Title | ||
---|---|---|
A feature binding computational model for multi-class object categorization and recognition |
Abstract | ||
---|---|---|
We propose a feature binding computational model based on the cognitive research findings. Feature integration theory is widely approved on the principles of the binding problem, which supplies the roadmap for our computational model. We construct the learning procedure to acquire necessary pre-knowledge for the recognition network on reasonable hypothesis–maximum entropy. With the recognition network, we bind the low-level image features with the high-level knowledge. Fundamental concepts and principles of conditional random fields are employed to model the feature binding process. We apply our model to current challenging problems, multi-label image classification and object recognition, and evaluate it on the benchmark image databases to demonstrate that our model is competitive to the state-of-the-art method. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/s00521-011-0562-1 | Neural Computing and Applications |
Keywords | DocType | Volume |
object recognition,feature integration theory,binding problem,conditional random fieldsfeature binding � feature integrationmulti-label image classification � object recognition,cognitive research finding,multi-label image classification,low-level image feature,benchmark image databases,feature binding process,recognition network,computational model | Journal | 21 |
Issue | ISSN | Citations |
6 | 1433-3058 | 3 |
PageRank | References | Authors |
0.38 | 8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xishun Wang | 1 | 8 | 0.79 |
Xi Liu | 2 | 36 | 10.08 |
Zhongzhi Shi | 3 | 2440 | 238.03 |
Hongjian Sui | 4 | 3 | 0.38 |