BRISQUE算法：一种无参考图像质量评估模型

需积分: 9 121 浏览量更新于2024-09-07 收藏 1.78MB PDF 举报

"本文介绍了一种名为BRISQUE(Blind/Referenceless Image Spatial Quality Evaluator)的图像质量评估算法，该算法适用于无参考或盲参考的图像质量分析，尤其在图像清晰度评价方面表现出色。它基于自然场景统计学原理，能够在空间域内进行操作，无需计算特定类型的失真特征，如振铃、模糊或块效应，而是通过量化局部归一化亮度系数的自然性损失来评估图像质量。BRISQUE利用局部归一化的亮度及其乘积在自然场景统计模型下的经验分布作为基础特征。与其他NR IQA方法不同，BRISQUE不需要进行DCT、小波等坐标变换。尽管简单，但BRISQUE在图像质量评估上的性能表现良好。" 详细说明: BRISQUE算法是一种针对图像质量评估的无参考或盲参考方法，这意味着它不需要原始未失真的参考图像也能对图像质量进行有效评估。这种方法主要关注于图像的"自然性"损失，即图像由于失真所失去的视觉真实感。在算法设计上，BRISQUE摒弃了传统的针对特定失真类型（如压缩噪声、模糊、量化等）的特征提取，转而采用一种更为通用的方法。核心在于，BRISQUE分析局部归一化的亮度系数及其乘积，这些特征来源于自然场景统计模型。自然场景统计理论认为，正常、未受干扰的图像具有一定的统计特性，这些特性可以作为判断图像质量的基础。BRISQUE通过计算这些局部统计特征的偏离程度，来评估图像失真的程度，进而得出一个全面的质量评分。算法的另一个显著特点是其在空间域内的操作。大多数其他无参考图像质量评估方法可能会使用DCT（离散余弦变换）、小波或其他频域变换来提取特征，而BRISQUE则直接在图像的像素空间进行分析，这简化了计算过程，提高了效率。尽管BRISQUE的设计相对简洁，但它在多个公开的图像质量数据库上的性能测试表明，该算法能够有效地预测人类视觉系统对图像质量的感知，具有较高的评估准确性和一致性。因此，BRISQUE在图像处理、图像压缩、视频编码等领域有着广泛的应用价值，对于优化图像处理算法和提高用户体验有重要的指导作用。

MITTAL et al.: NR IQA IN THE SPATIAL DOMAIN 4697

in this way is sufﬁcient not only to quantify naturalness, but

also to quantify quality in the presence of distortion.

In this article, we detail the statistical model of locally

normalized luminance coefﬁcients in the spatial domain, as

well as the model for pairwise products of these coefﬁcients.

We describe the statistical features that are used from the

model and demonstrate that these features correlate well with

human judgements of quality. We then describe how we learn

a mapping from features to quality space to produce an

automatic blind measure of perceptual quality. We thoroughly

evaluate the performance of BRISQUE, and statistically com-

pare BRISQUE performance to state-of-the-art FR and NR

IQA approaches. We demonstrate that BRISQUE is highly

competitive to these NR IQA approaches, and also statistically

better than the popular full-reference peak signal-to-noise-

ratio (PSNR) and structural similarity index (SSIM). We

show that BRISQUE performs well on independent databases,

analyze its complexity and compare it with other NR IQA

approaches. Finally, to further illustrate the practical relevance

of BRISQUE, we describe how a non-blind image denoising

algorithm can be augmented with BRISQUE in order to

improve blind image denoising. Results show that BRISQUE

augmentation leads to signiﬁcant performance improvements

over the state-of-the-art. Before we describe BRISQUE in

detail, we ﬁrst brieﬂy review relevant prior work in the area

of blind IQA.

II. P

REVIOUS WORK

Most existing blind IQA models proposed in the past

assume that the image whose quality is being assessed is

afﬂicted by a particular kind of distortion [5]–[11], [17].

These approaches extract distortion-speciﬁc features that relate

to loss of visual quality, such as edge-strength at block-

boundaries. However, a few general purpose approaches for

NR IQA have been proposed recently.

Li devised a set of heuristic measures to characterize visual

quality in terms of edge sharpness, random noise and structural

noise [18] while Gabarda and Cristobal, modeled anisotropies

in images using Renyi entropy [19]. The authors in [20]

use gabor ﬁlter based local appearance descriptors to form

a visual codebook, and learn DMOS score vector, associating

each word with a quality score. However, in the process of

visual codebook formation, each feature vector associated with

an image patch is labeled by DMOS asigned to the entire

image. This is questionable as each image patch can present a

different level of quality depending on the distortion process

the image is afﬂicted with. In particular, local distortions

such as packet loss might afﬂict only a few image patches.

Also, the approach is computationally expensive limiting its

applicability in real time applications.

Tang et al. [21] proposed an approach which learns an

ensemble of regressors trained on three different groups of

features - natural image statistics, distortion texture statistics

and blur/noise statistics. Another approach [22] is based on a

hybrid of curvelet, wavelet and cosine transforms. Although

these approaches work on a variety of distortions, each set

of features (in the ﬁrst approach) and transforms (in the

second) caters only to certain kinds of distortion processes.

This limits the applicability of their framework to new

distortions.

We have also developed previous NR QA models in the

past, following our philosophy, ﬁrst fully developed in [23],

that NSS models provide powerful tools for probing human

judgements of visual distortions. Our work on NSS based

FR QA algorithms [9], [23], [24], more recent RR models

[3] and very recent work on NSS based NR QA [12],

[13], [25] have led us to the conclusion that visual features

derived from NSS lead to particularly potent and simple QA

models [26].

Our recently proposed NSS based NR IQA model, dubbed

the Distortion Identiﬁcation-based Image INtegrity and Ver-

ity Evaluation (DIIVINE) index, deploys summary statistics

derived from an NSS wavelet coefﬁcient model, using a two

stage framework for QA: distortion-identiﬁcation followed by

distortion-speciﬁc QA [12]. The DIIVINE index performs

quite well on the LIVE IQA database [27], achieving statistical

parity with the full-reference structural similarity (SSIM)

index [28].

A complementary approach developed at the same time,

named BLind Image Notator using DCT Statistics (BLIINDS-

II index) is a pragmatic approach to NR IQA that operates

in the DCT domain, where a small number of features are

computed from an NSS model of block DCT coefﬁcients [13].

Efﬁcient NSS features are calculated and fed to a regression

function that delivers accurate QA predictions. BLIINDS-II is

a single-stage algorithm that also delivers highly competitive

QA prediction power. Although BLIINDS-II index is multi-

scale, the small number of feature types (4) allow for efﬁcient

computation of visual quality and hence the index is attractive

for practical applications.

While both DIIVINE and BLIINDS-II deliver top NR IQA

performance (to date), each of them has certain limitations.

The large number of features that DIIVINE computes implies

that it may be difﬁcult to compute in real time. Although

BLIINDS-II is more efﬁcient than DIIVINE, it requires non-

linear sorting of block based NSS features, which slows it

considerably.

In our continued search for fast and efﬁcient high perfor-

mance NSS based NR QA indices, we have recently stud-

ied the possibility of developing transform-free models that

operate directly on the spatial pixel data. Our inspiration for

thinking we may succeed is the pioneering work by Ruderman

[15] on spatial natural scene modeling, and the success of the

spatial multi-scale SSIM index [29], which competes well with

transform domain IQA models.

III. B

LIND SPATIAL IMAGE QUALITY ASSESSMENT

Much recent work has focused on modeling the statistics

of responses of natural images using multiscale transforms

(eg., Gabor ﬁlters, wavelets etc.) [16]. Given that neuronal

responses in area V1 of visual cortex perform scale-space-

orientation decompositions of visual data, transform domain

models seem like natural approaches, particularly in view of

the energy compaction (sparsity) and decorrelating properties

剩余13页未读，继续阅读

ning0025isme

粉丝: 1
资源: 1

BRISQUE算法：一种无参考图像质量评估模型

人工智能算法论文

十大经典算法及相关论文

关于蚁群算法的各种论文

关于四元数法捷联惯导解算算法的matlab程序组合包

程序员算法大全

C语言算法大全

算法导论代码

A*算法matlab

DBFLZO算法解压工具

粒子群算法与VMD算法的优化整合研究

最新资源