点击次数：

论文类型：期刊论文

发表时间：2018-04-01

发表刊物：International Journal of Performability Engineering

卷号：14

期号：4

页面范围：621-630

ISSN号：09731318

摘要：Convolutional neural networks (CNNs) have recently achieved remarkable success with superior performances in computer vision applications. In most CNN-based image retrieval methods, deep CNNs features are verified as discriminative descriptors for effective image representation. This paper exploits the best practice for CNNs application to national costume image retrieval. Several important aspects that affect the discriminative ability of deep CNNs features are investigated thoroughly, including layers selection, aggregation and weighting methods. Firstly, an effective weighting method for sum-pooling features aggregation is given, which is more suitable for national costume image than some typical aggregation methods such as SPoC and SCDA. Secondly, in view of the complementary strengths, compact multi-layer CNN features combined with low dimensions are proposed and proven to be effective for national costume expression. Finally, a re-ranking strategy of diffusion process is applied to further enhance the performance for national costume images retrieval. The experimental results show that the proposed method outperforms the existing methods remarkably, which will provide some new research ideas and technical references for researchers in the field of national costume image retrieval. © 2018 Totem Publisher, Inc. All rights reserved.