PROJECT TITLE :
Fast Representation Based on a Double Orientation Histogram for Local Image Descriptors - 2015
In recent years, extensive analysis on native invariant options has been conducted, and many novel descriptors have been developed for various situations. Frequently, these descriptors will supply distinctive benefits (such as stability, precision, and speed) for select applications but perform unsatisfactorily from a comprehensive perspective. Consequently, a novel native image descriptor, named quick illustration using a double orientation histogram (FRDOH), is developed in this paper primarily based on existing descriptors. First, a part is divided using intensity order (as in the native intensity order pattern descriptor) to encode spatial data. Then, the discriminability of the descriptor is enhanced using our proposed double orientation histogram. Second, to any improve the discriminability of the descriptor, the Hellinger distance is used to balance the results of huge and small bins within the histogram for the similarity measure of features. Finally, a novel interpolation strategy known as rapidly cascaded interpolation is employed to calculate the intensity of the neighboring points to cut back the computation time, whereas achieving high precision. The performance of the developed descriptor is evaluated via varied experiments on the affine covariant feature knowledge set of the Oxford knowledge set, a subset of a 3D object data set, and a subset of the IIT Delhi Touchless Palmprint knowledge set. These experiments demonstrate that the developed FRDOH descriptor outperforms the state-of-the-art descriptors in terms of comprehensive performance.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here