The perception of multiple objects: a connectionist approach
The perception of multiple objects: a connectionist approach
A bottom-up attention system for active vision
ECAI '92 Proceedings of the 10th European conference on Artificial intelligence
Task-dependent learning of attention
Neural Networks
A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Development of a Biologically Inspired Real-Time Visual Attention System
BMVC '00 Proceedings of the First IEEE International Workshop on Biologically Motivated Computer Vision
ICPR '98 Proceedings of the 14th International Conference on Pattern Recognition-Volume 1 - Volume 1
| Hi-index | 0.00 |
An approach of using a biologically motivated attention system to extracting objects of interest from an image is presented with possible broad application in computer vision. Starting with an RGB image, four streams of biologically motivated features are extracted and reorganized in order to calculate a saliency map allowing the selection of the most interesting objects. The approach is tested on three different types of images showing reasonable results. In addition, in order to verify the results on real images, we performed human test and compared the measured behaviors of human subjects with the results of the system.