Visible to the public Non-subsampled contourlet based feature level fusion using fuzzy logic and golden section algorithm for multisensor imaging systems

TitleNon-subsampled contourlet based feature level fusion using fuzzy logic and golden section algorithm for multisensor imaging systems
Publication TypeConference Paper
Year of Publication2015
AuthorsNirmala, D. E., Vaidehi, V.
Conference Name2015 IEEE International Conference on Computer Graphics, Vision and Information Security (CGVIS)
Keywordschoose-max fusion rule, feature extraction, Feature-level fusion, feature-level fusion methods, feature-level fusion schemes, Fuzzy logic, golden section algorithm, GSA, Image edge detection, image fusion, image fusion algorithm, Image resolution, image segmentation, image sensors, imaging sensors, mean rule blurs, mean-max fusion rule, multiresolution-based methods, multisensor imaging systems, nonsubsampled contourlet transform, nonsubsampled contourlet-based feature level fusion, NSCT, NSCT and Golden Section Algorithm, objective quality metrics, optimal fusion weights, Petrovic metric, pubcrawl170111, Transforms, visual sensor technology, visualization

With the recent developments in the field of visual sensor technology, multiple imaging sensors are used in several applications such as surveillance, medical imaging and machine vision, in order to improve their capabilities. The goal of any efficient image fusion algorithm is to combine the visual information, obtained from a number of disparate imaging sensors, into a single fused image without the introduction of distortion or loss of information. The existing fusion algorithms employ either the mean or choose-max fusion rule for selecting the best features for fusion. The choose-max rule distorts constants background information whereas the mean rule blurs the edges. In this paper, Non-Subsampled Contourlet Transform (NSCT) based two feature-level fusion schemes are proposed and compared. In the first method Fuzzy logic is applied to determine the weights to be assigned to each segmented region using the salient region feature values computed. The second method employs Golden Section Algorithm (GSA) to achieve the optimal fusion weights of each region based on its Petrovic metric. The regions are merged adaptively using the weights determined. Experiments show that the proposed feature-level fusion methods provide better visual quality with clear edge information and objective quality metrics than individual multi-resolution-based methods such as Dual Tree Complex Wavelet Transform and NSCT.

Citation Keynirmala_non-subsampled_2015