CAJ | 학술논문

针对目前主流去除雾霾算法采用亮度和色度分量分而治之的机制，割裂了二者固有的相关性，致使增强后图像质量不能两者兼顾的问题，本文以人眼视觉特性为依据，提出了一种亮度反馈的增强方法。该方法首先对亮度信息进行区域适应性调整，并对其细节和边缘进行提升，然后将该结果纳入色度信息处理的约束条件，较好的保持了两者间的相关性。实验表明本文算法在去除雾霾后视觉效果优异，具有较好的实用性和较少的计算资源消耗。
침대목전주류거제무매산법채용량도화색도분량분이치지적궤제，할렬료이자고유적상관성，치사증강후도상질량불능량자겸고적문제，본문이인안시각특성위의거，제출료일충량도반궤적증강방법。해방법수선대량도신식진행구역괄응성조정，병대기세절화변연진행제승，연후장해결과납입색도신식처리적약속조건，교호적보지료량자간적상관성。실험표명본문산법재거제무매후시각효과우이，구유교호적실용성화교소적계산자원소모。
Through the analysis of the current main of dehazing algorithms,we found that they adapted the divide and con-quer strategy to process the luminance and chrominance components,therefore they separated their correlation.To resolve the prob-lem,we performed a sort of method for enhancing and combining the image based on luminance feedback through the human visual characteristics.First,it adjusted the brightness information and lifted the edges and details of original image.Moreover,it regarded the results as constraint conditions which would be used in processing chromatic component for maintain their relevance.Experi-ments have demonstrated that the proposed method could obtain an excellent result and provide a good practicability and take less time.