Modeling object recognition in visual cortex using multiple firing k-means and non-negative sparse coding

• We construct a five-layer bio-inspired computational model to imitate the process of visual stream.
• Multiple firing k-means is applied for emulating the V2 neural responses.
• Non-negative sparse coding is used to reproduce the V4 neural responses.

The HMAX model developed by Serre et al. imitates the process of visual recognition in primates’ visual cortex. However, it has some limits in modeling the V2 neurons or higher level of visual cortex. We extend the model in some biologically plausible ways and construct a five-layer computational model, denoted as Sparse-HMAX model. First we use Gabor filters to describe the response properties of V1 neurons as in original HMAX model and describe C1 image patches with HOG descriptors. Then we integrate multiple firing k-means into the HMAX model to emulate the V2 neural responses and non-negative sparse coding to model V4 neurons. To investigate the efficacy of our proposed model, we perform experiments on three public databases: Caltech101, Caltech256 and GRAZ-01. Experimental results demonstrate that Sparse-HMAX model displays great improvements over the original HMAX model both in recognition accuracy and processing speed for object recognition. Our proposed method is also comparable to the prevalent approaches in recognition performance.