用于图像分类在线字典学习算法

摘要

稀疏编码在人脸识别上的成功促使这项技术应用在更广泛的计算机视觉中。图像分类是图像检索的基础，而图像的识别是比人脸识别更复杂，因为首先图像数据量更大，其次图像中要检索的目标数据不易得到。为解决这两个问题，提出了一种新的在线字典学习的算法。实验结果表明本方法在图像分类上比最近提出的其他字典学习的方法效果更好。%The success application of sparse coding in face recognition makes this technology used to a variety of problems in computer vision .Image classification is the basis of image re-trieval, but image recognition is more complex than face images .In order to solve these two problems , this paper proposed a new online dictionary learning algorithm .The experimental results showed that the method was better than other dictionary learning method in image classification .