I'm trying to create a object detection model to detect different type of milk. What is the best approach to achieve the result in the picture below? As you can see in the picture, this model did pretty well on locating and detecting different brand of milks. I've tried Faster R-CNN but they mix up products with similar shape really bad(not only on the classifier but also on the religion proposal net). I labeled my training images in the same way as in the picture below. Any help will be appreciated!
1 Answer
Have you tried regression here is a nice project to get you started could you give some feedback on the output?
-
$\begingroup$ I noticed that this repo using feature matching approach. I've tried similar method (with sift) without much success, brands is not always fully visible, or maybe my training image is too blur to extract key points. I will try to use this repo and post my result. Thank for you suggestion! $\endgroup$ Mar 19, 2019 at 14:35