COMMENTS:
SUMMARY:
This paper gives an overview of a constellation model of sketch recognition that uses stroke structure and distance to other known parts in order to identify objects. The strokes are labeled using a label assignment matrix and the remaining strokes in the sketch are identified using stroke label and interaction likelihoods. This method was tested on 5 classes of objects which included sketches of faces and airplanes, etc. Using a multipass threshold technique the recognizer completed it's recognition in less than 2 seconds.
DISCUSSION:
The constellation model assigns possible labels to strokes based on the features of strokes and pairs of strokes. While this work seems to be a novel approach to recognizing a small dataset with a small number of examples, I don’t see how this method of recognition is best applied to objects such as faces which can vary drastically. I also would have like to seen some explanation of how successful the recognizer was.
I think they picked faces because they can be used as a very good and natural example for many characteristics of their recognizer. They have optional shapes, they are very dependent on the location of each part, and they have clearly defined mandatory parts. I was also missing the accuracy indicator they mostly talk about the time it took and isolated cases of mislabelling.
ReplyDelete