Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

Ensemble Learning Algorithm for Cattle Breed Identification using Computer Vision Techniques

Download61 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343338,
        author={Vijayalakshmi  A and Shanmugavadivu  P and Vijayalakshmi  S and Shreyansh  Padarha and Sivaranjani  R},
        title={Ensemble Learning Algorithm for Cattle Breed Identification using Computer Vision Techniques},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={cattle breed identification ensemble learning image segmentation cnn},
        doi={10.4108/eai.23-11-2023.2343338}
    }
    
  • Vijayalakshmi A
    Shanmugavadivu P
    Vijayalakshmi S
    Shreyansh Padarha
    Sivaranjani R
    Year: 2024
    Ensemble Learning Algorithm for Cattle Breed Identification using Computer Vision Techniques
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343338
Vijayalakshmi A1,*, Shanmugavadivu P1, Vijayalakshmi S2, Shreyansh Padarha2, Sivaranjani R3
  • 1: Gandhigram Rural Institute (Deemed to be University), Dindigul
  • 2: Christ (Deemed to be University), Pune Lavasa Campus
  • 3: Veterinary College and Research Institute, Namakkal
*Contact email: vijiranjanis@gmail.com

Abstract

This research paper introduces a robust ensemble learning algorithm tailored for cattle breed identification, making use of the integration of cutting-edge computer vision techniques. The methodology combines Convolutional Neural Networks (CNN), YOLO object detection, canny edge detection, k-means image segmentation, and greyscale imaging to overcome inherent limitations in existing methodologies. Addressing challenges associated with obscured features and the presence of dirt on cows, the framework ensures precise and accurate breed prediction. The algorithm adopts a pipeline, encompassing critical stages such as cow identification, optimized resizing, k-means image segmentation, greyscale conversion, and canny edge detection. Through the union of these techniques, the ensemble learner, employing a voting-based mechanism, achieves outstanding performance in the classification of cattle breeds. This research contributes to the advancement of state-of-the-art methodologies for cattle breed identification, providing a foundation for improved decision-making processes in agricultural and livestock management.