“…The central objective is to recover the true colors of the objects observed as if the light source is a neutral illumination. This task in modern cameras is known as the computational color constancy and several unsupervised [2], [3], [4], [5], [6], [7], [8] and supervised approaches [9], [10], [11], [12], [13], [14], [15], [16] have been proposed to solve it. Achieving an invariant representation of the objects regardless of the illuminant is critical for many other vision tasks such as classification [17], [18] and scene understanding [19], [20], [20], [21].…”