• Mrs.Simran Mansoori
• Mr. Rajneesh Pachouri
• Mr. Anurag Jain

: In this research work, issues related in development of an effective and efficient animal detection, classification and tracking system are addressed. Successful attempts towards development of algorithmic models for animal segmentation, animal detection, classification and tracking are made. To support effective classification of animals, we propose two different methods to segment a animal from its background. Evaluation of the proposed animal segmentation algorithm is carried out by the use of region-based performance measures. We also propose a classification model based on different features and classifiers. The different features like color, gabor and LBP are extracted from the segmented animal images. Possibilities of fusing the features for improving the performance of the classification have also been explored. Also extracted features are represented in the form of interval-valued type data to preserve inter and intra class variations of animals. Classification of animals is accomplished using SVM and symbolic classifiers. Furthermore, we propose a model to segment, track and label animals in videos. The proposed system has three stages: segmentation, tracking and labeling. In first stage, an animal video has given as input and frames are extracted from the videos. Segmentation is carried out for all the frames using region merging based segmentation algorithm. In second stage, video frames are used for tracking the animal in entire animal videos. For labeling, gabor features are extracted from the images and stored in the knowledgebase. Classification of animals is accomplished using nearest neighbor classifier. In addition, we propose a system to classify animals in both images and videos using deep learning approach. Initially, features are extracted from images/frames using AlexNet pre-trained Probabilistic neural network. Later the extracted features are fed into multi-class Probabilistic neural network classifier for the purpose of classification.

segmentation,tracking, labeling, neural network, Animal Footprint, Animal-VehicleCollision (AVC), SVM.k contains.

"Foot Prints Image Based Animal Species Classification using PNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 2, page no.c411-c419, February-2024, Available :http://www.jetir.org/papers/JETIR2402248.pdf

"Foot Prints Image Based Animal Species Classification using PNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 2, page no. ppc411-c419, February-2024, Available at : http://www.jetir.org/papers/JETIR2402248.pdf