Continuous-Valued Quaternionic Hopfield Neural Network for Image Retrieval: A Color Space Study

Continuous-valued quaternionic Hopfield neural network (CV-QHNN) generalizes the traditional Hopfield network for the storage and retrieval of vectors whose components are unit quaternions. In this paper, we investigate the performance of the CV-QHNN for the retrieval of color images using three different color spaces: RGB, HSV, and CIE-HCL. We point out that a direct conversion from the RGB to unit quaternions may result distortions in which visually different colors are mapped into close quaternions. Preliminary computational experiments reveal that the CV-QHNN based on the HSV color space can be more effective for the removal of noise from a corrupted color image.