Abstract
A new multiple orientation event-based neurobiological recognition system is proposed by integrating recognition and tracking function in this paper, which is used for asynchronous address-event representation (AER) image sensors. The characteristic of this system has been enriched to recognize the objects in multiple orientations with only training samples moving in a single orientation. The system extracts multi-scale and multi-orientation line features inspired by models of the primate visual cortex. An orientation detector based on modified Gaussian blob tracking algorithm is introduced for object tracking and orientation detection. The orientation detector and feature extraction block work in simultaneous mode, without any increase in categorization time. An addresses lookup table (addresses LUT) is also presented to adjust the feature maps by addresses mapping and reordering, and they are categorized in the trained spiking neural network. This recognition system is evaluated with the MNIST dataset which have played important roles in the development of computer vision, and the accuracy is increased owing to the use of both ON and OFF events. AER data acquired by a dynamic vision senses (DVS) are also tested on the system, such as moving digits, pokers, and vehicles. The experimental results show that the proposed system can realize event-based multi-orientation recognition. The work presented in this paper makes a number of contributions to the event-based vision processing system for multi-orientation object recognition. It develops a new tracking-recognition architecture to feedforward categorization system and an address reorder approach to classify multi-orientation objects using event-based data. It provides a new way to recognize multiple orientation objects with only samples in single orientation.
Highlights
Visual object recognition is useful in many applications, such as vehicle recognition, face recognition, digit recognition, posture recognition, and fingerprint recognition
A spiking neural network (SNN; Wulfram and Werner, 2002) is used as a classifier receiving all the peak responses with time and address information to train the weights of each address, and all the weights are stored into a weights lookup table
Input Generation The multiple orientation event-based recognition system was implemented in MATLAB
Summary
Visual object recognition is useful in many applications, such as vehicle recognition, face recognition, digit recognition, posture recognition, and fingerprint recognition. Most object recognition techniques depend on capturing and processing sequences of still frames, which limits algorithmic efficiency when dealing with fast-moving objects. If precise object recognition is required, sequences of computationally demanding operations need to be performed on each acquired frame. Event-Based Multi-Orientation Recognition real-time autonomous systems (Triesch and Malsburg, 2001; Han and Feng-Gang, 2005). Vision sensing and object recognition in brains are performed without using the “frame” concept, but a continuous flow of visual information in the form of temporal spikes instead. Less information is required to identify objects, which improves recognition efficiency. Recent years have witnessed accelerative efforts in biomimetic visual sensory system for object recognition and tracking
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
