Oscillatory Neural Network as Hetero-Associative Memory for Image Edge
Detection
- URL: http://arxiv.org/abs/2202.12541v1
- Date: Fri, 25 Feb 2022 08:09:29 GMT
- Title: Oscillatory Neural Network as Hetero-Associative Memory for Image Edge
Detection
- Authors: Madeleine Abernot (SmartIES, LIRMM), Thierry Gil (LIRMM), Aida
Todri-Sanial (SmartIES, LIRMM)
- Abstract summary: We propose a novel image processing method by using ONNs as a hetero-associative memory for image edge detection.
This work is the first to explore ONNs as hetero-associative memory for image processing applications.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The increasing amount of data to be processed on edge devices, such as
cameras, has motivated Artificial Intelligence (AI) integration at the edge.
Typical image processing methods performed at the edge, such as feature
extraction or edge detection, use convolutional filters that are energy,
computation, and memory hungry algorithms. But edge devices and cameras have
scarce computational resources, bandwidth, and power and are limited due to
privacy constraints to send data over to the cloud. Thus, there is a need to
process image data at the edge. Over the years, this need has incited a lot of
interest in implementing neuromorphic computing at the edge. Neuromorphic
systems aim to emulate the biological neural functions to achieve
energy-efficient computing. Recently, Oscillatory Neural Networks (ONN) present
a novel brain-inspired computing approach by emulating brain oscillations to
perform autoassociative memory types of applications. To speed up image edge
detection and reduce its power consumption, we perform an in-depth
investigation with ONNs. We propose a novel image processing method by using
ONNs as a hetero-associative memory (HAM) for image edge detection. We simulate
our ONN-HAM solution using first, a Matlab emulator, and then a fully digital
ONN design. We show results on gray scale square evaluation maps, also on black
and white and gray scale 28x28 MNIST images and finally on black and white
512x512 standard test images. We compare our solution with standard edge
detection filters such as Sobel and Canny. Finally, using the fully digital
design simulation results, we report on timing and resource characteristics,
and evaluate its feasibility for real-time image processing applications. Our
digital ONN-HAM solution can process images with up to 120x120 pixels (166 MHz
system frequency) respecting real-time camera constraints. This work is the
first to explore ONNs as hetero-associative memory for image processing
applications.
Related papers
- Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture.
To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy.
Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
arXiv Detail & Related papers (2023-07-20T16:00:19Z) - Autism Disease Detection Using Transfer Learning Techniques: Performance
Comparison Between Central Processing Unit vs Graphics Processing Unit
Functions for Neural Networks [2.750124853532831]
We implement a system for classifying Autism disease using face images of autistic and non-autistic children to compare performance.
It was observed that GPU outperformed CPU in all tests conducted.
arXiv Detail & Related papers (2023-06-01T01:59:17Z) - Efficient Neural Network based Classification and Outlier Detection for
Image Moderation using Compressed Sensing and Group Testing [4.2455052426413085]
We propose an approach which exploits this fact to reduce the overall computational cost of such engines.
We present the quantitative matrix-pooled neural network (QMPNN), which takes as input $n$ images.
We also present pooled deep outlier detection, which brings CS and group testing techniques to deep outlier detection.
arXiv Detail & Related papers (2023-05-12T17:48:05Z) - Deep Dynamic Scene Deblurring from Optical Flow [53.625999196063574]
Deblurring can provide visually more pleasant pictures and make photography more convenient.
It is difficult to model the non-uniform blur mathematically.
We develop a convolutional neural network (CNN) to restore the sharp images from the deblurred features.
arXiv Detail & Related papers (2023-01-18T06:37:21Z) - Braille Letter Reading: A Benchmark for Spatio-Temporal Pattern
Recognition on Neuromorphic Hardware [50.380319968947035]
Recent deep learning approaches have reached accuracy in such tasks, but their implementation on conventional embedded solutions is still computationally very and energy expensive.
We propose a new benchmark for computing tactile pattern recognition at the edge through letters reading.
We trained and compared feed-forward and recurrent spiking neural networks (SNNs) offline using back-propagation through time with surrogate gradients, then we deployed them on the Intel Loihimorphic chip for efficient inference.
Our results show that the LSTM outperforms the recurrent SNN in terms of accuracy by 14%. However, the recurrent SNN on Loihi is 237 times more energy
arXiv Detail & Related papers (2022-05-30T14:30:45Z) - Concurrent Neural Tree and Data Preprocessing AutoML for Image
Classification [0.5735035463793008]
Current state-of-the-art (SOTA) methods do not include traditional methods for manipulating input data as part of the algorithmic search space.
We adapt the Evolutionary Multi-objective Algorithm Design Engine (EMADE), a multi-objective evolutionary search framework for traditional machine learning methods, to perform neural architecture search.
We show that including these methods as part of the search space shows potential to provide benefits to performance on the CIFAR-10 image classification benchmark dataset.
arXiv Detail & Related papers (2022-05-25T20:03:09Z) - Neural Space-filling Curves [47.852964985588486]
We present a data-driven approach to infer a context-based scan order for a set of images.
Our work learns a spatially coherent linear ordering of pixels from the dataset of images using a graph-based neural network.
We show the advantage of using Neural SFCs in downstream applications such as image compression.
arXiv Detail & Related papers (2022-04-18T17:59:01Z) - CNNs for JPEGs: A Study in Computational Cost [49.97673761305336]
Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade.
CNNs are capable of learning robust representations of the data directly from the RGB pixels.
Deep learning methods capable of learning directly from the compressed domain have been gaining attention in recent years.
arXiv Detail & Related papers (2020-12-26T15:00:10Z) - Accelerating Deep Learning Applications in Space [0.0]
We investigate the performance of CNN-based object detectors on constrained devices.
We take a closer look at the Single Shot MultiBox Detector (SSD) and Region-based Fully Convolutional Network (R-FCN)
The performance is measured in terms of inference time, memory consumption, and accuracy.
arXiv Detail & Related papers (2020-07-21T21:06:30Z) - Neural Sparse Representation for Image Restoration [116.72107034624344]
Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks.
Our method structurally enforces sparsity constraints upon hidden neurons.
Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
arXiv Detail & Related papers (2020-06-08T05:15:17Z)
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.