Shapes Characterization on Address Event Representation Using Histograms of Oriented Events and an Extended LBP Approach
This work addresses object recognition in neuromorphic vision systems, showing competitive results with simpler methods, but it is incremental as it builds on existing datasets and techniques.
The paper tackles shape characterization in Address Event Representation by proposing a new descriptor and histogram-based features, achieving 98.5% accuracy on the Poker-DVS dataset and up to 96.3% on MNIST-DVS.
Address Event Representation is a thriving technology that could change digital image processing paradigm. This paper proposes a methodology to characterize the shape of objects using the streaming of asynchronous events. A new descriptor that enhances spikes connectivity is associated with two oriented histogram based representations. This paper uses these features to develop both a non-supervised and a supervised multi-classification framework to recognize poker symbols from the Poker-DVS public dataset. The aforementioned framework, which uses a very limited number of events and a simple class modeling, yields results that challenge more sophisticated methodologies proposed by the state of the art. A feature family based on context shapes is applied to the more challenging 2015 Poker-DVS dataset with a supervised classifier obtaining an accuracy of 98.5 %. The system is also applied to the MNIST-DVS dataset yielding an accuracy of 94.6 % and 96.3 % on digit recognition, for scales 4 and 8 respectively.