Occluded Face Recognition Using Machine Learning

A fascinating and intense issue nowadays is the difficult problem of identifying human faces when they are obscured by various obstructions. Due to a sizable occluded zone dearth un-occluded portions, capacity most identification algorithms goes off dramatically. We describe pre-processing approach for that effective features-based fullest extent. Pose, lighting, age, emotions, hair covering face among 40 different occlusions included in dataset. Edge-preserving enhancement contrast measurement-correction pictures part two simultaneous procedures used step. Utilizing Gabor coefficients, Linear Binary Patterns based on Haar Wavelet components, Histogram Gaussian features, finest textural characteristics retrieved. The other set represent entire region composed wavelet color histograms, statistical global features first order. In order validate utilizing support vector machines, study takes into account 100 celebrities from CelebA dataset with posture occlusions. Compared well- known systems, suggested efficient optimal recognition system exhibited increased classification accuracy experiment analysis.