The primate visual system outperforms the existing automated vision systems in almost all measures. It can efficiently represent different objects present in a visual scene and form a meaningful perception of them through hierarchical processing and integration of different electrical signals in different areas of the visual cortex. Emulating the task of object detection and recognition in biological visual systems has always been the ultimate goal in computer vision.
The aim of this project is to investigate hierarchical neuronal circuits in biological systems and create bio-inspired models for visual feature extraction and invariant object detection and recognition. Spiking neurons are basic information processing units in the brain, which use spike times to represent and process sensory information. It is proposed in this research to develop hierarchical bio-inspired deep neural networks for robust object detection and recognition.
This project will build upon previous PhD works on hybrid learning in bio-inspired neural networks and multi-view face detection and recognition. It is anticipated that this project will result in the development of new bio-inspired hierarchical systems for visual feature extraction and invariant object detection and recognition. Results of this research will be disseminated in reputable conferences and journals.
The project involves review of the existing literature on visual information representation and processing in the brain as well as deep neural architectures for object detection and recognition. The existing neural learning mechanisms will then be explored and decisions will be made as to which neuron models and learning approaches will be used. New bio-inspired hierarchical models will be developed for visual feature extraction for invariant object detection and recognition.
This project is supervised by Dr. Ammar Belatreche.
Please note eligibility requirement:
• Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.
For further details of how to apply, entry requirements and the application form, see https://www.northumbria.ac.uk/research/postgraduate-research-degrees/how-to-apply/
Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. SF19/EE/CIS/BELATRECHE) will not be considered.
Start Date: 1 March 2020 or 1 October 2020
Northumbria University takes pride in, and values, the quality and diversity of our staff. We welcome applications from all members of the community. The University holds an Athena SWAN Bronze award in recognition of our commitment to improving employment practices for the advancement of gender equality and is a member of the Euraxess network, which delivers information and support to professional researchers.
- F Ahmed, F Khelifi, A Lawgalv, A Bouridane (2019) “Comparative Analysis of a Deep Convolutional Neural Network for Source Camera Identification”, 2019 IEEE 12th International Conference on Global Security, Safety and Sustainability (ICGS3).
- M Zhang, H Qu, A Belatreche, Y Chen, Z Yi (2018) “A highly effective and robust membrane potential-driven supervised learning method for spiking neurons”, IEEE transactions on neural networks and learning systems 30 (1), 123-137.
- A Taherkhani, A Belatreche, Y Li, LP Maguire (2018) “A supervised learning algorithm for learning precise timing of multiple spikes in multilayer spiking neural networks”, IEEE transactions on neural networks and learning systems 29 (11), 5394-5407.
- McCarroll N., Belatreche A., Harkin J., Li Y. (2015) “Bio-inspired hierarchical framework for multi-view face detection and pose estimation,” in IEEE International Joint Conference on Neural Networks (IEEE IJCNN), Killarney, 2015.
- Aboozar T., Belatreche A, Li Y, Maguire L. (2015) DL-ReSuMe: A Delay Learning-Based Remote Supervised Method for Spiking Neurons. IEEE Transactions on Neural Networks and Learning Systems, 26 (12). pp. 3137-3149
- Wang J., Belatreche A., Maguire L., McGinnity T.M (2015) SpikeTemp: An Enhanced Rank-Order-Based Learning Approach for Spiking Neural Networks with Adaptive Structure. IEEE Transactions on Neural Networks and Learning Systems.