Clustering based image segmentation for elephant detection

This paper proposes a clustering based image segmentation approach for elephant recognition. Appreciable recognition rate was achieved by k-means clustering technique followed by feature extraction and K nearest neighbour (K-NN) classifier. The k-means algorithm employs the concept of fitness and belongingness to provide a more adaptive and betterclustering process as compared to several conventional algorithms. Elephant shape features are extracted for the recognition. Recognition rate for each class is calculated for performance evaluation. Recognition rate for different K values in K-NN classifier is calculated to find a proper K value for the proposed design.