دانشگاه گیلان
معاونت پژوهش و فناوری دانشگاه گیلان
انتشارات دانشگاه گیلان

 آمار

تعداد نشریات31
تعداد شماره‌ها797
تعداد مقالات7,617
تعداد مشاهده مقاله29,036,234
تعداد دریافت فایل اصل مقاله7,670,728
Mosafer, Hediyeh, Taherpour Gelsefid, Homa, Ghozat, Rana, Azhdehnia, Armin, Ghofrani, Javad, Kozegar, Ehsan. (1404). Nose-to-ID: A Deep Learning Framework for Dog Identification Using Nose-Print Biometrics. فیزیولوژی و بیوتکنولوژی آبزیان, (), -. doi: 10.22124/cse.2025.30957.1110
Hediyeh Mosafer; Homa Taherpour Gelsefid; Rana Ghozat; Armin Azhdehnia; Javad Ghofrani; Ehsan Kozegar. "Nose-to-ID: A Deep Learning Framework for Dog Identification Using Nose-Print Biometrics". فیزیولوژی و بیوتکنولوژی آبزیان, , , 1404, -. doi: 10.22124/cse.2025.30957.1110
Mosafer, Hediyeh, Taherpour Gelsefid, Homa, Ghozat, Rana, Azhdehnia, Armin, Ghofrani, Javad, Kozegar, Ehsan. (1404). 'Nose-to-ID: A Deep Learning Framework for Dog Identification Using Nose-Print Biometrics', فیزیولوژی و بیوتکنولوژی آبزیان, (), pp. -. doi: 10.22124/cse.2025.30957.1110
Mosafer, Hediyeh, Taherpour Gelsefid, Homa, Ghozat, Rana, Azhdehnia, Armin, Ghofrani, Javad, Kozegar, Ehsan. Nose-to-ID: A Deep Learning Framework for Dog Identification Using Nose-Print Biometrics. فیزیولوژی و بیوتکنولوژی آبزیان, 1404; (): -. doi: 10.22124/cse.2025.30957.1110

Nose-to-ID: A Deep Learning Framework for Dog Identification Using Nose-Print Biometrics

Computational Sciences and Engineering
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 04 تیر 1404
نوع مقاله: Original Article
شناسه دیجیتال (DOI): 10.22124/cse.2025.30957.1110
نویسندگان
Hediyeh Mosafer1؛ Homa Taherpour Gelsefid2؛ Rana Ghozat2؛ Armin Azhdehnia2؛ Javad Ghofrani3؛ Ehsan Kozegar* 4
1Department of Computer Engineering, Faculty of Technology and Engineering- East of Guilan, University of Guilan, Guilan, Iran.
2Department of Computer Engineering, Faculty of Technology and Engineering- East of Guilan, University of Guilan, Guilan, Iran
3Department of Computer Science, University of Applied Sciences Bonn-Rhein-Sieg, Germany
4Faculty of Technology and Engineering, University of Guilan
چکیده
Accurate identification of individual dogs plays a crucial role in various applications including pet recovery, veterinary management, and animal welfare. This study proposes a fully automated dog identification framework based on unique nose-print biometric patterns, leveraging deep learning techniques to overcome limitations of traditional identification methods. The proposed approach processes user-submitted videos by selecting the most frontal frame via head pose estimation, detects the nose region using a fine-tuned YOLOv8 model, and extracts discriminative embeddings through a multi-resolution ResNeSt-based convolutional network enhanced with advanced augmentation strategies. The resulting embeddings are fused to produce robust identity descriptors capable of distinguishing between thousands of individual dogs. Experimental results demonstrate the system’s efficacy under real-world conditions, emphasizing its potential for practical deployment in pet identification and management systems.
کلیدواژه‌ها
Dog identification؛ Pet identification System؛ Nose-print biometrics؛ Dog nose print؛ Animal re-identification؛ Dog Nose Detection
آمار
تعداد مشاهده مقاله: 23


سامانه مدیریت نشریات علمی. قدرت گرفته از سیناوب