I have a collection of photographs depicting various objects taken from a very large dataset. Each image contains a different number of objects, and the same object can be depicted slightly differently. I am able to detect the objects in the images and calculate a measure of similarity between any two objects. Each object in each image is numbered internally from 1 to the total number of objects in the image. My goal is to identify unique objects and match them to their internal numbering in each image. For example, if I have five images, I want to find the "spoon" object and assign it the values [1, 4, 0, 7, 2], with the understanding that it may not appear in all images. I believe the Hungarian algorithm may help me, but I am not sure how to proceed.
Asked
Active
Viewed 35 times
