Segmentation is a process of dividing or dividing an image into homogeneous or continuous regions based on similarity. Similarity can be the pixel value of the entire region being somewhat similar, etc. Basically, image segmentation deals with dividing the image into meaningful structures. The main objective of image segmentation is to discover the object from the image. The purpose of image processing task is to find the object of image pixels which is somewhat similar in nature. For example, if we want to find out the length of a car from an image, we first need to find out the set of pixels that represent the car. Another example in medical imaging segmentation is to calculate the volume of the cardiac ventricle, so we first find the pixels that make up the ventricle. The main goal of image segmentation is to simplify or change the representation of an image differently, i.e. more suitable or useful and easily changeable or capable of performing the operation easily. Segmentation is an important process in many image processing and computer vision applications. In computer vision, segmentation is a method of dividing the entire digital image into different regions. Basically segmentation algorithms are mainly based on one of the following properties. • Discontinuity • Similarity Discontinuity Discontinuity refers to the unexpected change in the intensity value of pixels. Similarity Similarity refers to partitioning the image into different regions based on predefined criteria such as Threshold, region merging, region expansion and region subdivision, etc. There are several main approaches to image segmentation. • Region based segmentation • Edge detection based segmentation • Pixel based segmentation • Edge based segmentation… middle of the paper… in image processing, a lot of research has been done in this field but we can't be sure that which segmentation process is effective compared to others. It is also difficult to say whether or not a particular method or algorithm is applicable to an image or set of images. In the current era, a commonly used method is the subjective evaluation for a segment evaluating segmented method. In subjective segmentation evaluation, we manually compare the result of different-different segmentation algorithm. This method is effective but takes more time because manually judging all the methods takes too much time. So this method is limited to some methods. Since each person has their own evaluation criteria or standards for judging the segment, the result of the subjective evaluation method differs from person to person. So this method cannot give unbiased results.