Content-based image retrieval by combining convolutional neural networks and sparse representation
Content-based image retrieval by combining convolutional neural networks and sparse representation
复制标题
DOI：
10.1007/s11042-019-7321-1
复制
发表时间：
2019-03
影响因子：
3.6
通讯作者：
A. Sezavar;H. Farsi;S. Mohamadzadeh
中科院分区：
文献类型：
--
作者：
A. Sezavar;H. Farsi;S. Mohamadzadeh
随着存储盘上存储的数据和图像的增加，图像检索中就出现了必要的图像处理任务。尽管迄今为止针对该任务已有大量研究报道，但图像低级特征与人类概念之间的语义差距仍然是基于内容的图像检索的一个重要挑战。对于该任务，提出了一种结合卷积神经网络和稀疏表示的鲁棒方法，其中使用CNN和稀疏表示来提取深层特征，以提高检索速度和准确性。所提出的方法已在三个常见的图像检索数据库（Corel、ALOI 和 MPEG7）上进行了测试。通过计算 P(0.5)、P(1) 和 ANMRR 等指标，实验结果表明，与最先进的方法相比，所提出的方法具有更高的精度和更好的速度。
As stored data and images on memory disks increase, image retrieval has a necessary task on image processing. Although lots of researches have been reported for this task so far, semantic gap between low level features of images and human concept is still an important challenge on content-based image retrieval. For this task, a robust method is proposed by a combination of convolutional neural network and sparse representation, in which deep features are extracted by using CNN and sparse representation to increase retrieval speed and accuracy. The proposed method has been tested on three common databases on image retrieval, named Corel, ALOI and MPEG7. By computing metrics such as P(0.5), P(1) and ANMRR, experimental results show that the proposed method has achieved higher accuracy and better speed compared to state-of-the-art methods.