毕业设计要做图像分割 识别什么的。
看论文看到 superpixels 开始脑补是 像素插值算出来的
后来越看越不想，搜索发现根本是另外一回事
http://blog.sina.com.cn/s/blog_50363a7901011dtd.html
有定义
Many existing algorithms in computer vision use the pixel-grid as the underlying representation. For example, stochastic models of images, such as Markov random fields, are often defined on this regular grid. Or, face detection is typically done by matching stored templates to every fixed-size (say, 50x50) window in the image.
The pixel-grid, however, is not a natural representation of visual scenes. It is rather an "artifact" of a digital imaging process. It would be more natural, and presumably more efficient, to work with perceptually meaningful entities obtained from a low-level grouping process. For example, we can apply the Normalized Cuts algorithm to partition an image into, say, 500 segments (what we call superpixels).
低级特征分组处理的结果 就叫做 superpixels
 Empirical Studies and Applications]" title="超像素：以经验为根据的研究和应用[Superpixel: Empirical Studies and Applications]" action-data="http%3A%2F%2Fttic.uchicago.edu%2F~xren%2Fresearch%2Fsuperpixel%2Fimages%2F100048.jpg" action-type="show-slide" style="margin: 0px; padding: 0px; border-width: 0px; list-style: none;"> |
 Empirical Studies and Applications]" title="超像素：以经验为根据的研究和应用[Superpixel: Empirical Studies and Applications]" action-data="http%3A%2F%2Fttic.uchicago.edu%2F~xren%2Fresearch%2Fsuperpixel%2Fimages%2F100048_seg.jpg" action-type="show-slide" style="margin: 0px; padding: 0px; border-width: 0px; list-style: none;"> |
| (a) | (b) |
 Empirical Studies and Applications]" title="超像素：以经验为根据的研究和应用[Superpixel: Empirical Studies and Applications]" action-data="http%3A%2F%2Fttic.uchicago.edu%2F~xren%2Fresearch%2Fsuperpixel%2Fimages%2F100048_overseg.jpg" action-type="show-slide" style="margin: 0px; padding: 0px; border-width: 0px; list-style: none;"> |
 Empirical Studies and Applications]" title="超像素：以经验为根据的研究和应用[Superpixel: Empirical Studies and Applications]" action-data="http%3A%2F%2Fttic.uchicago.edu%2F~xren%2Fresearch%2Fsuperpixel%2Fimages%2F100048_seg_overseg.jpg" action-type="show-slide" style="margin: 0px; padding: 0px; border-width: 0px; list-style: none;"> |
| (c) | (d) |
a是待处理图片，b是人类的视觉分割，c是superpixel map，d是根据c新做的人类视觉分割
其方法有多种
http://blog.sina.com.cn/s/blog_6f126f5b010134a3.html 方法简介