Face Recognition using MATLAB

matlabhelpers demonstrate the process of constructing a face recognition program in MATLAB. Face recognition is the process of identifying one or more people in images or videos by analyzing and comparing patterns. Algorithms for face recognition typically extract facial features and compare them to a database to find the best match. Face recognition is an important part of many biometric, security, and surveillance systems, as well as image and video indexing systems. Face recognition gives computer vision to extract discriminative information from facial images, and pattern recognition or machine learning techniques to model the appearance of faces and to classify them. Machine learning techniques that are applied to the extracted features to perform face recognition or classification using: Supervised learning techniques such as support vector machines (SVM) and decision trees, Ensemble learning methods, Deep neural networks.

One of the most common projects students want to implement is Face Recognition system. Almost in every academic semester, students are required to submit their final year project. A large number of these students submit projects on Face Recognition. There are many ways of recognizing a face. Today I will show the simplest way of implementing a face recognition system using MATLAB. Here no machine learning or Convolutional neural network (CNN) is required to recognize the faces. To keep the face recognition system as simple as possible, I used eigenvector based recognition system. The recognition part is very easy. However, I have seen most of the people struggle with preparing and loading the dataset. In this tutorial, I covered dataset preparation, loading dataset and using them to recognize faces. You can download the dataset from the link below. You can copy the codes as well.

Deep learning methods, especially convolutional neural networks have achieved significant success in the area of computer vision including the difficult face recognition problems. Training of deep models shows exceptional performance with large datasets, but they are not suitable for learning from few samples. This paper proposes a modified deep learning neural network to learn face representation from a smaller dataset. The proposed network is composed of a set of elaborately designed CNNs, RELUs and fully connected layers. The training dataset is augmented with synthetically generated samples by applying Gaussian and Poisson noise to each sample of the training set, thus doubling the size of the training set.