Journal of Advances in Mathematics and Computer Science

Many researches have been going on since last two decades for object recognition, shape matching, and pattern recognition in the field of computer vision. Face recognition is one of the important issues in object recognition and computer vision. Many face image datasets, related competitions, and evaluation programs have encouraged innovation, producing more powerful facial recognition technology with promising results. In recent years, we have witnessed tremendous improvements in face recognition performance from complex deep neural network architectures trained on millions of face images. Face recognition is the most important biometric and stills many challenges such as pose variation, illumination variation, etc. In order to achieve the desired performance when deploying in reality, the methods depend on many factors. One of the main factors is quality of input image. Therefore, facial recognition systems is installed outdoors which are always affected by extreme weather events such as haze, fog. The existence of haze dramatically degrades the visibility of outdoor images captured in inclement weather and affects many high-level computer vision tasks such as detection and recognition system. In this paper, we propose a preprocessing method to remove haze from input images that enhances their quality to improve effectiveness and recognition rate for face identification based on Convolutional Neural Network (CNN) based on the available datasets and our self-built data. To perform the proposed method for outdoor face recognition system, we have improved the system accuracy from 90.53% to 98.14%. The results show that the proposed method improves the quality of the image with other traditional methods.