基于自适应梯度域融合的图像无缝镶嵌方法  

Seamless image mosaic method based on adaptive gradient domain fusion

作　　者：孙洁[1] 李良福[1] 肖樟树[1] 

机构地区：[1]陕西师范大学计算机科学学院,西安710119

出　　处：《计算机应用研究》2015年第9期2835-2838,2848,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61201434);中央高校基本科研业务专项资金资助项目(GK201503068)

摘　　要：图像融合是获取高质量镶嵌图像的关键步骤,针对空域和频域的融合方法在实现图像合成时易产生拼接缝隙和模糊问题,提出了一种梯度域下的图像无缝镶嵌方法。该方法对融合区域关键要素的选取作了改进,并加入自适应的混合梯度引导插值,利用带有Dirichlet边界条件的Poisson方程求解待融合区域的像素值。同时,结合全局亮度调整算法消除曝光差异。此外,在图像配准阶段,提出自适应阈值的Harris角点算法解决阈值的不通用性问题。实验结果表明,该方法有较强的适应性,能够有效降低曝光差异的影响,消除拼接缝隙,在保持清晰度的同时,提高了镶嵌图像的质量,达到了无缝镶嵌的效果。Image fusion is a crucial step to achieve high quality mosaic image. In view of the questions of producing seam-line and blurring for fusion algorithms based on spatial and frequency domain, this paper presented a seamless mosaic method based on gradi- ent domain. It improved the key elements in fusion region and added adaptive mixing gradients to guide interpolation. Then it solved pixel values in fusion region by using Poisson equation with Dirichlet boundary conditions. Meanwhile, it used global brightness ad- justment algorithm to wipe off exposure difference and achieve a smooth transition. In addition, for image registration, it proposed Harris comer algorithm with adaptive threshold to solve a problem that threshold was not universal. Experimental results show that this method has strong adaptability, can effectively reduce the influence of exposure difference, eliminate the seam-line. While keeping the definition, it improves the quality of mosaic images and achieves the effect of seamless mosaic.

关 键 词：图像镶嵌 自适应 梯度域 混合梯度 泊松融合 亮度调整 曝光差异 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]