Learning receptive fields and quality lookups for Blind quality assessment of stereoscopic images - 2016

PROJECT TITLE :

Learning receptive fields and quality lookups for Blind quality assessment of stereoscopic images - 2016

ABSTRACT:

Blind quality assessment of 3D pictures encounters a lot of new challenges than its 2D counterparts. During this paper, we have a tendency to propose a blind quality assessment for stereoscopic images by learning the characteristics of receptive fields (RFs) from perspective of dictionary learning, and constructing quality lookups to replace human opinion scores while not performance loss. The necessary feature of the proposed methodology is that we tend to don't would like a giant set of samples of distorted stereoscopic pictures and therefore the corresponding human opinion scores to be told a regression model. To be additional specific, in the training phase, we tend to learn native RFs (LRFs) and international RFs (GRFs) from the reference and distorted stereoscopic images, respectively, and construct their corresponding native quality lookups (LQLs) and international quality lookups (GQLs). Within the testing section, blind quality pooling can be easily achieved by looking optimal GRF and LRF indexes from the learnt LQLs and GQLs, and the quality score is obtained by combining the LRF and GRF indexes together. Experimental results on three publicly 3D image quality assessment databases demonstrate that compared with the existing ways, the devised algorithm achieves high consistent alignment with subjective assessment.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here