Computer vision is one of the most important technology emerging in the IT market. Computer vision is a way to provide a powerful ability to see and interpret the real-time objects to the computer just like us or possibly even better than us. An image segmentation is the key processes in machine vision. It is the method of separate a high quality picture into non-overlapping multiple regions to get more precise and significant result. This technique provide us much more granular and reliable information about images like shape, color, and texture, etc. Image segmentation makes a huge impression in Image compression or Object detection techniques, Content-based image retrieval, Video surveillance, Medical imaging, and Traffic control system, etc. It is efficient to process small segments of images one by one to gather information and renounce the regions without information than to process an entire image for particular information. So, image segmentation is help us to dividing image into small segments for advance processing. We can divide a digital image using properties of images such as pixel values, intensity value, texture, shape, etc. So, we can achieve image segmentation by segmenting the images based on these properties. There are many techniques through which one can achieve image segmentation. Here, we discussed multiple techniques apply to achieve image segmentation and compare their benefits and drawbacks followed by the conclusion.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.