An Efficient Supervised Deep Hashing Method for Image Retrieval |
| |
Authors: | Abid Hussain Heng-Chao Li Muqadar Ali Samad Wali Mehboob Hussain Amir Rehman |
| |
Affiliation: | 1.School of Computing and Artificial Intelligence, Southwest Jiao Tong University, Chengdu 611731, China;2.Department of Mathematics, Namal Institute, Mianwali 42250, Pakistan |
| |
Abstract: | In recent years, searching and retrieving relevant images from large databases has become an emerging challenge for the researcher. Hashing methods that mapped raw data into a short binary code have attracted increasing attention from the researcher. Most existing hashing approaches map samples to a binary vector via a single linear projection, which restricts the flexibility of those methods and leads to optimization problems. We introduce a CNN-based hashing method that uses multiple nonlinear projections to produce additional short-bit binary code to tackle this issue. Further, an end-to-end hashing system is accomplished using a convolutional neural network. Also, we design a loss function that aims to maintain the similarity between images and minimize the quantization error by providing a uniform distribution of the hash bits to illustrate the proposed technique’s effectiveness and significance. Extensive experiments conducted on various datasets demonstrate the superiority of the proposed method in comparison with state-of-the-art deep hashing methods. |
| |
Keywords: | deep learning deep supervised hashing convolutional neural network image retrieval |
|
|