This study investigated the use of weakly supervised learning (WSL) and partial annotation-based semantic segmentation for recognizing ingredients in the traditional Korean dish bulgogi. A dataset was created to encompass various cooking stages and imaging conditions, with pixel-level labels generated for major ingredients: beef, onion, green onion, carrot, chili pepper, mushroom, button mushroom, and king oyster mushroom, using partial annotations. To enhance model robustness, data augmentation techniques such as rotation, scaling, horizontal flipping, and color jittering were employed. The DeepLabV3+ architecture was utilized, with ResNet50 and ResNet101 serving as backbone networks. The results demonstrated that ResNet50 provided stable performance with lower computational costs, while ResNet101 achieved higher segmentation accuracy for smaller or visually complex ingredients. Models trained with data augmentation showed improved recall and F1-scores, especially for smaller ingredient classes. Overall, both backbone models exhibited consistent performance across key segmentation metrics, including mean Intersection over Union (mIoU), precision, recall, and F1-score. These findings indicate that WSL, in conjunction with partial annotation, can effectively facilitate ingredient-level segmentation in mixed dishes like bulgogi.

Abstract
서 론
연구내용 및 방법
    1. 연구 개요
    2. 연구자료
    3. 약지도 학습 기반 의미론적 분할 모델의 구축 및 성능평가 방법
결과 및 고찰
    1. 불고기 성분인식을 위한 ResNet50과 ResNet101 비교
    2. 약지도 학습 모델의 성능 평가 지표
    3. ResNet 기반 WSL 모델 성능 비교
    4. 성분 인식의 정성적 비교
    5. 이미지 생성 기반 데이터 증강 효과
결 론
감사의 글
References

• 박영훈(부천대학교 토목공학과 교수) | Young Hoon Park (Professor, Dept. of Civil Engineering, Bucheon University, Bucheon-si 14632, Korea)
• 김영금(주식회사 가가 상무이사) | Young Keum Kim (Executive Director, GaGa Co., Ltd Ansan-si 15399, Korea)
• 최은영(부천대학교 식품영양학과 조교수) | Eun Young Choi (Assistant Professor, Dept. of Food and Nutrition, Bucheon University, Bucheon-si, 14632, Korea) Corresponding author