Attention selection using global topological properties based on pulse coupled neural network

• We propose a TPA (topological properties-based attention) model using topological properties and quaternion.
• Inspired by topological perception theory in psychology, we introduce the topological property to attention selection.
• Using Unit-linking PCNN (Pulse Coupled Neural Network) hole-filter expresses the topological property in TPA.
• TPA is better than PQFT (Phase spectrum of Quaternion Fourier Transform) with more accuracy.

Topological properties are with invariance and take priority over other features, which play an important role in cognition. This paper introduces a new attention selection model called TPA (topological properties-based attention), which adopts topological properties and quaternion. In TPA, using Unit-linking PCNN (Pulse Coupled Neural Network) hole-filter expresses an important topological property (the connectivity) in visual attention selection. Meanwhile, using the quaternion Fourier transform based phase spectrum of an image or a frame in a video obtains the spatio-temporal saliency map, which shows the result of attention selection. Adjusting the weight of a topological channel can change its influence. The experimental results show that TPA reflects the real attention selection more accurately than PQFT (Phase spectrum of Quaternion Fourier Transform).