TY - JOUR
AU1 - Hariharan, K.
AU2 - Raajan, N. R.
AB - Multispectral and hyper spectral image fusion aspires to improve the spectral information and spatial details. Previous fusion algorithms have concentrated on spectral information and spatial details, but those fused images have missed its sharpening. This paper is introduced the ripple type-II (RT-II) transform and deep neural network (DNN). RT -II transform can be decomposed both multispectral and hyper spectral images, then DNN are used for recognize the complementary features and sharpened the decomposed images. Then applied the fused rules for fuse the both images and applied inverse RT -II transform to get fused image. In this paper, the proposed method gets better entropy, standard deviation (SD), Correlation Coefficient (CC), Edge-Dependent Fusion Quality Index (EDFQI), Edge Based Similarity Measure (EBSM), Structural similarity (SSIM) as compared with other methods. The best way of analyzing the concepts of date and image fusion methods is to perform fusion based analysis in multimedia based tools.so that an end user can understand easily. The aspects like video, sound, text, animation, graphics have been elucidated by means of multimedia tools.
TI - Performance enhanced hyperspectral and multispectral image fusion technique using ripplet type-II transform and deep neural networks for multimedia applications
JF - Multimedia Tools and Applications
DO - 10.1007/s11042-018-6174-3
DA - 2020-02-05
UR - https://www.deepdyve.com/lp/springer-journals/performance-enhanced-hyperspectral-and-multispectral-image-fusion-CFOaiVaXQg
SP - 3561
EP - 3570
VL - 79
IS - 5-6
DP - DeepDyve