Topological invariant features take priority over other vision features in early visual perception stage, which is the core idea of topological perception theory. In order to improve the robustness and distinguishability of the invariant features extracted by pulse coupled neural network (PCNN), the topological properties are integrated into PCNN. The improved PCNN model is called as topological property motivated PCNN (TPCNN), which adopts the saliency map calculated by the spectral residual approach as the important topological properties (the connectivity, and the number of holes in target). In TPCNN, firstly, the normalized saliency map is used as a linking coefficient to enhance the importance of saliency object when we calculating the invariant features. Secondly, the entropy signature of the saliency map is treated as an additional new feature and merged into original features calculated by PCNN, then the final invariant feature is obtained. The proposed TPCNN is used to calculate the invariant feature of different kinds of fish in the paper. Experimental results show that TPCNN outperforms the state-of-art models on invariant features extraction.

Introduction

As a bio-inspired neural network model, the pulse coupled neural network (PCNN) [1], [2] has many good characteristics, such as a single layer, no prior training is required, possessing a good theoretical basis of the biological vision system, etc. Nowadays, PCNN is widely used in image segmentation [3]–[۵], image enhancement [6], image authentication [7], [8], image fusion [9], feature extraction and pattern recognition [10]–[۱۴] etc. Though it already has a good performance about the invariant features (also called image signature) extracted by basic PCNN, great changes may happen when the target’s shaping changes a little. To improve the robustness and distinguishability of the invariant features calculated by basic PCNN. We reference the topological perception theory [15], [16] of cognitive psychology and introduce the topological property into the simplified PCNN model. A topological property motivated PCNN (TPCNN) is proposed and it is used to extract the color image invariant features successfully in the paper. Topological perception theory [15], [16] is an important branch of cognitive psychology. It is the psychological foundation of TPCNN model. The core idea of Topological perception theory is that visual perception organization should be interpreted as transformation and invariance over transformation.