The 10th International Conference on Next Generation Computing 2024 (2024.11)바로가기
페이지
pp.113-116
저자
Jeonghyun Choi, Daeyong Kim, Chinchol Kim, Seungwoo Choi, Jaeyoo Lee, Seongjoon Yoo
언어
영어(ENG)
URL
https://www.earticle.net/Article/A468822
원문정보
초록
영어
In this study, we analyzed animal registration data to identify the most popular dog breeds raised in South Korea. And then, a dataset was collected for the identified dog breeds and used to perform transfer learning on the YOLOv8 model to develop a breed classification model, and the classification accuracy was measured for each dog breed. The accuracy of classifying dog breeds by breed was confirmed to be at least 84% and up to 100%.
목차
Abstract I. INTRODUCTION II. RELATED WORKS A. Dog Breed Classification Dataset B. Related works C. YOLOv8 III. METHOD A. Data Preparation B. Collect data C. Refine and process data IV. TRAINING MODEL A. YOLO model and hyperparameter B. Results V. IMPLEMENTATION VI. CONCLUSION A. Analysis result B. Future work ACKNOWLEDGMENT REFERENCES