当前位置: X-MOL 学术Color Res. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Colorimetric characterization of color imaging systems using a multi-input PSO-BP neural network
Color Research and Application ( IF 1.2 ) Pub Date : 2022-01-07 , DOI: 10.1002/col.22772
Lu Liu 1 , Xufen Xie 1, 2 , Yuncui Zhang 1 , Fan Cao 1 , Jing Liang 1 , Ningfang Liao 2
Affiliation  

Most commonly used camera characterization methods do not use a deep learning-based artificial neural network approach at present. This article proposes a colorimetric characterization method for color imaging systems based on the multi-input particle swarm optimization backpropagation neural network. Combined with a particle swarm optimization algorithm for global search and a 19-input vector, this method not only overcomes the effects of local extrema on the multi-input backpropagation neural network, but also improves the accuracy of the common input backpropagation neural network. Images of a ColorChecker SG chart were collected using a Canon EOS 1000D camera for experimental verification, and the color differences were used to evaluate the characterization results. The results show that the color differences of the multi-input particle swarm optimization backpropagation neural network (structure: 19-7-3) model are substantially better than those of the multi-input backpropagation neural network (structure: 19-7-3) and common input backpropagation neural network (structure: 3-4-3) models. Its performance is close to that of the weighted nonlinear regression model. The multi-input particle swarm optimization backpropagation neural network is hence an effective method for colorimetric characterization with good prediction accuracy.

中文翻译:

使用多输入 PSO-BP 神经网络的彩色成像系统的色度表征

目前最常用的相机表征方法不使用基于深度学习的人工神经网络方法。本文提出了一种基于多输入粒子群优化反向传播神经网络的彩色成像系统的比色表征方法。该方法结合全局搜索的粒子群优化算法和19个输入向量,不仅克服了局部极值对多输入反向传播神经网络的影响,而且提高了普通输入反向传播神经网络的精度。使用佳能 EOS 1000D 相机收集 ColorChecker SG 图表的图像用于实验验证,并使用色差来评估表征结果。结果表明,多输入粒子群优化反向传播神经网络(结构:19-7-3)模型的色差明显优于多输入反向传播神经网络(结构:19-7-3)和常见的输入反向传播神经网络(结构:3-4-3)模型。其性能接近于加权非线性回归模型。因此,多输入粒子群优化反向传播神经网络是一种具有良好预测精度的色度表征的有效方法。其性能接近于加权非线性回归模型。因此,多输入粒子群优化反向传播神经网络是一种具有良好预测精度的色度表征的有效方法。其性能接近于加权非线性回归模型。因此,多输入粒子群优化反向传播神经网络是一种具有良好预测精度的色度表征的有效方法。
更新日期:2022-01-07
down
wechat
bug