结合多特征与线性判别分析的图像检索
IMAGE RETRIEVAL BASED ON MULTIPILE FEATURES AND LINEAR DISCRIMINANT ANALYSIS
丁功鸿 1黄山2
作者信息
- 1. 四川大学电气工程学院 四川成都 610065
- 2. 四川大学计算机学院 四川成都 610065
- 折叠
摘要
卷积神经网络的全连接层特征缺乏对图像底层信息的描述,导致部分样本无法被成功检索.并且全连接层特征维度高,检索效率低下.针对这种情况,提出一种结合线性判别分析和多层特征的图像检索方法.该方法利用卷积神经网络提取卷积层和全连接层特征,并融合HSV特征,使用线性判别分析对融合特征降维.多层特征能增加图像的区分度,提升识别准确率.与其他算法的实验结果表明,该方法在检索精度和检索速度上有一定的提高.
Abstract
The fully connected layer features of convolutional neural networks lack the description of the underlying information of image,result in that some samples cannot be retrieved successfully.Moreover,it's not efficient to retrieve directly due to the high dimension of the fully convolutional layer features.To solve this problem,we propose an image retrieval method by combining linear discriminant analysis and multiple features.Convolutional neural network was used to extract features from both convolutional layer and fully convolutional layer,and it merged HSV color features together.Dimension of the fused features was reduced by linear discriminant analysis.Multi-layer features could increase the image differentiation and improve the recognition accuracy.Comparison experiments show that this method makes improvement in precision and speed on the task of image retrieval.
关键词
深度学习/多特征/线性判别分析/图像检索Key words
Deep learning/Multiple features/Linear discriminant analysis/Image retrieval引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
维普
万方数据