Appearance-and-Spectral-Based Identification System for Penguin Individuals

Youta Noboru¹, Yuko Ozasa¹, Masayuki Tanaka²

¹Tokyo Denki University, ²Institute of Science Tokyo
ITE Transactions on Media Technology and Applications

Individual Penguin Identification Research

Abstract

We present a system for identifying individual penguins in flock images by combining appearance-based penguin detection with RGB images and spectral-based penguin identification with hyperspectral (HS) information. For the spectral-based identification, we propose a classification and ensemble approach inspired by the observation that many animals have similar color patterns. For example, penguins typically have black and white coloration, with consistent color distributions across individuals. The proposed system's effectiveness was experimentally validated with a mean Average Precision (mAP) metric. The proposed Appearance-and-Spectral-Based identification system significantly outperformed conventional appearance-based and spectral-based systems.

Proposed system that effectively integrates appearance and spectral information. It uses RGB images for animal detection and spectral data for individual identification.

Visual comparison of identification results

Visual comparison of penguin identification results across different approaches. Our method demonstrates superior performance in accurately identifying individual penguins across various image resolutions. For the Spectralbased approach, colored areas indicate predicted penguin locations: green for correct identifications and red for misidentifications.

Comparison of mAP, Precision, Recall, and F1-score for penguin individual identification using different approaches across image resolutions.

BibTeX


        @article{noboru2025appearance,
          title={Appearance-and-Spectral-Based Identification System for Penguin Individuals},
          author={Noboru, Youta and Ozasa, Yuko and Tanaka, Masayuki},
          journal={ITE Transactions on Media Technology and Applications},
          volume={13},
          number={2},
          pages={211--220},
          year={2025},
          publisher={The Institute of Image Information and Television Engineers}
        }