Main Article Content
Abstract
In image processing classification is one of the complex tasks. The main objective of classification is to identify the object using features that are extracted and group these features on similarity basis to form clusters. Segmentation plays critical role to distinguish required feature from undesirable features. There are many approaches which are used for this purpose. In this paper various techniques used for segmentation and classification are compared and shortcomings are highlighted. Also the benefits and limitation of these techniques are enlisted in tabular form. Support vector machine with hyperplanes is paid stress upon. This mechanism with small dataset is quite useful but as the size of data increases, SVM performance lags. To overcome the problem, KNN mechanism to form cluster of similar elements and SVM can classify large dataset.