快速在线主动学习的图像自动分割算法

Image Automatic Segmentation Based on Fast Online Active Learning

提出经前馈神经网络快速在线学习、构建像素分类模型进行图像分割的算法.首先利用谱残差法计算像素显著度,通过对少数高显著度点的分布进行多尺度分析,获得符合人眼视觉特性的显著图和注视区域.然后从注视区域和非注视区域随机抽样构成由正负样本像素组成的训练集,在线训练一个两分类的随机权前馈神经网络模型.最后使用该模型分类全图像素,实现图像分割.实验表明,文中算法在谱残差法基础上提升对图像中显著目标的分割性能,分割结果与人类视觉感知匹配度较好.

An algorithm for image segmentation is proposed by building a pixels classification model. The model is trained online fast with a feed-forward neural network. Firstly, saliency map is computed by spectral residual （ SR） approach. Then, multi-scale analysis is conducted via dispersion of minority high saliency points, and saliency map and gaze areas highly matching with human visual system are obtained. Next, positive and negative samples are selected randomly from saliency and non-saliency regions to compose the training set. A two-class random weighted feed-forward neural network model is trained. Finally, whole image pixels are classified by this model, and image segmentation is realized. Experiments show that the proposed algorithm enhances the segmentation performance for salient object grounded on the spectral residual based method, and the segmentation results are close to human visual perception.