Unsupervised Learning Techniques in Neural Network for Face Recognition
This paper represents the review of systematic comparison between of unsupervised learning algorithms for face recognition. In neural network, different algorithms are used for face recognition. Each algorithm has different accuracy factors. Commonly these methods asset a set of base images and serve faces as linear combo of images. In our proposed review, firstly we discuss about the face detection using neural network along with the concept of digital image processing. In this paper, different era algorithms: K-means, C-means, PCA (principle component analysis), single SVM (support vector machine), ensemble SVM, RBF (redial basis function), and LVQ (learning vector quantization) are compared on the basis of recognition rate, error rate and identify the best algorithm.
Keywords: Face recognition (FR), recognition rate (RR), error rate (ER), principle component analysis (PCA), support vector machine (SVM), radial basis function (RBF), learning vector quantization (LVQ), K-means, C-means
Cite this Article Prince Verma, Jagriti, Manpreet Kaur. Unsupervised Learning Techniques in Neural Network for Face Recognition. Journal of Advancements in Robotics. 2020; 7(1): 25–29p.
- There are currently no refbacks.
This site has been shifted to https://stmcomputers.stmjournals.com/