Animal Classification System: A Block Based Approach

TL;DR

This paper presents a block-based animal classification system using segmentation, texture features, and classifiers like KNN and PNN, tested on a custom dataset of 25 animal classes with promising results.

Contribution

It introduces a novel approach combining segmentation, block partitioning, and texture features for animal classification, evaluated with a new dataset.

Findings

KNN classifier achieved high accuracy

Segmentation improved classification performance

Method effective on a diverse animal dataset

Abstract

In this work, we propose a method for the classification of animal in images. Initially, a graph cut based method is used to perform segmentation in order to eliminate the background from the given image. The segmented animal images are partitioned in to number of blocks and then the color texture moments are extracted from different blocks. Probabilistic neural network and K-nearest neighbors are considered here for classification. To corroborate the efficacy of the proposed method, an experiment was conducted on our own data set of 25 classes of animals, which consisted of 4000 sample images. The experiment was conducted by picking images randomly from the database to study the effect of classification accuracy, and the results show that the K-nearest neighbors classifier achieves good performance.