uncertain condition. Firstly, taking the fast moving vehicle from camera kept in different position and angles and convert video into image frames. After removing motion blur in the image frame, detect the license plate from the front or the rear of a car by using morphological operation. This experiment results show that this method used to recognize the moving vehicle's license plate without much effort.

Background subtraction is the first processing stage in video surveillance. It is a general term for a process which aims to separate foreground objects from a background. The goal is to construct and maintain a statistical representation of the scene that the camera sees. The output of background subtraction will be an input to a higher-level process. Background subtraction under dynamic environment in the video sequences is one such complex task. It is an important research topic in image analysis and computer vision domains. This work deals background modeling based on modified adaptive Gaussian mixture model (GMM) with three temporal differencing (TTD) method in dynamic environment. The results of background subtraction on several sequences in various testing environments show that the proposed method is efficient and robust for the dynamic environment and achieves good accuracy.

We present a scalable object tracking framework, which is capable of removing shadows and tracking the people. The framework consists of background subtraction, fuzzy based shadow removal and boundary tracking algorithm. This work proposes a general-purpose method that combines statistical assumptions with the object-level knowledge of moving objects, apparent objects, and shadows acquired in the processing of the previous frames. Pixels belonging to moving objects and shadows are processed differently in order to supply an object-based selective update. Experimental results demonstrate that the proposed method is able to track the object boundaries under significant shadows with noise and background clutter.

Automated analysis of crowd activities using surveillance videos is an important issue for communal security, as it allows detection of dangerous crowds and where they are headed. Public places such as shopping centres and airports are monitored using closed circuit television (CCTV) in order to ensure normal operating conditions. Computer vision based crowd analysis algorithm can be divided into three groups; people counting, people tracking and crowd behaviour analysis. In this paper the behaviour understanding will be used for crowd behaviour analysis. The purpose of these methods could lead to a better understanding of crowd activities, improved design of the built environment and increased pedestrian safety.

We have proposed a method for abnormal crowd detection and tracking in this paper. Automated analysis of crowd activities using surveillance videos is an important issue for communal security, as it allows detection of dangerous crowds and where they are headed. Public places such as shopping centres and airports are monitored using closed circuit television in order to ensure normal operating conditions. Computer vision based crowd analysis algorithm can be divided into three groups; people counting, people tracking and crowd behaviour analysis. In this paper the behaviour understanding will be used for crowd behaviour analysis. The purpose of these methods could lead to a better understanding of crowd activities, improved design of the built environment and increased pedestrian safety. The experimental results show that the proposed method achieves good accuracy

A new loom of outdoor scene image segmentation algorithm is based on the region amalgamation. Here we are going to identify both structured (e.g. buildings, persons, car, etc.) and unstructured background objects (sky, road, grass, etc.) which are containing the some characteristic based on color, intensity, and texture in sequence. Our main aim is to solve the over segmented objects and strong reflection of objects. These problems are solved by using SRM (Statistical Region Merging) algorithm. In pre-processing the input image is converted into CIE (Commission Internationalde Eclairage) color space technique. Then bottom-up segmentation process is used to capture the structured and unstructured image characteristics. Another process is the Ada boost classifier which is used to classify the background objects in outdoor environment scenes. Ada boost is focused on difficult patterns. Then the contour maps are used to detect the boundary energy. Boundary detection test is the grouping of objects with a pair of connected neighboring regions. In this paper we have used an experimental result of two databases (Gould data set and Berkeley segmentation data set) and provide accurate segmentation using region merging. Finally the statistical region merging provides the groupings of images to identify the computer vision.

In video surveillance systems, background subtraction is the first processing stage and it is used to determine the objects in a particular scene. It is a general term for a process which aims to separate foreground objects from a relatively stationary background. It should be processed in real time. It is obtained in human detection system by computing the variation, pixel-by-pixel, between the current frame and the image of the background, followed by an automatic threshold. This paper proposed a K means based background subtraction for real time video processing in video surveillance. We have analyzed and evaluate the performance of the proposed method, with standard K-means and other background subtractions algorithms. The experimental results showed that the proposed method provides better output.

Multi-camera applications are numerous and each application has its specific means of acquisition representation and display. The quality of the perceived multi view video image is dependent on the means of presentation. The most of the fundamental problem in MIQM (Multi-camera Image Quality Measure) is finding the image quality measure. A multi-camera image quality measure MIQM is distortions in multi-camera system can be classified into geometric and photometric distortions. Geometric distortion in multi-camera system is defined as structural disparity such as discontinuity and misalignment in the observed image due to geometric error. Geometric error can occur during mapping which may include rotation and translation. Photometric distortion in single camera is defined as the degradation in perceptual feature that are known to attract visual attention such as noise blur and blocking artifacts. We propose multi-camera image quality measure is combination of the three index measure is necessary to capture the impact of three distortions on multi view perception. The measure was designed to capture the visual effects of artifacts introduced at the acquisition and pre compositing process to predict the composed image quality.