A study on the relationship between depth map quality and stereoscopic image quality using upsampled depth maps - Emerging Trends in Image Processing, Computer Vision, and Pattern Recognition - page 125

2.2 NR IQA Tools
2.2.1 Sharpness degree
Sharpness degree [ 16 ] is used to represent the extent of sharpness of the image and is deined
by the following equation:
(3)
where
2.2.2 Blur metric
Another tool for measuring blur atempts to obtain the spread of the edges. First, an edge de-
tector (e.g., a Sobel edge detector) is applied to a grayscale image. We scan each row of the
image for pixels corresponding to an edge location. The start and end positions of the edge
are defined as the locations of the local extrema closest to the edge. The spread of the edge is
then given by the distance between the end and start positions and is identified as the local
blur measure for this edge location. The global blur measure for the whole image is obtained
by averaging the local depth values over all edges found [ 17 ] :
(4)
2.2.3 Blind image quality index
Blind image quality index (BIQI) [ 18 ] identifies the likeliest distortion in the image and then
quantiies this distortion using an NSS-based approach. Given a distorted image, the al-
gorithm first estimates the presence of a set of distortions in the image that consists of JPEG,
JPEG2000, white noise, Gaussian Blur, and Fast fading. The amount or probability of each dis-