Using CNN as a optimiser for finding ideal features?

Question

I have a task i need to solve using computer vision, but I can't figure out what kind of feature would be ideal to extract. I could possibly train a CNN network, which could do the classification, is it then somehow possible to learn what kind of features it uses, and what is used to discriminate class A from class b? And then do the same just using openCV or something similar?

Answer 1

是的，你可以这样做。实际上，这正是CNN所做的，他们学习的功能可能最适合您的特定数据和任务，然后您可以使用经过培训的网络作为功能提取器。

这是CNN的常见用法，而OpenCV对DNN module中的神经网络的支持有限。