A neural network model for selective attention in visual pattern recognition
Biological Cybernetics
Object recognition by computer: the role of geometric constraints
Object recognition by computer: the role of geometric constraints
Learning in neural networks with material synapses
Neural Computation
Face Recognition by Elastic Bunch Graph Matching
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Network-Based Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Learning for View-Based Human Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A computational model for visual selection
Neural Computation
Locating Faces Using Statistical Feature Detectors
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
International Journal of Computer Vision - Special issue on statistical and computational theories of vision: Part II
Object Detection Using the Statistics of Parts
International Journal of Computer Vision
A Coarse-to-Fine Strategy for Multiclass Shape Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Attractor Networks for Shape Recognition
Neural Computation
Feature-centric evaluation for efficient cascaded object detection
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
This article describes a parallel neural net architecture for efficient and robust visual selection in generic gray-level images. Objects are represented through flexible star-type planar arrangements of binary local features which are in turn star-type planar arrangements of oriented edges. Candidate locations are detected over a range of scales and other deformations, using a generalized Hough transform. The flexibility of the arrangements provides the required invariance. Training involves selecting a small number of stable local features from a predefined pool, which are well localized on registered examples of the object. Training therefore requires only small data sets. The parallel architecture is constructed so that the Hough transform associated with any object can be implemented without creating or modifying any connections. The different object representations are learned and stored in a central module. When one of these representations is evoked, it "primes" the appropriate layers in the network so that the corresponding Hough transform is computed. Analogies between the different layers in the network and those in the visual system are discussed. Furthermore, the model can be used to explain certain experiments on visual selection reported in the literature.