No-reference sharpness metric based on local edge kurtosis

Caviedes, Jorge E.; Gurbuz, Sabri

doi:10.1109/icip.2002.1038901

Cited by 117 publications

(60 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Common NR metrics include variance metric, auto-correlation metric, frequency threshold metric, histogram threshold metric, histogram frequency metric, generalized block-edge impairment metrics, etc. [15,16,17,18,19,20,21,22,23,24]. Distortions can be mainly classified into noise, blur, blocking artifact (including blocking blur).…”

Section: Introductionmentioning

confidence: 99%

“…Distortions can be mainly classified into noise, blur, blocking artifact (including blocking blur). Many NR metrics can only measure some types of distortions, especially feasible for blocking or blur [15,16,17,18,19,20,21,22]. In [23], a natural scene statistics (NSS) model of contourlet coefficients adopts an image-dependent threshold to assess different distortions, but its accuracy still need to be further improved and it needs a training database to determine proper related parameters of the approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

No-Reference Image Quality Assessment through SIFT Intensity

Sun¹,

Ding²,

Xu³

2014

Appl. Math. Inf. Sci.

View full text Add to dashboard Cite

SIFT (Scale Invariant Feature Transform) points are scale-space extreme points, representing local minutiae structure features in the Gaussian scale space. SIFT intensity, as a novel no-reference metric, is feasible to assess various common distortions without the access to reference images. The metric introduces image preprocessing: neighborhood enhancement through contrast enhancement of adjacent pixels to reduce false SIFT points triggered by random signals; double-size image magnification through linear interpolation to amplify distortion effects to improve its sensitivity to image quality. SIFT intensity is defined as the number of SIFT points in a unit region and is calculated based on the first octave of the difference-of-Gaussian scale space. Experimental results demonstrate that SIFT intensity is superior to existing classic no-reference metrics and can be used to assess different distortions.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

No-Reference Image Quality Assessment through SIFT Intensity

Sun¹,

Ding²,

Xu³

2014

Appl. Math. Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…As an improvement over the global kurtosis sharpness measure [19], Caviedes et al proposed a local kurtosis sharpness measure based on detected edges [24]. Compared with other edge based algorithms, the local kurtosis measure handles different types of edges in the same fashion and elegantly avoids the difficulty in distinguishing step and line edges.…”

Section: B Sharpness Measuresmentioning

confidence: 99%

Extreme Zoom Surveillance: System Design and Image Restoration

Yao¹,

Abidi²,

Abidi³

2007

JMM

View full text Add to dashboard Cite

Abstract-Applications of digital imaging with extreme zoom are traditionally found in astronomy and wild life monitoring. More recently, the need for such capabilities has extended to long range surveillance and wide area monitoring such as forest fires, harbors, and waterways. In this paper, we present a number of sensor arrangements for such applications, focusing on optical setups, auto-focusing mechanisms, and image deblurring techniques. Considering both the speed of convergence and robustness to image degradations induced by high system magnifications and long observation distances, we introduce an auto-focusing algorithm based on sequential search with a variable step size. We derive the transition criteria following maximum likelihood (ML) estimation for the selection of suitable step sizes. The efficiency of the proposed algorithm is illustrated in real-time auto-focusing and tracking of faces from distances of 50m~300m.We also develop an image restoration algorithm for high magnification imaging systems, where an adaptive sharpness measure is employed as a cost function to guide the fine search for an optimal point spread function (PSF) for image deblurring. Experimental results demonstrate a considerably enhanced robustness to image noise and artifacts and ability to select the optimum PSF, producing superior restored images.

show abstract

“…A content independent sharpness metric has been proposed in [34]. It is motivated by observations on statistical measures of image frequency distributions.…”

Section: A Single Feature Metricsmentioning

confidence: 99%