The computation of saliency from an image and a video is an interesting challenge in image processing and computer vision. Context-aware saliency, which addresses the saliency based on the geometric structure of an image, is known as one of the most powerful schemes for computing saliency. An obstacle of the context-aware scheme is the heavy computation load. We reduce the computational load in a great scale by applying the dart throwing algorithm, which is a widely used stochastic noise generation scheme in computer graphics society.

ABSTRACT   1. 서론   2. 관련 연구   3. 픽셀 샘플링   4. 돌출 특징 측정   5. 구현 및 결과   6. 결론 및 향후 연구   참고문헌

• 윤그림(상명대학교 소프트웨어대학 디지털미디어학부) | Geurim Yun
• 양희경(상명대학교 일반대학원 컴퓨터과학과 박사과정) | Heekyung Yang
• 민경하(상명대학교 소프트웨어대학 디지털미디어학부 조교수) | Kyungha Min Correspondence to