Fast image clustering based on convolutional neural network and binary K-means

Shengcai Ke; Yongwei Zhao; Bicheng Li; Zhibing Wu; Xin Liu

doi:10.1117/12.2244263

29 August 2016 Fast image clustering based on convolutional neural network and binary K-means

Shengcai Ke, Yongwei Zhao, Bicheng Li, Zhibing Wu, Xin Liu

Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100332E (2016) https://doi.org/10.1117/12.2244263
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China

Abstract

Visual features used in state-of-the-art image clustering methods lack of learning, which leads to low representational power. Furthermore, the efficiency of traditional clustering methods is low for large image dataset. So, a fast image clustering method based on convolutional neural network and binary K-means is proposed in this paper. Firstly, a large-scale convolutional neural network is employed to learn the intrinsic implications of training images so as to improve the discrimination and representational power of visual features. Secondly, ITQ hash algorithm is applied to map the high dimensional deep features into low-dimensional hamming space, and multi-index hash table is used to index the initial clustering centers so that the nearest center lookup becomes extremely efficient. Finally, image clustering is accomplished efficiently by binary K-means algorithm. Experimental results of ImageNet-1000 datasets indicate that the expression ability of visual features is effectively improved and the image clustering performance is substantially boosted compared with state-of-the-art methods.

Citation Download Citation

Shengcai Ke, Yongwei Zhao, Bicheng Li, Zhibing Wu, and Xin Liu "Fast image clustering based on convolutional neural network and binary K-means", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100332E (29 August 2016); https://doi.org/10.1117/12.2244263

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available