Computational complexity of image processing algorithms for an intelligent mobile enabled tongue diagnosis scheme

Tongue diagnosis is an auxiliary, effective and non-invasive technique to evaluate the condition of a patient's internal organ in traditional East Asian medicine. The diagnosis process relies on expert's opinion based on visual inspection of colour, substance, coating, form and motion of the tongue. This work explores the computational complexity of image processing techniques to analyse chromatic properties and textural features for tongue image segmentation. The dynamic and novel approach of this work involves consideration of skin colour covering various range of contrast diversity while image segmentation, making it distinct from existing works. The aim of this research is to seek for an algorithm with reduced computational complexity suitable to be implemented in an enhanced mobile enable solution. The algorithm for tongue image processing needs to be fast and less complex making the system apt for mobile devices executing automatic tongue diagnosis entailing clinical decision support system. Analysing the performance of different colour models, RGB was unveiled to have a better enactment than others. The performance of edge detection techniques were evaluated on images with close contrast difference based on segmentation result and processing time. The morphological processing showed better result to separate the tongue from its background which can be further employed for geometric shape based disease diagnosis.