基于各向异性韦伯二值模式的局部特征提取算法

Local Feature Extraction Algorithm Based on Anisotropic Weber Local Binary Pattern

复杂光照场景下图像局部特征提取一直是图像处理的研究热点,针对韦伯局部描述符(WLD)简单的量化方法以及方向特征提取不足,提出了一种新的图像局部特征描述符,称为各向异性韦伯二值模式(AWLBP)。该算法中WLD算子中的差分激励分量由引入尺度参量和角度参量后改进的各向异性LOG算子来代替,方向梯度分量由局部二值模式(LBP)来代替,将二者融合生成二维AWLBP直方图,然后转化为一维直方图,最后使用KNN分类器进行分类。算法在CMUPIE人脸数据库和PhoTex纹理图像库的大量的实验中验证了其有效性和准确性。实验结果表明,提出的图像特征提取算法在复杂光照的场景下具有很高的有效性和鲁棒性。

Image local feature extraction in complex illumination scenes has always been a research hotspot in image processing.Aiming the simple quantization method of Weber local descriptor (WLD) operator and the lack of directional feature extraction,a new image local feature descriptor called anisotropy Weber local binary pattern (AWLBP) was proposed.Firstly,the differential excitation component in the WLD operator is replaced by an anisotropic LOG operator that introduces the scale parameter and the angle parameter.Secondly,the gradient directions component is replaced by the (LBP) operator.Third,combine the two to generate a two-dimensional AWLBP histogram,which is then converted into a one-dimensional histogram,and finally classified using the KNN classifier.The algorithm validates its validity and accuracy in a large number of experiments in the CMUPIE face database and the PhoTex texture image library.The experimental results show that the proposed image feature extraction algorithm is highly effective and robust in complex illumination scenarios.