Comments:
Longfei
Summary
Rather than a detailed algorithm, LADDER is a language to describe how sketched diagrams in a domain are drawn, displayed, and edited. And this description can be automatically transformed into domain specific shape recognizer, editing recognizers and shape exhibitors to use for sketch recognition domain.
The LADDER as a language itself consists of following components: Shape definition, Language contents, and vectors.
And the whole recognition system consists of Recognition of primitive shapes, Recognition of domain shapes, Editing recognition and Constraint solver.
The constraints play an important role for the whole system. These constraints can be predefined or user-customized. These constraints limit as well as simplify the way of doing recognition.
Discussion
This method is not a traditional recognition method, like learning features or templates. T
his is like what I have discussed in the previous blog -- the context given by user can be rich enough and well defined, so that, instead of extracting feature and template from input sketch, the system is more robust at interpreting the context.
Undoubtedly, LADDER is a rich and well-defined context, instead of being an augmented context to the traditional method, this idea has opened a new way of doing sketch recognition.
Longfei
Summary
Rather than a detailed algorithm, LADDER is a language to describe how sketched diagrams in a domain are drawn, displayed, and edited. And this description can be automatically transformed into domain specific shape recognizer, editing recognizers and shape exhibitors to use for sketch recognition domain.
The LADDER as a language itself consists of following components: Shape definition, Language contents, and vectors.
And the whole recognition system consists of Recognition of primitive shapes, Recognition of domain shapes, Editing recognition and Constraint solver.
The constraints play an important role for the whole system. These constraints can be predefined or user-customized. These constraints limit as well as simplify the way of doing recognition.
Discussion
This method is not a traditional recognition method, like learning features or templates. T
his is like what I have discussed in the previous blog -- the context given by user can be rich enough and well defined, so that, instead of extracting feature and template from input sketch, the system is more robust at interpreting the context.
Undoubtedly, LADDER is a rich and well-defined context, instead of being an augmented context to the traditional method, this idea has opened a new way of doing sketch recognition.
YES, I really want to see the compiler of LADDER, fantastic.
ReplyDelete