中文说明: 可靠的视觉显著性估计允许图像无适当处理先验知识的他们的内容,,因此仍然是重要的一步,在很多计算机 vi中港合资的任务包括图像分割、 目标识别、 和自适应压缩。我们提出了一种区域对比基于的显著性提取算法,其中同时l评估全球对比差异和空间相干性。所提出的算法很简单, 高效、 和收益率 全分辨率显著性映射。我们的算法一直高于现有的显著性检测方法,收益率较高的精度和更好的召回率,当使用其中一个最大可公开获得的数据集评估。 我们还演示如何
English Description:
Reliable estimation of visual saliency allows appropriate processing of images without prior knowledge of their contents, and thus remains an important step in many computer vision tasks including image segmentation, object recognition, and adaptive compression. We propose a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence. The proposed algorithm is simple, efficient, and yields Click the file on the left to start the preview,please !The preview only provides 20% of the code snippets, the complete code needs to be downloaded Loading Report