Abstract

Data security technology is of great significance to the application of high resolution remote sensing image (HRRS) images. As an important data security technology, perceptual hash overcomes the shortcomings of cryptographic hashing that is not robust and can achieve integrity authentication of HRRS images based on perceptual content. However, the existing perceptual hash does not take into account whether the user focuses on certain types of information of the HRRS image. In this paper, we introduce the concept of subject-sensitive perceptual hash, which can be seen as a special case of conventional perceptual hash, for the integrity authentication of HRRS image. To achieve subject-sensitive perceptual hash, we propose a new deep convolutional neural network architecture, named MUM-Net, for extracting robust features of HRRS images. MUM-Net is the core of perceptual hash algorithm, and it uses focal loss as the loss function to overcome the imbalance between the positive and negative samples in the training samples. The robust features extracted by MUM-Net are further compressed and encoded to obtain the perceptual hash sequence of HRRS image. Experiments show that our algorithm has higher tamper sensitivity to subject-related malicious tampering, and the robustness is improved by about 10% compared to the existing U-net-based algorithm; compared to other deep learning-based algorithms, this algorithm achieves a better balance between robustness and tampering sensitivity, and has better overall performance.

Highlights

  • As important geographic data, high-resolution remote sensing (HRRS) images are widely used in geographic information extraction [1,2], surveying and mapping [3,4], Earth resource surveys [5], geological disaster investigation and rescue [6], land use [7], military reconnaissance [8] and other fields [9,10]

  • Compared with conventional perceptual hash, subject-sensitive perceptual hash is Compared with conventional perceptual hash, subject-sensitive perceptual hash is characterized characterized by using the trained multi-scale U-shape chained M-shape convolution network (MUM-Net) model to extract the perceptual features of high resolution remote sensing image (HRRS)

  • We first give a set of comparative examples to explain the subject-sensitive subject-sensitive hash in Section perceptual hash more vividly. 4.3

Read more

Summary

Introduction

High-resolution remote sensing (HRRS) images are widely used in geographic information extraction [1,2], surveying and mapping [3,4], Earth resource surveys [5], geological disaster investigation and rescue [6], land use [7], military reconnaissance [8] and other fields [9,10]. Since high precision and confidentiality are important characteristics of HRRS images, the use value of the HRRS images will be greatly reduced if people are not sure whether the HRRS images have been tampered with. The tampered HRRS image may even lose application value.

Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call