상세 보기
Scene Classification Algorithm Based on Semantic Segmented Objects
- Yeo, Woon-Ha;
- Heo, Young-Jin ;
- Choi, Young-Ju;
- Park, Seo-Jeon;
- Kim, Byung-Gyu
Citations
SCOPUS
2초록
Scene classification is one of the important problems in image and video search and recommendation systems. We propose an efficient scene classification method for three different classes by detecting objects in the scene. For detecting objects in an image, pre-trained semantic segmentation model is used. A weight matrix which has bias values to determine a scene class statistically is constructed. Finally, we classify an image into one of three classes (i.e. indoor, nature, city) by using the designed weighting matrix. The proposed method achieved 92% of verification accuracy and improved over 2% when comparing to the existing convolutional neural network (CNN) models. ? 2021 IEEE.
키워드
deep learning; scene classification; semantic segmentation; weighting matrix; Convolutional neural networks; Image segmentation; Search engines; Semantics; Detecting objects; Different class; Scene classification; Segmented objects; Semantic segmentation; Video search; Weight matrices; Weighting matrices; Object detection
- 제목
- Scene Classification Algorithm Based on Semantic Segmented Objects
- 저자
- Yeo, Woon-Ha; Heo, Young-Jin ; Choi, Young-Ju; Park, Seo-Jeon; Kim, Byung-Gyu
- 발행일
- 2021-01
- 유형
- Proceedings Paper
- 저널명
- 2021 IEEE International Conference on Consumer Electronics (ICCE)
- 권
- 2021-January
- 언어
- ENG
- 출판사
- Institute of Electrical and Electronics Engineers Inc.
- 발행국가
- 미국
- ISSN
- E 2158-4001
P 2158-3994