Face recognition is a fascinating application in the field of image recognition. However face images with glasses create hindrance. Glasses detection plays an important role in face recognition and soft biometrics for person identification. However, automatic glasses detection is still a challenging problem under real application scenarios because of face variations, light conditions, and self-occlusion, have significant influence on its performance.
The goal of this project is to classify images of people into two classes: Glass and No-Glass based upon whether they wear a glass in the image or not. However, there is a variety in the shape, design and appearance of glasses which makes it challenging.