I've been reading a lot about computer vision lately, and while there is a huge amount of info about object classification, and a lot less on object detection, I have not found anything on class-based object detection i.e when I know what I am looking for. For example, looking for cats on a picture. Nowadays you can say if a picture is a cat (object classification), or if the picture has cats among other things. How would I use this knowledge to improve the performance (in both accuracy and speed)?
Somethings that I wouldn't do (but i'm tempted to do):
- Perform a brute-force solution with a binary classifier
- Implement a shape-based selective search and then use a binary classifier
What i would really like to do, but haven't found in the literacy:
- Implement a trainable selective search to find class-based regions of interest.
- Use a binary classifier to check if ROI is in fact the object to be found.