Frontiers in Robotics and AI (Aug 2015)
Unbiased decoding of biologically motivated visual feature descriptors
Abstract
Visual feature descriptors are essential elements in most computer and robot vision systems. They typically lead to an abstraction of the input data, images or video, for further processing such as clustering and machine learning. In clustering applications, the cluster center represents the prototypical descriptor of the cluster and estimating the corresponding signal value, such as color value or dominating flow orientation, by decoding the prototypical descriptor, is essential. Machine learning applications determine the relevance of respective descriptors and a visualization of the corresponding decoded information is very useful for the analysis of the learning algorithm. Thus decoding of feature descriptors is a relevant problem, frequently addressed in recent work.Also the human brain represents sensorimotor information at a suitable abstraction level through varying activation of neuron populations. Approximative computational models have been derived that confirm neurophysiological experiments on the representation of visual information by decoding the underlying signals. However, the represented variables have a bias towards centers or boundaries of the tuning curves. Despite the fact that feature descriptors in computer vision are motivated from neuroscience, the respective decoding methods have been derived largely independent.From first order principles, we derive unbiased decoding schemes for biologically motivated feature descriptors with a minimum amount of redundancy and suitable invariance properties. These descriptors establish a non-parametric density estimation of the underlying stochastic process with a particular algebraic structure. Based on the resulting algebraic constraints, we show formally how the decoding problem is formulated as an unbiased maximum likelihood estimator and we derive a recurrent inverse diffusion scheme to infer the dominating mode of the distribution. These methods are evaluated and compared to existing methods.
Keywords
