We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Large scale image retrieval with DCNN and local geometrical constraint model.
- Authors
Zhou, Huabing; Tao, Yiwei; Shi, Jinshu; Li, Xiaolin; Chen, Deng; Zhang, Yanduo; Xie, Liang
- Abstract
Image retrieval, which refers to browse, search and retrieve the images of the same scene or object from a large database of digital images, has attracted increasing interests in recent years. This paper proposes a coarse-to-fine method for fast indexing with Deep Convolutional Neural Network(DCNN) and Local Geometrical Constraint Model. We first use a vector quantized DCNN feature descriptors and exploit enhanced Locality-sensitive hashing(LSH) techniques for fast coarse-grained retrieval. Then, we focus on obtaining high-precision preserved matches for fine-grained retrieval. This is formulated as a maximum likelihood estimation of a Bayesian model with latent variables indicating whether matches in the putative set are inliers or outliers. We impose the non-parametric global geometrical constraints on the correspondence using Tikhonov regularizers in a reproducing kernel Hilbert space. To ensure the well-posedness of the problem, we develop a local geometrical constraint that can preserve local structures among neighboring feature points, and it is also robust to a large number of outliers. The problem is solved by using the Expectation Maximization algorithm. Extensive experiments on real near-duplicate images for both feature matching and image retrieval demonstrate that the results of the proposed method outperform current state-of-the-art methods.
- Subjects
IMAGE retrieval; GEOMETRIC modeling; MAXIMUM likelihood statistics; HILBERT space; LATENT variables; IMAGE registration; MEDLINE
- Publication
Multimedia Tools & Applications, 2019, Vol 78, Issue 17, p24391
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-018-7036-8