Geng Zhao

Bio: Geng Zhao is an academic researcher from Beijing Electronic Science and Technology Institute. The author has contributed to research in topics: Encryption & Deep learning. The author has an hindex of 10, co-authored 35 publications receiving 392 citations.

Chaos-based image encryption scheme combining DNA coding and entropy

Abstract: Information security has became more and more important issue in modern society, one of which is the digital image protection. In this paper, a secure image encryption scheme based on logistic and spatiotemporal chaotic systems is proposed. The extreme sensitivity of chaotic system can greatly increase the complexity of the proposed scheme. Further more, the scheme also takes advantage of DNA coding and eight DNA coding rules are mixed to enhance the efficiency of image confusion and diffusion. To resist the chosen-plaintext attack, information entropy of DNA coded image is modulated as the parameter of spatiotemporal chaotic system, which can also guarantee the sensitivity of plain image in the encryption process. So even a slight change in plain image can cause the complete change in cipher image. The experimental analysis shows that it can resistant different attacks, such as the brute-force attack, statistical attack and differential attack. What's more, The image encryption scheme can be easily implemented by software and is promising in practical application.

Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence

Abstract: Aesthetic quality prediction is a challenging task in the computer vision community because of the complex interplay with semantic contents and photographic technologies. Recent studies on the powerful deep learning based aesthetic quality assessment usually use a binary high-low label or a numerical score to represent the aesthetic quality. However the scalar representation cannot describe well the underlying varieties of the human perception of aesthetics. In this work, we propose to predict the aesthetic score distribution (i.e., a score distribution vector of the ordinal basic human ratings) using Deep Convolutional Neural Network (DCNN). Conventional DCNNs which aim to minimize the difference between the predicted scalar numbers or vectors and the ground truth cannot be directly used for the ordinal basic rating distribution. Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization). Experimental results on large scale aesthetic dataset demonstrate the effectiveness of our introduced CJS-CNN in this task.

ILGNet: inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation

Abstract: In this study, the authors address a challenging problem of aesthetic image classification, which is to label an input image as high- or low-aesthetic quality. We take both the local and global features of images into consideration. A novel deep convolutional neural network named ILGNet is proposed, which combines both the inception modules and a connected layer of both local and global features. The ILGnet is based on GoogLeNet. Thus, it is easy to use a pre-trained GoogLeNet for large-scale image classification problem and fine tune their connected layers on a large-scale database of aesthetic-related images: AVA, i.e. domain adaptation . The experiments reveal that their model achieves the state of the arts in AVA database. Both the training and testing speeds of their model are higher than those of the original GoogLeNet.

Color image encryption in non-RGB color spaces

Abstract: To protect the contents of images in the mobile internet era during image storage and transmission, image encryption has achieved a tremendous success during the last decades. Traditional color image encryption method often use the RGB color space. We have the observation that in non-RGB color spaces, the luminance channels often contain more information for content recognition than the chroma channels do. Thus, in this paper we propose to use high level encryption schemes in more informative channels and low level encryption schemes in less informative channels. The 2D Arnold’s cat map followed by the 3D Lu chaotic map are conducted in the luminance channel. The less complicated DNA coding and 1D logistic map based encryption scheme is leveraged in the chroma channels. We use this strategies in 4 typical non-RGB color spaces, i.e., YCbCr, YIQ, HSV, L*a*b*. We evaluate and compare the performances and the time consumptions of the methods in the 4 Non-RGB color spaces. The experimental results reveal that the encryption methods in Non-RGB color spaces can achieve similar results as the method that conducts the same encryption level in each channel of the RBG color space, including the resistance to several attacks such as brute-force attack, statistic attack, correlation attack, while consuming less time. The method in YCbCr color space performances the best in the time consumption.

3D textured model encryption via 3D Lu chaotic mapping

Abstract: In the emerging Virtual/Augmented Reality (VR/AR) era, three dimensional (3D) content will be popularized just as images and videos today The security and privacy of these 3D contents should be taken into consideration 3D contents contain surface models and solid models Surface models include point clouds, meshes and textured models Previous work mainly focused on the encryption of solid models, point clouds and meshes This work focuses on the most complicated 3D textured model We propose a 3D Lu chaotic mapping based encryption method for 3D textured models We encrypt the vertices, polygons, and textures of 3D models separately using the 3D Lu chaotic mapping Then the encrypted vertices, polygons and textures are composited together to form the final encrypted 3D textured model The experimental results reveal that our method can encrypt and decrypt 3D textured models correctly Furthermore, typical statistic and brute-force attacks can be resisted by the proposed method

Perceptual image quality assessment: a survey

Abstract: Perceptual quality assessmentplays a vital role in the visual communication systems owing to theexistence of quality degradations introduced in various stages of visual signalacquisition, compression, transmission and display.Quality assessment for visual signals can be performed subjectively andobjectively, and objective quality assessment is usually preferred owing to itshigh efficiency and easy deployment. A large number of subjective andobjective visual quality assessment studies have been conducted during recent years.In this survey, we give an up-to-date and comprehensivereview of these studies.Specifically, the frequently used subjective image quality assessment databases are firstreviewed, as they serve as the validation set for the objective measures.Second, the objective image quality assessment measures are classified and reviewed according to the applications and the methodologies utilized in the quality measures.Third, the performances of the state-of-the-artquality measures for visual signals are compared with an introduction of theevaluation protocols.This survey provides a general overview of classical algorithms andrecent progresses in the field of perceptual image quality assessment.

A Comprehensive Review on Image Encryption Techniques

Abstract: Image encryption techniques play a significant role in multimedia applications to secure and authenticate digital images. This paper presents a comprehensive study of various image encryption techniques. This paper covers the most significant developments in meta-heuristic based image encryption techniques. The various attacks and performance measures related to image encryption techniques have also been studied. The existing techniques are analyzed with respect to differential, statistical, and key analyses. The main goal of this paper is to give a broad perspective on characteristics of image encryption techniques. The paper concludes by discussing significant advancements in the field of image encryption and highlighting future challenges.