论文标题
振荡性神经网络作为图像边缘检测的异质促进记忆
Oscillatory Neural Network as Hetero-Associative Memory for Image Edge Detection
论文作者
论文摘要
在边缘设备（例如相机）上要处理的数据越来越多，它激发了人工智能（AI）的整合。在边缘执行的典型图像处理方法，例如特征提取或边缘检测，使用能量，计算和内存饥饿算法的卷积过滤器。但是，边缘设备和摄像头具有稀缺的计算资源，带宽和功率，并且由于隐私限制而受到限制，将数据发送到云。因此，需要在边缘处理图像数据。多年来，这一需求引起了人们对在边缘实施神经形态计算的极大兴趣。神经形态系统旨在模仿生物神经功能以实现节能计算。最近，振荡性神经网络（ONN）通过模拟脑振荡以执行应用自动求解记忆类型，提出了一种新型的脑启发计算方法。为了加快图像边缘检测并减少其功耗，我们对ONN进行了深入的研究。我们通过使用ONN作为异伴关系记忆（HAM）来提出一种新型的图像处理方法进行图像边缘检测。我们使用First，Matlab仿真器，然后进行完全数字ONN设计来模拟我们的Onn-Ham解决方案。我们在灰度方形评估图上显示了结果，也显示了黑白和灰色尺度28x28 MNIST图像，最后在黑白512x512标准测试图像上。我们将解决方案与标准边缘检测过滤器（例如Sobel和Canny）进行了比较。最后，使用完全数字设计模拟结果，我们报告了时间和资源特征，并评估其对实时图像处理应用程序的可行性。我们的数字ON-HAM解决方案可以处理尊重实时摄像机约束的最多120x120像素（166 MHz系统频率）的图像。这项工作是第一个探索图像处理应用程序的异性缔合记忆的探索。
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.
