为了对复杂自然场景中各类显著目标进行准确的检测, 提出了一种基于图像对比度的检测方法。首先利用全局对比度算子对图像进行检测得到全局对比度显著图, 再利用局部对比度算子进行检测得到局部对比度显著图, 对局部对比度显著图再做边缘处理和形态学膨胀, 然后用全局对比度算子对其紧凑化得到最后的局部对比度显著图。融合全局和局部对比度显著图并加入一定的先验知识得到最后的显著目标图。实验表明该方法性能超过了现有大多数显著目标检测方法。

In order to detect all kinds of salient object in natural scene, we present a method which combined image global contrast and local contrast information. Firstly, use global and local contrast detector to get the global and local contrast saliency map. Then, make border cut and morphological dilation on local contrast saliency map. Finally, combine global and local contrast saliency map and make center bias to get final saliency map. We provide quantitative evaluation which shows the proposed method outperforms many other state-of-art methods.