EFFECTIVE TECHNIQUE FOR FACE RECOGNITION SYSTEM IN ATTENDANCE APPLICATIONS
Keywords:Gabor Wavelets, LBP, LMG, Linear Discriminant Analysis (LDA), Euclidean Distance.
One of the most common attendance systems is the manual attendance i.e., staff marking the attendance in attendance sheet and it will consume more time. To overcome this automatic face recognition system is used in attendance applications. Face recognition is a personal identification system that uses personal characteristics of a person to identify the person's identity. Here, proposes a novel facial feature extraction method named Gabor ordinal measures. It incorporates the dissimilarity of Gabor features and the hardiness of ordinal measures as a promising solution to jointly handle the variations in face images. Two representative methods- Gabor wavelets and Local Binary Patterns (LBP). Gabor wavelets are wavelets which minimizes the product of its standard deviations in the time and frequency domain. Local Matching Gabor method (LMG) was developed to encode the Gabor magnitude features. Gabor features are extracted from magnitude, phase, real, and imaginary components of Gabor images. They are jointly encoded as visual primitives in local images. LDA is a dimensionality reduction method commonly used for classification problems. It projects the features in higher dimension space into a lower dimension space. Finally, Euclidean Distance is used for face recognition.