Create labels or annotation from two color images


I have two categories of images to use in my deep learning model. The firs category is aerial images that contain roads (such as road-1.jpg). The second category is two color images that contains road and non-road areas (such as annotation-1.jpg ). I want use second category for labels. So how can I create labels or annotation from second category images.I know there are some image cutting tools. But I'm looking for a tool that does this automatically by using the color information in the images. For example, I want to automatically create label map for the red areas in annotation-1.jpg. In addition, I am going to use the Python programming language and the Tensorflow library.

road-1.jpg annotation-1.jpg


Posted 2019-08-31T18:34:15.643

Reputation: 1

I'm not sure I can understand the question the way it is asked now. – Dr. H. Lecter – 2019-08-31T22:27:59.307

Dear @Dr. H. Lecter, I have added some details. – fdas – 2019-09-01T15:20:50.733

No answers