A Graduated Assignment Algorithm for Graph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
On a relation between graph edit distance and maximum common subgraph
Pattern Recognition Letters
Symbol Recognition by Error-Tolerant Subgraph Matching between Region Adjacency Graphs
IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
Structural Matching in Computer Vision Using Probabilistic Relaxation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Probabilistic Approach to Learning Costs for Graph Edit Distance
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
The Future of Human-Computer Interaction
Queue - HCI
IEEE Transactions on Pattern Analysis and Machine Intelligence
Human interaction for high-quality machine translation
Communications of the ACM - A View of Parallel Computing
Multimodal interactive transcription of text images
Pattern Recognition
Interactive pattern recognition
MLMI'07 Proceedings of the 4th international conference on Machine learning for multimodal interaction
Self-organizing maps for learning the edit costs in graph matching
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Exploration of the labelling space given graph edit distance costs
GbRPR'11 Proceedings of the 8th international conference on Graph-based representations in pattern recognition
Hi-index | 0.00 |
We propose a new method to automatically obtain edit costs for error-tolerant graph matching based on interactive and adaptive graph recognition. Values of edit costs for deleting and inserting nodes and vertices are crucial to obtain good results in the recognition ratio. Nevertheless, these parameters are difficult to be estimated and they are usually set by a naïve trial and error method. Moreover, we wish to seek these costs such that the system obtains the correct labelling between nodes of the input graph and nodes of the model graph. We consider the labelling imposed by a specialist is the correct one, for this reason, we need to present an interactive and adaptive graph recognition method in which there is a human interaction. Results show that when cost values are automatically found, the quality of labelling increases.