Saliency map using features derived from spiking neural networks of primate visual cortex
This work addresses saliency detection for computer vision applications, but it appears incremental as it builds on existing biological models and simulators without claiming major breakthroughs.
The authors tackled the problem of generating saliency maps for digital images by proposing a framework inspired by primate visual cortex, using spiking neural networks to extract features, and applied it to benchmark images with results described but no concrete numbers provided.
We propose a framework inspired by biological vision systems to produce saliency maps of digital images. Well-known computational models for receptive fields of areas in the visual cortex that are specialized for color and orientation perception are used. To model the connectivity between these areas we use the CARLsim library which is a spiking neural network(SNN) simulator. The spikes generated by CARLsim, then serve as extracted features and input to our saliency detection algorithm. This new method of saliency detection is described and applied to benchmark images.