Enhanced pyramid image fusion on visible and infrared images at pixel and feature levels

Autor: Babu Reddy, B Ashalatha
Rok vydání: 2017
Předmět:
Zdroj: 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS).
DOI: 10.1109/icecds.2017.8389510
Popis: In today's Technology Advancements, Multi Scale Image Fusion plays a crucial role in the Digital Image Processing field. Various features of Multi-Scale Image Fusion are applied in areas such as Image Classification, Remote Vision, Medical Imaging, Satellite Imaging and Forensic Sciences. Multi-Scale Image Fusion can be described as combining the best features of two or more images which are at different resolution levels and getting a single coherent Fused Image. Laplacian Pyramid is a Multi-Scale Resolution technique, in which low resolution images are fused to produce a high resolution images. But the resultant high resolution image is a blurred image when compared to original images. This Paper provides a new method to remove the blurriness from the high resolution image using Wiener Filter. This method worked on Pyramid Image Fusion on Visible Images, Infrared Images and combination of Visible and Infrared Images at Pixel and Feature levels using Simple Average and PCA (Principle Component Analysis) methods. The Experimental results showed better PSNR (Peak Signal to Noise Ratio) Values than the Multi Scale Fusion process using Laplacian Pyramid
Databáze: OpenAIRE