Gabor filter based optical image recognition using Fractional Power Polynomial model based common discriminant locality preserving projection with kernels

This paper presents Gabor filter based optical image recognition using Fractional Power Polynomial model based Common Kernel Discriminant Locality Preserving Projection. This method tends to solve the nonlinear classification problem endured by optical image recognition owing to the complex illumination condition in practical applications, such as face recognition. The first step is to apply Gabor filter to extract desirable textural features characterized by spatial frequency, spatial locality and orientation selectivity to cope with the variations in illumination. In the second step we propose Class-wise Locality Preserving Projection through creating the nearest neighbor graph guided by the class labels for the textural features reduction. Finally we present Common Kernel Discriminant Vector with Fractional Power Polynomial model to reduce the dimensions of the textural features for recognition. For the performance evaluation on optical image recognition, we test the proposed method on a challenging optical image recognition problem, face recognition.

► This method tends to solve the nonlinear classification of variable illumination-based optical image. ► This method proposes Gabor filter based Fractional Power Polynomial model to extract complex features for classification. ► This method performs well on the challenging optical image recognition.