Selective Search
البحث الانتقائي
خوارزمية يدوية لاقتراح المناطق تبدأ بتجزئة الصورة إلى مناطق دقيقة ثم تدمجها تدريجيًّا بناءً على اللون والملمس والحجم، مُنتجةً نحو 2000 مقترح لكل صورة.
A handcrafted region proposal algorithm that starts with fine-grained image segmentation and iteratively merges regions based on color, texture, and size similarity, producing ~2000 proposals per image.
Also translated asالبحث الاصطفائي، خوارزمية البحث الانتقائي
First appears in this corpus in: Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation (2014)
Appears in these papers
- Fast R-CNN2015in the sky ✦
- Fast R-CNN2015in the sky ✦
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks2015in the sky ✦
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014in the sky ✦
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014in the sky ✦
- You Only Look Once: Unified, Real-Time Object Detection2015in the sky ✦