Wild Animal Classifier Using CNN

TL;DR

This paper discusses the use of convolutional neural networks (CNNs) combined with image processing techniques like segmentation to improve wild animal classification accuracy for environmental monitoring.

Contribution

It introduces a methodology integrating image segmentation with CNNs to address heterogeneity in image sources, enhancing classification performance.

Findings

Segmentation improves CNN accuracy in wild animal classification.

Preprocessing reduces heterogeneity, leading to better feature extraction.

The approach enhances tracking and protection efforts for wildlife.

Abstract

Classification and identification of wild animals for tracking and protection purposes has become increasingly important with the deterioration of the environment, and technology is the agent of change which augments this process with novel solutions. Computer vision is one such technology which uses the abilities of artificial intelligence and machine learning models on visual inputs. Convolution neural networks (CNNs) have multiple layers which have different weights for the purpose of prediction of a particular input. The precedent for classification, however, is set by the image processing techniques which provide nearly ideal input images that produce optimal results. Image segmentation is one such widely used image processing method which provides a clear demarcation of the areas of interest in the image, be it regions or objects. The Efficiency of CNN can be related to the preprocessing done before training. Further, it is a well-established fact that heterogeneity in image sources is detrimental to the performance of CNNs. Thus, the added functionality of heterogeneity elimination is performed by the image processing techniques, introducing a level of consistency that sets the tone for the excellent feature extraction and eventually in classification.