Description

Identification of Femour and Tibia from the knee images was helpful in identification of knee diseases in images. One of the important technologies for image processing is image segmentation. The complexity of image content is still a big challenge for carrying out automatic image segmentation. A lot of work shows that the user guidance can help to define the desired content to be extracted and thus reduce the ambiguities produced by the automatic methods. A brief overview of some of the most common segmentation techniques, and a comparison between them comprise this literature review. Image segmentation is the fundamental step to analyze images and extract data from them. The process of the identification of the regions based on the prior knowledge about shape will be more helpful for the identification of the regions that are not in definite geometric shapes. Training data is created by means of the identification of the shapes of the different training samples for the particular datasets. The matching training samples were used for the initial contour for the active contour extraction process. The chan-vese segmentation method is used for this process. The abnormalities in the images can be identified based on the extracted portions in the chan-vese model. The performance of the segmentation process is measured.