基于显著性检测的花卉图像分割
首发时间:2014-09-18
摘要:针对花卉图像复杂的背景问题,本文提出基于显著性检测的花卉图像前景分割方法。该方法通过为花卉图像的显著性区域训练前景背景分类器,自适应设定初始前景背景的信息分布,并结合GrabCut算法实现将花卉的主体部分从背景中分离开。相对于经典的花卉图像分割方法。本文提出的方法,不需要对每一类花进行单独的训练,是一种自适应的花卉图像分割方法。
For information in English, please click here
Saliency Detection based Flower Image Foreground Segmentation
Abstract:In terms of the complicated background of flower images, we proposed a sailency detection based flower image forground segmenttation method. To be specific, we train a foreground and background classifier for flower saliency region, set initial foreground and background segmentation threshold adaptively, and then segment the main part of a flower in the image from the background based on the GrabCut method. Different from the classical flower classification method, this method is an adaptive flower classification method and don`t need a separate training for each kind of flower.
Keywords: Flower Image Segmentation Saliency Detection Fine-grained Image
基金:
论文图表:
引用
No.4609414981334141****
同行评议
共计0人参与
勘误表
基于显著性检测的花卉图像分割
评论
全部评论0/1000