Comments on others
Danielle
Summary
In this paper recognition is based upon a constellation model or `pictorial structure' is used to aid in recognition. This basically implies that the recognition is not only based on the features of individual shapes but in the context around them. The distance and position of each recognized subshape relative to the others becomes important in labeling it as one thing or another. Some of the shapes are mandatory and some are optional, in the example of a model constellation of a face the mouth, eyes and nose are mandatory and the ears can be modular leading to the model shown in the figure below. In this case individual and pairwise features are calculated to process recognition, but the pairwise features are only calculated between mandatory parts to reduce time complexity. Also mandatory labels are assigned first in order to provide a better context to the usually larger number of optional parts.
Discussion
This paper is a very good example of the use of context in sketch recognition. In this case shape labeling is not only made based on geometric features of individual shapes but also in how they are located relative to each other. Also I find it interesting that it is highly inspired in computer vision, which allows sharing techniques and algorithms in both worlds.
Yeah, I thought this paper was very interesting too. I tried to use context for recognition in the first assignment. You have to make a lot of assumption which can be a good or bad thing depending on the domain. For instance with the model constellation of the face, you have to assume it's not a profile image right?
ReplyDeleteRight, and maybe you can add in new models to recognize orientations, such as the profile view.
ReplyDelete