Comparison of Feature Extraction Techniques for Handwritten Digit Recognition with a Photonic Reservoir Computer

机译：用光子存储库计算机进行手写数字识别的特征提取技术比较

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

Reservoir computing is a bio-inspired computing paradigm for processing time-dependent signals. Its photonic implementations have received much interest recently, and have been successfully applied to speech recognition and time-series forecasting. However, few works have been devoted to the more challenging computer vision tasks. In this work, we use a large-scale photonic reservoir computer for classification of handwritten digits from the MNIST database. We investigate and compare different feature extraction techniques (such as zoning, Gabor filters, and HOG) and report classification errors of 1% experimentally and 0.8% in numerical simulations.

机译：储层计算是一种生物启发的计算范例，用于处理时间相关的信号。最近，其光子实现受到了广泛的关注，并已成功地应用于语音识别和时间序列预测。但是，很少有工作致力于更具挑战性的计算机视觉任务。在这项工作中，我们使用大型光子存储计算机对MNIST数据库中的手写数字进行分类。我们调查并比较了不同的特征提取技术（例如分区，Gabor滤波器和HOG），并通过实验报告了1％的分类错误，在数值模拟中报告了0.8％的分类错误。

著录项

来源
《International conference on artificial neural networks》|2019年|175-179|共5页
会议地点
作者
Piotr Antonik; Nicolas Marsal; Daniel Brunner; Damien Rontani;
展开▼
作者单位

展开▼
会议组织
原文格式 PDF
正文语种
中图分类
关键词
Photonic reservoir computing; Handwritten digit classification; Feature extraction; MNIST dataset;

机译：光子储层计算;手写数字分类;特征提取; MNIST数据集;

相似文献

外文文献
中文文献
专利

1. Handwritten digit recognition: investigation of normalization and feature extraction techniques [J] . Liu CL, Nakashima K, Sako H, Pattern Recognition: The Journal of the Pattern Recognition Society . 2004,第2期

机译：手写数字识别：归一化和特征提取技术研究
2. Analysis and comparison of machine learning classifiers and deep neural networks techniques for recognition of Farsi handwritten digits [J] . Nanehkaran Y. A., Zhang Defu, Salimi S., Journal of supercomputing . 2021,第4期

机译：机器学习分类器和深神经网络识别的分析与比较Farsi手写数字
3. Multiple classifiers fusion and CNN feature extraction for handwritten digits recognition [J] . Hui-huang Zhao, Han Liu Granular Computing . 2020,第3期

机译：手写数字识别的多分类器融合和CNN特征提取
4. Comparison of Feature Extraction Techniques for Handwritten Digit Recognition with a Photonic Reservoir Computer [C] . Piotr Antonik, Nicolas Marsal, Daniel Brunner, International conference on artificial neural networks . 2019

机译：用光子储库计算机对手写数字识别特征提取技术的比较
5. Pattern recognition and feature extraction using lidar-derived elevation models in GIS: A comparison between visualization techniques and automated methods for identifying prehistoric ditch-fortified sites in North Dakota [D] . Radermacher, Matthew Jeffery. 2016

机译：使用GIS中基于激光雷达的高程模型进行模式识别和特征提取：可视化技术与识别北达科他州史前沟壑加固地点的自动化方法之间的比较
6. Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN) [O] . Savita Ahlawat, Amit Choudhary, Anand Nayyar, 2020

机译：使用卷积神经网络（CNN）改进的手写数字识别
7. Novel feature extraction technique for the recognition of handwritten digits [O] . Abdelhak Boukharouba, Abdelhak Bennia 2017

机译：用于识别手写数字的新颖特征提取技术

Comparison of Feature Extraction Techniques for Handwritten Digit Recognition with a Photonic Reservoir Computer

摘要

著录项

相似文献

相关主题

期刊订阅