Individual Eye Gaze Prediction with the Effect of Image Enhancement Using Deep Neural Networks

The prediction of individual eye gaze is a research topic that has gained the interest of researchers with its wide range of applications because neural networks majorly increase the rate of accuracy of individual gaze. In this research work, MPIIGaze dataset has been employed for the prediction of individual gaze and the direction of individual gaze was grouped into down view, left view, right view and lastly centre view. A CNN model was used to train and validate a random selection of images. Firstly, the ordinary images were trained and validated, after which image enhancement processing technique was applied. With the image brightness enhancement technique, a higher rate of gaze prediction accuracy was achieved. Hence, it can be deduced that image enhancement has proved its purpose by providing image interpretation with better quality.