中文摘要：

依据显著目标是显眼、紧凑和完整的思路,提出基于过渡滑动窗特征分布贝叶斯分析的显著目标检测模型。首先根据局部区域与其多个尺度邻域的对比得到亮度显著映射图;然后利用颜色信息的空间紧凑性、同质性和孤立性得到颜色显著映射图;同时通过多尺度多方向的Gabor滤波器组模拟人类视觉系统提取图像块的方向显著映射图。最后将这些显著特征一起输入单尺度的贝叶斯结构模型,通过对比贝叶斯结构模型中窗内和过渡窗外的特征值计算出该像素是显著像素的概率值,最后通过取最大化映射规则计算出输入图像的显著图,从而得到显著目标。将此算法应用于不同图像进行仿真实验,得到较好的显著性检测结果,表明该方法是切实可行的。

英文摘要：

According to the thought that the salient object in an image is often conspicuous,compact and complete,a Bayesian salient object extraction model based on space distribution and local complexity of the transition window is proposed.First of all,the bright saliency value map is obtained by computing the contrast of local area and its multiple scales neighborhood,and then the color saliency value map is computed by using conspicuous,space distribution and locally uniform of color information.Meanwhile,the orientation saliency value map is obtained by multi-scale analysis responses of Gabor filters.The above saliency values are inputted into the single-scale Bayesian framework model based on transition-sliding window.Then the probability of that a pixel＇s salient is computed by comparing the saliency values inside the window and outside the transition window.Finally,the saliency map of the input image is obtained by taking the maximum value,so the salient object is located and extracted according to the saliency map.The proposed method is applied to all kinds of images,and the better test results show that the algorithm is feasible and valuable.