主成分分析网络(PCANet)是一种简单的深度学习网络模型,在图像识别领域具有很强的应用潜力.本文在PCANet的基础上,通过对PCANet结构进行分析,构造了一种基于多层特征融合的PCANet(PCANet_dense)网络模型.与单纯地只将前一层网络输出作...主成分分析网络(PCANet)是一种简单的深度学习网络模型,在图像识别领域具有很强的应用潜力.本文在PCANet的基础上,通过对PCANet结构进行分析,构造了一种基于多层特征融合的PCANet(PCANet_dense)网络模型.与单纯地只将前一层网络输出作为后一层网络输入的PCANet不同,PCANet_dense利用了不同层的特征信息.在2层网络结构中,它首先将原始图像特征和第1层网络的输出进行级联,然后将级联后的结果作为第2层网络的输入.而在3层网络结构中,它则将第1层和第2层网络的输出级联起来,作为第3层网络的输入.由于PCANet_dense在训练每一层(除了第1层)时使用了更多信息,因此能够获得比原PCANet更好的效果.为了验证所提方法的有效性,本文使用CMU PIE数据集构建网络模型,并在ORL、AR和Extended Yale B 3个公开人脸数据集上对所提出方法的性能进行了测试,实验结果表明,本文提出的PCANet_dense获得了比PCANet更好的性能.展开更多
Flower Image Classification is a Fine-Grained Classification problem.The main difficulty of Fine-Grained Classification is the large inter-class similarity and the inner-class difference.In this paper,we propose a new...Flower Image Classification is a Fine-Grained Classification problem.The main difficulty of Fine-Grained Classification is the large inter-class similarity and the inner-class difference.In this paper,we propose a new algorithm based on Saliency Map and PCANet to overcome the difficulty.This algorithm mainly consists of two parts:flower region selection,flower feature learning.In first part,we combine saliency map with gray-scale map to select flower region.In second part,we use the flower region as input to train the PCANet which is a simple deep learning network for learning flower feature automatically,then a 102-way softmax layer that follow the PCANet achieve classification.Our approach achieves 84.12%accuracy on Oxford 17 Flowers dataset.The results show that a combination of Saliency Map and simple deep learning network PCANet can applies to flower image classification problem.展开更多
In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the d...In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the data is mapped into a higher-dimensional space with kernel principal component analysis to make the data linearly separable. Then a two-layer KPCANet is built to obtain the principal components of the image. Finally, the principal components are classified with a linear classifier. Experimental results showthat the proposed KPCANet is effective in face recognition, object recognition and handwritten digit recognition. It also outperforms principal component analysis network（ PCANet） generally. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.展开更多
文摘主成分分析网络(PCANet)是一种简单的深度学习网络模型,在图像识别领域具有很强的应用潜力.本文在PCANet的基础上,通过对PCANet结构进行分析,构造了一种基于多层特征融合的PCANet(PCANet_dense)网络模型.与单纯地只将前一层网络输出作为后一层网络输入的PCANet不同,PCANet_dense利用了不同层的特征信息.在2层网络结构中,它首先将原始图像特征和第1层网络的输出进行级联,然后将级联后的结果作为第2层网络的输入.而在3层网络结构中,它则将第1层和第2层网络的输出级联起来,作为第3层网络的输入.由于PCANet_dense在训练每一层(除了第1层)时使用了更多信息,因此能够获得比原PCANet更好的效果.为了验证所提方法的有效性,本文使用CMU PIE数据集构建网络模型,并在ORL、AR和Extended Yale B 3个公开人脸数据集上对所提出方法的性能进行了测试,实验结果表明,本文提出的PCANet_dense获得了比PCANet更好的性能.
文摘Flower Image Classification is a Fine-Grained Classification problem.The main difficulty of Fine-Grained Classification is the large inter-class similarity and the inner-class difference.In this paper,we propose a new algorithm based on Saliency Map and PCANet to overcome the difficulty.This algorithm mainly consists of two parts:flower region selection,flower feature learning.In first part,we combine saliency map with gray-scale map to select flower region.In second part,we use the flower region as input to train the PCANet which is a simple deep learning network for learning flower feature automatically,then a 102-way softmax layer that follow the PCANet achieve classification.Our approach achieves 84.12%accuracy on Oxford 17 Flowers dataset.The results show that a combination of Saliency Map and simple deep learning network PCANet can applies to flower image classification problem.
基金The National Natural Science Foundation of China(No.6120134461271312+7 种基金6140108511301074)the Research Fund for the Doctoral Program of Higher Education(No.20120092120036)the Program for Special Talents in Six Fields of Jiangsu Province(No.DZXX-031)Industry-University-Research Cooperation Project of Jiangsu Province(No.BY2014127-11)"333"Project(No.BRA2015288)High-End Foreign Experts Recruitment Program(No.GDT20153200043)Open Fund of Jiangsu Engineering Center of Network Monitoring(No.KJR1404)
文摘In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the data is mapped into a higher-dimensional space with kernel principal component analysis to make the data linearly separable. Then a two-layer KPCANet is built to obtain the principal components of the image. Finally, the principal components are classified with a linear classifier. Experimental results showthat the proposed KPCANet is effective in face recognition, object recognition and handwritten digit recognition. It also outperforms principal component analysis network（ PCANet） generally. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.
