- Exhaustive Search
It aims at finding all the possible locations by systematically enumerating all the possible candidates.
- Segmetation
It uses the image structure to cluster pixels into different regions.
- Selective Search
A method of improving Exhaustive Search by combining Segmetation. One of the method of Region proposal which has Sliding window and Selective search.
https://medium.com/@rishu__2701/mastering-sliding-window-techniques-48f819194fd7
Group similar regions based on color, pattern, size, and shape within the original image.
1) Repeat the oversegmented image several times,
2) group similar regions together,
3) and draw bounding box.
https://developer-lionhong.tistory.com/31
Selective search captures both these features, yet with some additional benefits:
- It captures all scales, addressing the fact that objects in images can present at different sizes and orientations. This step is based on the intuition of the hierarchical structure of images. The creation of initial regions is done via a graph-based greedy algorithm, which starts grouping the most similar regions until the whole image becomes a unique region.
- It diversifies the grouping of regions according to different metrics. Indeed, there is no optimal strategy to group regions together: sometimes might be because of the color, sometimes because of the texture, and so forth. Specifically, the authors introduced four different diversification strategies based on color, texture, size and fill. For each feature, a similarity score (between each couple of regions) is computed. The final similarity score is nothing but a linear combination of the above four similarity scores.
- It is computationally fast, differently from its predecessor exhaustive search.
- Formula
https://sahiltinky94.medium.com/selective-search-for-object-recognitions-eca15dc9c47c
'Deep Learning > Object Detection' 카테고리의 다른 글
| (prerequisite-SPPNet) BOVW(Bag Of Visual Words) (0) | 2024.01.24 |
|---|---|
| R-CNN (0) | 2024.01.23 |
| (prerequisite-R-CNN) Non-maximum Suppression(NMS) (0) | 2024.01.23 |
| (prerequisite-R-CNN) Bounding Box Regression (0) | 2024.01.23 |
| (prerequisite-R-CNN) RoI(Region of Interest), Quantization, RoI Align (0) | 2024.01.20 |