Quaternion Structural Similarity: A New Quality Index for Color Images

Amir Kolaman, Orly Yadid-Pecht

Abstract:

One of the most important issues for researchers developing
image processing algorithms is image quality.Methodical
quality evaluation, by showing images to several human observers,
is slow, expensive, and highly subjective. On the other hand, a visual
quality matrix (VQM) is a fast, cheap, and objective tool for
evaluating image quality. Although most VQMs are good in predicting
the quality of an image degraded by a single degradation,
they poorly perform for a combination of two degradations. An
example for such degradation is the color crosstalk (CTK) effect,
which introduces blur with desaturation. CTK is expected to become
a bigger issue in image quality as the industry moves toward
smaller sensors. In this paper, we will develop a VQM that will
be able to better evaluate the quality of an image degraded by a
combined blur/desaturation degradation and perform as well as
other VQMs on single degradations such as blur, compression, and
noise. We show why standard scalar techniques are insufficient to
measure a combined blur/desaturation degradation and explain
why a vectorial approach is better suited.We introduce quaternion
image processing (QIP), which is a true vectorial approach and has
many uses in the fields of physics and engineering. Our new VQM
is a vectorial expansion of structure similarity using QIP, which
gave it its name—Quaternion Structural SIMilarity (QSSIM).We
built a new database of a combined blur/desaturation degradation
and conducted a quality survey with human subjects. An extensive
comparison between QSSIM and other VQMs on several image
quality databases—including our new database—shows the superiority
of this new approach in predicting visual quality of color
images.