International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Chirp & Click: Dual-Modal Bird Species Recognition using Deep Learning on Image and Audio Inputs |
|---|---|
| ABSTRACT | Bird species recognition is crucial for biodiversity monitoring and conservation. This paper presents Chirp & Click, a dual-modal deep learning system that identifies bird species using both visual and acoustic signals. The system employs MobileNetV2 for image classification and a custom CNN for audio classification using Mel-spectrograms, with a weighted fusion mechanism (α = 0.6 for images, 0.4 for audio). Implemented as an offline Flutter mobile application with TensorFlow Lite, the system achieves 88% test accuracy across 50+ species with sub-second inference, demonstrating 12% improvement over single modalities. Field testing with 12 users confirmed practical usability in remote areas without internet connectivity. |
| AUTHOR | DR. MALIKARJUNA S B, INCHARA P M, VINAYAKA G C, PRAGYA R K, RESHMA K C Department of Artificial Intelligence & Machine Learning, Bapuji Institute of Engineering and Technology (BIET), Davanagere, Visvesvaraya Technological University (VTU), Belagavi, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312005 |
| pdf/5_Chirp & Click Dual-Modal Bird Species Recognition using Deep Learning on Image and Audio Inputs.pdf | |
| KEYWORDS |
