Multi Distance Face Recognition of Eye Localization with Modified Gaussian Derivative Filter

Face recognition at a distance (FRAD) is one of the most difficult types of face recognition applications, particularly at a distance. Due to the poor resolution of facial image, it is difficult to identify faces from a distance. Recently, while recording individuals, the camera view is broad and just a small portion of a person's face is visible in the image. To ensure that the facial image has a low resolution, which deteriorates both face detection and identification engines, the facial image is constantly at low resolution. As an immediate solution, employing a high-definition camera is considered as a simple and practical approach to improve the reliability of algorithm and perform well on low-resolution facial images. While facial detection will be somewhat decreased, a picture with higher quality will result in a slower face detection rate. The proposed work aims to recognize faces with good accuracy even at a distance. The eye localization works for the face and eye location in the face of a human being with varied sizes at multiple distances. This process is used to detect the face quickly with a comparatively high accuracy. The Gaussian derivative filter is used to reduce the feature size in the storage element, which improves the speed of the recognition ratio. Besides, the proposed work includes benchmark datasets to evaluate the recognition process. As a result, the proposed system has achieved a 93.24% average accuracy of face recognition.

Eye Localization Using Convolutional Neural Networks and Image Gradients

Eye detection is a preprocessing step in many methods using facial images. Some algorithms to detect eyes are based on the characteristics of the gradient flow in the iris-sclera boundary. These algorithms are usually applied to the whole face and a posterior heuristic is used to remove false positives. In this paper, we reverse that approach by using a Convolutional Neural Network (CNN) to solve a regression problem and give a coarse estimate of the eye regions, and only then do we apply the gradient-based algorithms. The CNN was combined with two gradient-based algorithms and the results were evaluated regarding their accuracy and processing time, showing the applicability of both methods for eye localization.