-
公开(公告)号:US20080131026A1
公开(公告)日:2008-06-05
申请号:US12028934
申请日:2008-02-11
申请人: Joel M. RECHT
发明人: Joel M. RECHT
IPC分类号: G06K9/00
CPC分类号: H04N21/4302 , G06K9/00127 , G06K9/0014 , G06K9/4633 , G06K9/52 , G06T7/11 , G06T7/12 , G06T7/155 , G06T7/194 , G06T7/48 , G06T2207/10056 , G06T2207/20036 , G06T2207/30024 , H04N21/242
摘要: A method for recognizing an object in an image is disclosed wherein a fractal map of the image is generated by estimating the fractal dimension of each pixel in the image. The fractal map may be segmented by thresholding and locations of candidate objects are determined. The pixel value of the image pixel corresponding to the same location where the candidate object is found in the fractal map may be compared to a threshold value. If the pixel value is greater than the threshold value, the candidate object is recognized as a valid object.
摘要翻译: 公开了一种用于识别图像中的对象的方法,其中通过估计图像中每个像素的分形维数来生成图像的分形图。 可以通过阈值分割分形图并确定候选对象的位置。 可以将对应于在分形图中找到候选对象的相同位置的图像像素的像素值与阈值进行比较。 如果像素值大于阈值,则候选对象被识别为有效对象。