Reduced-reference stereoscopic image quality assessment based on view and disparity zero-watermarks

Zhou, Wujie; Jiang, Gangyi; Yu, Mei; Shao, Feng; Peng, Zongju

doi:10.1016/j.image.2013.10.005

Cited by 20 publications

(12 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Objective IQA models can automatically predict the degree of image distortion and are usually used for monitoring and controlling multimedia services, ensuring that end-users receive a satisfactory quality of experience [1]. Generally, objective IQA methods can be divided into three categories: full-reference (FR) [2], reduced-reference (RR) [3] and no-reference (NR) [4] or blind image quality assessment (BIQA). FR-IQA methods directly quantify the difference between distorted images and their perfect versions.…”

Section: Introductionmentioning

confidence: 99%

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

Jiang

et al. 2015

2015 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

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-stepframework based deep neural network (DNN) is designed and employed as the pooling strategy. Compared with the support vector machine (SVM), the proposed three-stepframework DNN can excavate better feature representation, leading to more accurate predictions and stronger generalization ability. The proposed model achieves stateof-the-art performance on two authoritative databases and excellent generalization ability in cross database experiments.Index Terms-Blind image quality assessment, deep neural network, stacked auto-encoder, DoG.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Jiang

et al. 2015

2015 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the development of the information hiding technology, Pizzolante (2014) proposed to take the digital watermarking technique applied to the microscope images. The digital watermark is divided into image watermarks (Tsai et al 2013;Zhou et al 2014), audio watermark (Duymaz 2012;Zhang et al 2014b), video watermark (Xie et al 2013;Panyavaraporn 2013) and the alike according to different formats. Castiglione et al proposed an engine for lossless dynamic and adaptive compression of 3D medical images, and they also embedded security watermarks within them.…”

Section: Introductionmentioning

confidence: 99%

A digital image watermarking method based on host image analysis and genetic algorithm

Han

Zhao

Qiu

2015

J Ambient Intell Human Comput

View full text Add to dashboard Cite

This paper mainly comes up with a new watermarking method based on host image analysis and genetic algorithm. Through the characteristics of human visual system, the host image analysis can ensure the imperceptibility. It greatly enhance the embedding capacity of the watermark under the same visual effect, which can embed more watermark in the host image. The genetic algorithm is used in embedding process. It can not only improve the image quality, but also enhance the security and robustness of the watermarked image in a large extent. This algorithm satisfies an optimal compromise between the robustness and image quality. Besides that, the experimental results show that this method has great influence on transparency and robustness.

show abstract

“…Most objective image quality assessment methods [12,14,[64][65][66][67][68] either require access to the original image as reference [8,14,67,68] or only can evaluate images, degraded with predefined distortions [64][65][66]76] and therefore, lacking generalization approach. Reduced reference IQA methods [13,[64][65][66] provide a solution by extracting a minimal set of parameters from the reference image for cases where the reference image is not fully accessible.…”

Section: Introductionmentioning

confidence: 99%

“…Reduced reference IQA methods [13,[64][65][66] provide a solution by extracting a minimal set of parameters from the reference image for cases where the reference image is not fully accessible. However, determination of the effective parameter set is an important issue.…”

Section: Introductionmentioning

confidence: 99%

“…However, determination of the effective parameter set is an important issue. No-reference IQA algorithms [60][61][62][63][64][65][66][67][68][69][70][71][72][73][74][75][76][77] attempt to perform quality evaluation for specific type of distorted images [60][61][62] and designed specifically for JPEG or JPEG2000 compression artifacts [15]. Two prominent works by Wang et al [10] and Sheikh [9] have been reported relating to no-reference image quality assessment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

No-reference image quality assessment using interval type 2 fuzzy sets

Sil

2015

Applied Soft Computing

View full text Add to dashboard Cite

Reduced-reference stereoscopic image quality assessment based on view and disparity zero-watermarks

Cited by 20 publications

References 37 publications

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

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

A digital image watermarking method based on host image analysis and genetic algorithm

No-reference image quality assessment using interval type 2 fuzzy sets

Contact Info

Product

Resources

About