Reputation: 73
I am a newbie in image processing, I need to find different objects in an image (for example a room image) and be able to distinguish these objects and color them with distinct colors, I started with canny edge detection to find out different edges of the objects but in order to distinguish different objects what do I do next?
Upvotes: 0
Views: 72
Reputation: 1295
If you want to detect objects, you should think more than just image processing. The detecting object process is a long process.
Let's start with detecting that is an image a hotdog or not hotdog? Let me summarize the steps;
If you want to detect hotdog from an image which contains another objects too (i.e. chair, table, coke and etc.), you should perform sliding window approach to detect hotdog and draw bounding box on it.
The state of the art in object detection is Deep Learning. You can train CNN to interpret images but it requires tons of works to train it. You can use trained neural nets, for example TensorFlow's trained neural nets, here is a demo video about it. You can use it to detect any different kind of object which are in your room image.
Upvotes: 1