In　Traditional　Chinese　Medicine　(TCM),　tongue　inspection　is　one　of　the　most　important　diagnostic　means.　Due　to　the　limitations　of　capturing　devices　and　variations　in　lighting　conditions,　there　are　color　distortions　between　the　captured　tongue　images　and　the　actual　human　visual　perceived.　In　this　paper,　we　proposed　a　Deep　Color　Correction　Network　(DCCN)　to　learn　the　mapping　model　between　the　captured　distorted　color　images　and　the　target　visually　perceived　color　appearance　under　different　lighting　conditions　and　provides　the　color　consistency　across　different　cameras　or　capture　deceives.　Experimental　results　show　that　the　DCCN　model　can　achieve　high　accuracy　and　robustness　in　both　of　the　objective　and　subjective　tongue　image　color　correction　metrics.　©　2018　IEEE.