Selective Search
Selective search is a greedy algorithm that combines smaller segmented regions to generate region proposals. This algorithm takes an image as input and output generates region proposals on it. This algorithm has the advantage over random proposal generation in that it limits the number of proposals to approximately 2000 and these region proposals have a high recall.
Algorithm
- Generate initial sub-segmentation of the input image.
- Combine similar bounding boxes into larger ones recursively
- Use these larger boxes to generate region proposals for object detection.
In Step 2 similarities are considered based on color similarity, texture similarity, region size, etc. We have discussed the selective search algorithm in great detail in this article.
R-CNN | Region Based CNNs
Since Convolution Neural Network (CNN) with a fully connected layer is not able to deal with the frequency of occurrence and multi objects. So, one way could be that we use a sliding window brute force search to select a region and apply the CNN model to that, but the problem with this approach is that the same object can be represented in an image with different sizes and different aspect ratios. While considering these factors we have a lot of region proposals and if we apply deep learning (CNN) to all those regions that would computationally very expensive.
Ross Girshick et al in 2013 proposed an architecture called R-CNN (Region-based CNN) to deal with this challenge of object detection. This R-CNN architecture uses the selective search algorithm that generates approximately 2000 region proposals. These 2000 region proposals are then provided to CNN architecture that computes CNN features. These features are then passed in an SVM model to classify the object present in the region proposal. An extra step is to perform a bounding box regressor to localize the objects present in the image more precisely.