Haiyong Xu

Bio: Haiyong Xu is an academic researcher from Ningbo University. The author has contributed to research in topics: Image quality & Watermark. The author has an hindex of 9, co-authored 31 publications receiving 183 citations.

Difference of Gaussian statistical features based blind image quality assessment: A deep learning approach

Abstract: Nowadays, natural scene statistics (NSS) based blind image quality assessment (BIQA) models trained by machine learning, tend to achieve excellent performance. However, BIQA is still a very challenging research topic due to the lack of reference images. The key of further improvement lies in feature mining and pooling strategy decision. In this work, a new BIQA model is proposed to utilize local normalized multi-scale difference of Gaussian (DoG) response in distorted images as features which show a high correlation with perceptual quality. Then, a three-step-framework based deep neural network (DNN) is designed and employed as the pooling strategy. Compared with the support vector machine (SVM), the proposed three-step-framework DNN can excavate better feature representation, leading to more accurate predictions and stronger generalization ability. The proposed model achieves state-of-the-art performance on two authoritative databases and excellent generalization ability in cross database experiments.

A Two-Stage Underwater Enhancement Network Based on Structure Decomposition and Characteristics of Underwater Imaging

Abstract: Due to the scattering and attenuation of light into the water, the underwater image usually appears with color distortion, blurred details, and low contrast. To address these problems, a novel two-stage underwater image convolutional neural network (CNN) based on structure decomposition (UWCNN-SD) for underwater image enhancement is proposed by considering the characteristics of underwater imaging. Specifically, the raw underwater image is decomposed into high-frequency and low-frequency based on theoretical analysis of the underwater imaging. Then, a two-stage underwater enhancement network including a preliminary enhancement network and a refinement network is proposed. In the first stage, the preliminary enhancement network, which contains the high-frequency and the low-frequency enhancement networks, is proposed. The high-frequency part is enhanced directly by a deep learning network, and the low-frequency enhancement network is based on the underwater imaging, which is integrated transmission map and background light into joint component map. In the second stage, the refinement network is designed to further optimize the color of the underwater image by considering complexity of underwater imaging. The experimental results of synthetic and real-world underwater images/videos demonstrate that the proposed UWCNN-SD method can perform color correction and enhancement on different types of underwater images. The ablation study verifies the effectiveness of each component, and application tests further illustrate that the proposed UWCNN-SD method can obtain underwater images with higher visual quality. The trained model is available at: https://github.com/wushengcong/UWCNN-SD .

A novel robust color image watermarking method using RGB correlations

Abstract: In order to protect the copyright of the color image, a novel robust color image watermarking method using correlations of RGB channels is presented. RGB three channels of the color image have much strong correlations, which are stable under various image attacks, and thus these correlations can be mined to embed watermark for robustness. In order to keep RGB correlations and chrominance perception, the color image is considered as the third-order tensor, and tucker decomposition is employed to operate on the color image. At first, Tucker decomposition is used to generate the first feature image, which includes the most of image energies and correlations between three channels. Then, the first feature image is divided into non-overlap blocks, and the singular value decomposition (SVD) is used to decompose the block to compute the left-singular matrix. Finally, the stable coefficients relationship of the left-singular matrix is modified to embed watermark for obtaining the robustness. Experimental results show that the proposed method outperforms other existing color image watermarking methods, which can resist JPEG compression, salt & pepper noise, median filtering, scaling, blurring, low-pass filtering, and so on attacks.

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.

On the use of deep learning for blind image quality assessment

Abstract: In this work, we investigate the use of deep learning for distortion-generic blind image quality assessment. We report on different design choices, ranging from the use of features extracted from pre-trained convolutional neural networks (CNNs) as a generic image description, to the use of features extracted from a CNN fine-tuned for the image quality task. Our best proposal, named DeepBIQ, estimates the image quality by average-pooling the scores predicted on multiple subregions of the original image. Experimental results on the LIVE In the Wild Image Quality Challenge Database show that DeepBIQ outperforms the state-of-the-art methods compared, having a linear correlation coefficient with human subjective scores of almost 0.91. These results are further confirmed also on four benchmark databases of synthetically distorted images: LIVE, CSIQ, TID2008, and TID2013.