使用深度学习识别场景

Question

What is the approach to recognize a scene with deep learning (preferably Keras). There are many examples showing how to classify images of limited size eg dogs/cats hand-written letters etc. There are also some examples for the detection of a searched object within a big image.

But, what is the best approach to recognize eg is it a class-room, bed-room or a dinning room? Create a data-set with that images? I think no. I think one should train a model with many things, which may appear in the scene, create a vector of the found things in the analysed image and using the second classifier (SVM or simple NN) classify the scene. Is it a right approach?

PS: Actually, I'm facing another problem, which IHMO the same. My "scene" is a microscope image. The images contain different sets of cells and artifacts. Depending on a set, a doctor makes a diagnosis. So I aim to train a CNN with the artifacts, which I extract with a simple morphologicyl methods. These artifacts (eg biological cells) will be my features. So the first level of the recognition - feature extraction is done by CNN, the later classification by SVM. Just wanted be sure, that I'm not reinventing a wheel.

Answer 1

In my opinion the comparison between your room-scenes and the biological scenes differ. Especially since your scene is a microscope image (probably of a limited predefined domain).

In this case, pure classification should work (without seeing the data). In other words the neural network should be able to figure out what it is seeing, without having you to hand-craft features (in case you need interpretability that's a whole new discussion).

Also there are lots approaches for scene understanding in this paper .