基于距离度量学习的DCT域JPEG图像检索

由于特征有限，传统基于欧式距离的压缩域检索性能并不理想。本文引入距离度量学习技术，研究压缩域图像检索，提出了一种基于距离度量学习的离散余弦变换（DCT）域联合图像专家小组（JPEG）图像检索方法。首先，提出了一种更有效的 DCT 域特征提取方法；其次，运用距离度量学习技术训练出一个更加有效的度量矩阵进行检索。在 Corel5000上的图像检索实验表明，新方法有效提高了检索准确度。

JPEG images retrieval in DCT domain based on Distance Metric Learning

Due to limited features extracted from compression domain, the conventional Euclidean distance based retrieval performance in compressed-domain is not satisfactory. The Distance Metric Learning(DML) is introduced to compressed-domain images retrieval and a DML based Discrete Cosine Transform(DCT) domain retrieval for Joint Photographic Experts Group(JPEG) images is developed. Firstly, we propose a more effective DCT domain features extraction method, and then the DML is applied to train a more efficient metric matrix for retrieval. Retrieval experiment on Corel5000 images database demonstrates that the approach proposed can effectively improve the retrieval accuracy.