A neuromorphic approach to image processing and machine vision
- URL: http://arxiv.org/abs/2209.02595v1
- Date: Sun, 7 Aug 2022 05:01:57 GMT
- Title: A neuromorphic approach to image processing and machine vision
- Authors: Arvind Subramaniam
- Abstract summary: We explore the implementation of visual tasks such as image segmentation, visual attention and object recognition.
We have emphasized on the employment of non-volatile memory devices such as memristors to realize artificial visual systems.
- Score: 0.9137554315375922
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Neuromorphic engineering is essentially the development of artificial
systems, such as electronic analog circuits that employ information
representations found in biological nervous systems. Despite being faster and
more accurate than the human brain, computers lag behind in recognition
capability. However, it is envisioned that the advancement in neuromorphics,
pertaining to the fields of computer vision and image processing will provide a
considerable improvement in the way computers can interpret and analyze
information. In this paper, we explore the implementation of visual tasks such
as image segmentation, visual attention and object recognition. Moreover, the
concept of anisotropic diffusion has been examined followed by a novel approach
employing memristors to execute image segmentation. Additionally, we have
discussed the role of neuromorphic vision sensors in artificial visual systems
and the protocol involved in order to enable asynchronous transmission of
signals. Moreover, two widely accepted algorithms that are used to emulate the
process of object recognition and visual attention have also been discussed.
Throughout the span of this paper, we have emphasized on the employment of
non-volatile memory devices such as memristors to realize artificial visual
systems. Finally, we discuss about hardware accelerators and wish to represent
a case in point for arguing that progress in computer vision may benefit
directly from progress in non-volatile memory technology.
Related papers
- Unidirectional brain-computer interface: Artificial neural network
encoding natural images to fMRI response in the visual cortex [12.1427193917406]
We propose an artificial neural network dubbed VISION to mimic the human brain and show how it can foster neuroscientific inquiries.
VISION successfully predicts human hemodynamic responses as fMRI voxel values to visual inputs with an accuracy exceeding state-of-the-art performance by 45%.
arXiv Detail & Related papers (2023-09-26T15:38:26Z) - Computational imaging with the human brain [1.614301262383079]
Brain-computer interfaces (BCIs) are enabling a range of new possibilities and routes for augmenting human capability.
We demonstrate ghost imaging of a hidden scene using the human visual system that is combined with an adaptive computational imaging scheme.
This brain-computer connectivity demonstrates a form of augmented human computation that could in the future extend the sensing range of human vision.
arXiv Detail & Related papers (2022-10-07T08:40:18Z) - Adapting Brain-Like Neural Networks for Modeling Cortical Visual
Prostheses [68.96380145211093]
Cortical prostheses are devices implanted in the visual cortex that attempt to restore lost vision by electrically stimulating neurons.
Currently, the vision provided by these devices is limited, and accurately predicting the visual percepts resulting from stimulation is an open challenge.
We propose to address this challenge by utilizing 'brain-like' convolutional neural networks (CNNs), which have emerged as promising models of the visual system.
arXiv Detail & Related papers (2022-09-27T17:33:19Z) - EDeNN: Event Decay Neural Networks for low latency vision [26.784944204163363]
We develop a new type of neural network which operates closer to the original event data stream.
We demonstrate state-of-the-art performance in angular velocity regression and competitive optical flow estimation.
arXiv Detail & Related papers (2022-09-09T15:51:39Z) - Peripheral Vision Transformer [52.55309200601883]
We take a biologically inspired approach and explore to model peripheral vision in deep neural networks for visual recognition.
We propose to incorporate peripheral position encoding to the multi-head self-attention layers to let the network learn to partition the visual field into diverse peripheral regions given training data.
We evaluate the proposed network, dubbed PerViT, on the large-scale ImageNet dataset and systematically investigate the inner workings of the model for machine perception.
arXiv Detail & Related papers (2022-06-14T12:47:47Z) - Attention Mechanisms in Computer Vision: A Survey [75.6074182122423]
We provide a comprehensive review of various attention mechanisms in computer vision.
We categorize them according to approach, such as channel attention, spatial attention, temporal attention and branch attention.
We suggest future directions for attention mechanism research.
arXiv Detail & Related papers (2021-11-15T09:18:40Z) - Brain-inspired algorithms for processing of visual data [5.045960549713147]
We review approaches for image processing and computer vision based on neuro-scientific findings about the functions of some neurons in the visual cortex.
We pay particular attention to the mechanisms of inhibition of the responses of some neurons, which provide the visual system with improved stability to changing input stimuli.
arXiv Detail & Related papers (2021-03-02T10:45:38Z) - Data augmentation and image understanding [2.123756175601459]
dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience.
dissertation focuses on learning representations that are more aligned with visual perception and the biological vision.
arXiv Detail & Related papers (2020-12-28T11:00:52Z) - Photonics for artificial intelligence and neuromorphic computing [52.77024349608834]
Photonic integrated circuits have enabled ultrafast artificial neural networks.
Photonic neuromorphic systems offer sub-nanosecond latencies.
These systems could address the growing demand for machine learning and artificial intelligence.
arXiv Detail & Related papers (2020-10-30T21:41:44Z) - A Developmental Neuro-Robotics Approach for Boosting the Recognition of
Handwritten Digits [91.3755431537592]
Recent evidence shows that a simulation of the children's embodied strategies can improve the machine intelligence too.
This article explores the application of embodied strategies to convolutional neural network models in the context of developmental neuro-robotics.
arXiv Detail & Related papers (2020-03-23T14:55:00Z) - Continuous Emotion Recognition via Deep Convolutional Autoencoder and
Support Vector Regressor [70.2226417364135]
It is crucial that the machine should be able to recognize the emotional state of the user with high accuracy.
Deep neural networks have been used with great success in recognizing emotions.
We present a new model for continuous emotion recognition based on facial expression recognition.
arXiv Detail & Related papers (2020-01-31T17:47:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.