COMMENTS:
SUMMARY:
This paper describes a set of FORTRAN programs created for sketch recognition called the HUNCH system. The programs work together to perform difference interpretations of the parts of a sketch. The STRAIT program uses the minima of the speed function to locate the corners in a sketch. Anything that shows a gradual increase or decrease in speed was passed onto the CURVIT program to further refine the results.
HUNCH faced certain challenges such as latching which is the process of joining endpoints that are in close proximity of each other. The latching in the STRAIT program was improved and resulted in STRAIN. The authors discuss other challenges to interpretation such as double lines. In application, HUNCH uses a context-free data structure to assign meanings to the parts of a sketch.
DISCUSSION:
The programs presented in this paper were a significant contribution to sketch recognition at the time they were developed. I haven’t come across any works prior to this that feature corner finding methods as successful as the one presented here (someone please correct me if there’s another paper out there that I’m not considering).
The approach presented for an interactive system seems to suggest a certain level of machine learning through input from the user. However, I think the authors could have mentioned how much input from the users was required for the system to make a successful interpretation.
On a side note, I thought the text in the paper was difficult to read. It may have been the quality of the file itself, I don’t know.
I see the same problem, you mentioned only the first system they developed. What about the so called new system after CURVIT, STRAIN, HUNCH? Everything is fuzzy after somewhere in the middle of the paper.......Yes I agreed, the paper seems to me much of an abstract view of the system that they developed than a detailed oriented one. May be this was just some preliminary work of it......
ReplyDelete