Image processing plays a vital role in many recent computer applications in the association with machine learning technology. The supervised training on dataset of features can only be successful if the segmentation process is accurate in the computer vision phase. The term segmentation is the process of extracting or identification of distinguishable regions in an image. This is performed based on the properties of image pixel intensity values and their proximities. This paper mainly focuses on an investigation of various latest image segmentation techniques performed in the field of computer vision and image processing. Segmentation plays a vital role in computer vision since any fault in segmentation will led to inaccurate extraction of features which results in wrong prediction of the decision support systems.

Abstract-Every year a large number of researches has occurred on image retrieval. CBIR stands for content based image retrieval i.e. images are retrieved from databases on basis of contents rather than textual references. This paper refers to various CBIR methods in medical fields. It also include certain referential points to some feature descriptors that paved way to flourish researches in this fields. . The effectiveness of content based image retrieval lies on the feature extraction method. This paper refers the CBIR methods based on the analysis of feature descriptors. There are different methods which focus on various properties like, intensity, spatio-temporal features etc.