A pattern recognition approach based on feature-wise comparison

In this paper, an approach to pattern recognition has been proposed. The approach is successful in obtaining good classification accuracies in good time given large variance datasets when compared to some common classification approaches. In Section I an overview of problems of some common classification approaches is given. In Section II the Proposed Approach is discussed. This is followed by Section III in which implementation and testing of the Proposed Approach on several data sets is discussed. A comparison of the performance of the Proposed Approach and some common classification approaches is made. The experimental results show that the proposed approach generally performs better than some common classification approaches by achieving higher accuracies of classification. It is also faster than Backpropagation Approach.