Blind Quality Assessment of Tone-Mapped Images Via Analysis of Information, Naturalness, and Structure

Gu, Ke; Wang, Shiqi; Zhai, Guangtao; Ma, Siwei; Yang, Xiaokang; Wang, Lin; Zhang, Wenjun; Gao, Wen

doi:10.1109/tmm.2016.2518868

Cited by 194 publications

(91 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As different image processing tasks may produce images with various kinds of distortion, task-oriented IQA tailored for each task individually becomes necessary. For example, Gu et al study quality assessment methods for contrast enhancement [10] and tone mapping [8]. For image and video compression, blocking, blur, and ringing artifacts are often detected as metrics for IQA [15,30].…”

Section: Related Workmentioning

confidence: 99%

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Liu

Wang

2016

Sens Imaging

View full text Add to dashboard Cite

Traditionally, image compression was optimized for the pixel-wise fidelity or the perceptual quality of the compressed images given a bit-rate budget. But recently, compressed images are more and more utilized for automatic semantic analysis tasks such as recognition and retrieval. For these tasks, we argue that the optimization target of compression is no longer perceptual quality, but the utility of the compressed images in the given automatic semantic analysis task. Accordingly, we propose to evaluate the quality of the compressed images neither at pixel level nor at perceptual level, but at semantic level. In this paper, we make preliminary efforts towards image semantic quality assessment (ISQA), focusing on the task of optical character recognition (OCR) from compressed images. We propose a fullreference ISQA measure by comparing the features extracted from text regions of original and compressed images. We then propose to integrate the ISQA measure into an image compression scheme. Experimental results show that our proposed ISQA measure is much better than PSNR and SSIM in evaluating the semantic quality of compressed images; accordingly, adopting our ISQA measure to optimize compression for OCR leads to significant bit-rate saving compared to using PSNR or SSIM. Moreover, we perform subjective test about text recognition from compressed images, and observe that our ISQA measure has high consistency with subjective recognizability. Our work explores new dimensions in image quality assessment, and demonstrates promising direction to achieve higher compression ratio for specific semantic analysis tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Liu

Wang

2016

Sens Imaging

View full text Add to dashboard Cite

show abstract

“…The goal of the data term ( − ) 2 is to minimize the distance between u and g, while the second (regularization) term strives to achieve smoothness by minimizing the partial derivatives of u. Finally, is responsible for the balance between the two terms; increasing the value of l results in progressively smoother images u.…”

Section: Edge-preserving Smoothing Via Wlsmentioning

confidence: 99%

“…Wei et al [1] presents a two layer local inverse Tone Mapping assessment algorithm by decomposing via edge-preserving method. Ke Gu et al [2] provides a High dynamic range (HDR) imaging methods working actively. They developed an objective quality metric based LDR images creation by many TMOs without accessing original HDR images.…”

Section: Introductionmentioning

confidence: 99%

CIELAB based Tone-Mapping Algorithm for LDR Image Generation

Patle¹,

Jain²

2016

IJCA

View full text Add to dashboard Cite

This paper presents a analysis of the CIELAB color feature based tone mapping technique. The basic tone mapping was generally the reverse going to the old technology objects compatibility. The compatibility is the basic requirement of the market to grow with the latest technology and the old objects to work with new technology. The paper worked for maintaining this compatibility. The basic theme of the work is done in the SCIELAB color space. The proposed method has done the tone mapping through the decomposition of the image in this SCIELAB color space. The Visual quality of the proposed method is same as of saliency based tone mapping but it is more computational efficient.

show abstract

“…The third type of objective IQA methods are currently popular blind/no-reference (NR) IQA models. A majority of this type of methods depend on statistical regulations (see [12]- [15]). …”

Section: Introductionmentioning

confidence: 99%

No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization

Wang

Zhai

et al. 2017

IEEE Trans. Cybern.

Self Cite

298

101

View full text Add to dashboard Cite

The general purpose of seeing a picture is to attain information as much as possible. With it, we in this paper devise a new no-reference/blind metric for image quality assessment (IQA) of contrast distortion. For local details, we first roughly remove predicted regions in an image since unpredicted remains are of much information. We then compute entropy of particular unpredicted areas of maximum information via visual saliency. From global perspective, we compare the image histogram with the uniformly distributed histogram of maximum information via the symmetric Kullback-Leibler divergence. The proposed blind IQA method generates an overall quality estimation of a contrast-distorted image by properly combining local and global considerations. Thorough experiments on five databases/subsets demonstrate the superiority of our training-free blind technique over state-of-the-art full- and no-reference IQA methods. Furthermore, the proposed model is also applied to amend the performance of general-purpose blind quality metrics to a sizable margin.

show abstract

Blind Quality Assessment of Tone-Mapped Images Via Analysis of Information, Naturalness, and Structure

Cited by 194 publications

References 38 publications

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

Recognizable or Not: Towards Image Semantic Quality Assessment for Compression

CIELAB based Tone-Mapping Algorithm for LDR Image Generation

No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization

Contact Info

Product

Resources

About