SIFT-SURF commutation using fuzzy logic to image mosaicking
Barba Ana Victoria, Alberto Rosales, Perez Hernandez L. Manuel · 2017
An alternative is presented to create an image mosaic commuting between the features extraction SIFT (Scale Invariant Features) and SURF (Speeded-Up Robust Features) algorithms. Due to the ambiguity in detail classification and switching between these algorithms, it is proposed to use a pre-processing stage and a fuzzy logic system for the feature extraction. Image register presents the intensity level assignation process in the pixels that are equal in the overlapping images. The following proposal is evaluated in a quantitative matter via the MAE (Mean Absolute Error) and PSNR (Peak Signal to Noise Ratio) factors, achieving better results.