Comments:
Francisco
Summary:
The paper propose a spatial recognition and grouping algorithm for graphics and symbol recognition. It can be treated as an optimization over a large space of possible groupings.
The neighborhood graph
According to the relationship between each pair of strokes, a neighborhood graph is constructed. Each node represents a stroke, and each edge represents the close proximity between two nodes. So there are a few connected subsets. Each connected subsets can produce a lot of groups.
A* based Optimization and Adaboost Recognition
The goal is to find the best grouping among all possible groupings of strokes. A* search is employed to find the best combination according to the combination cost. Adaboost is used to implement recognition on each combination
The algorithm is evaluated in HHReco sketched shape database. And it performs very well, high to 97% accuracy. It is also evaluated on a more complex set of randomly synthesized flowchars, and performs well. But the time cost is too high when recognizing complex symbols.
Discussion:
The grouping technique is very common in sketch recognition. The main problem is how to deal with the huge time cost, especially in some real-time applications. The author also encountered the same problem when recognizing complex charts.
In the paper, I think there is a situation that the algorithm cannot work. For example, symbol A is consisted by symbol B and symbol C. Actually it is very common in sketch recognition, such as COA diagrams.
Very good appreciation about COA, in fact many domains tend to label their shapes by putting text adjacent to the symbols. In this case the neighborhood approach is not the best.
回复删除