Feature fusion using the Local Binary Pattern Histogram Fourier and the Pyramid Histogram of Feature fusion using the Local Binary Pattern Oriented Gradient in iris recognition

Recently, more researchers have been interested in the fusion of many features of biometric modality. The real problems of the world are to find answers due to their assistance in finding solutions to a host of current real-world problems. Sufficient data is available in scheme that is easily accessible and can be put together into a feature vector. A combination of local Binary Pattern Histogram Fourier (LBP-HF) descriptor and the Pyramid Histogram of Oriented Gradient (PHOG) is concentrated on in this research, histogram bins are now made distinctive. Classifications may be hamper due to the fact that several features may result in problems. In order to find a solution to this difficulty, Principal Component Analysis (PCA) should be applied in order to minimize the size of the vector dimensionality of the iris features. The set of random samples of the compound features is setup to generate several weak multiple Support Vector Machine (SVM) classifiers and can be fused into a powerful digestion rule. Using the challenging CASIA-v4 database when experiments were conducted to determine the approach utility. It was found that the proposed work has excellent findings when the approach was evaluated against existing methods.