A Review on K-N earest Neighbour Based Classification for Object Recognition

Object recognition has an important role in automation technology. There have been many research and proposed methods to perform object recognition optimally. In object recognition, KNN classifier is one of the popular classification techniques used in object recognition systems. Many kinds of research done to compare the performance of KNN classifier with other classifiers in object recognition systems. However, no works are found reviewing the optimal implementation of the KNN classification method to achieve the best performance in object recognition systems. This paper reviews some research done on KNN based classification for object recognition systems and classify the research based on the type of image dataset used and the image visual features extracted used in the research. A total of 25 papers is classified into 2 main categories: image dataset of objects with cluttered background and image dataset of objects with a discarded background. The research is further classified into several different subcategories: color features, shape features, texture features, edge features, corner features, and interest points. A systematic literature review is done to find the optimal implementation of the KNN classification method in object recognition systems. The result of this paper shows the suitable type of image dataset of objects and the feature extraction technique used in KNN based object recognition, and the performance of KNN classifier in object recognition systems.