A Scale-Changeable Image Analysis Method

Abstract

The biological vision system is far more efficient than machine vision system. This is due to the former has rich neural layers for representation and process. In order to obtain a non-task-dependent image representation schema, the early phase of neural vision mechanism is worth simulating. We design a neural model to simulate non-classical receptive field of ganglion cell and its local feedback control circuit, and find it can represent image, beyond pixel level, self-adaptively and regularly. The experimental results prove this method can represent image faithfully with low cost, and can produce a compact and abstract approximation to facilitate successive image segmentation as well as integration operation. This representation schema is good at extracting spatial relationship from different components of image, thus it can be applied to formalize image semantics. Further it can be applied to object recognition or image classification tasks in future.

DOI: 10.1007/978-3-642-23957-1_7

Extracted Key Phrases

3 Figures and Tables

Cite this paper

@inproceedings{Wei2011ASI, title={A Scale-Changeable Image Analysis Method}, author={Hui Wei and Bo Lang and Qingsong Zuo}, booktitle={EANN/AIAI}, year={2011} }