The program uses HOG and LBP features to detect human in images. First, use the HOG feature only to detect humans. Next, combine the HOG feature with the LBP feature to form an augmented feature (HOG-LBP) to detect human. A Two-Layer Perceptron (feedforward neural network) will be used to classify the input feature vector into human or no-human.

A module that can extract LBP features (local binary pattern) from 3D images. Can be used for extracting features from medical images.

A two-class fingerprint spoof detector that uses Local Binary Patterns (LBP) features along with Support Vector Machines (SVM) to distinguish live fingerprints images from spoof samples.

Fingerprint-Spoof-Detector

Classifier for MOUSE eyes used in behavioural experiments.

It, shoes? It's a demo project to use both traditional computer vision methods and deep learning to detect and recognize shoes based on shoes7k dataset

Final course project for image processing in RPI