IEEE Trans Image Process. 2017 Apr;26(4):1626-1636. doi: 10.1109/TIP.2017.2655438. Epub 2017 Jan 18.
We present texture operators encoding class-specific local organizations of image directions (LOIDs) in a rotation-invariant fashion. The LOIDs are key for visual understanding, and are at the origin of the success of the popular approaches, such as local binary patterns (LBPs) and the scale-invariant feature transform (SIFT). Whereas, LBPs and SIFT yield hand-crafted image representations, we propose to learn data-specific representations of the LOIDs in a rotation-invariant fashion. The image operators are based on steerable circular harmonic wavelets (CHWs), offering a rich and yet compact initial representation for characterizing natural textures. The joint location and orientation required to encode the LOIDs is preserved by using moving frames (MFs) texture representations built from locally-steered image gradients that are invariant to rigid motions. In a second step, we use support vector machines to learn a multi-class shaping matrix for the initial CHW representation, yielding data-driven MFs called steerable wavelet machines (SWMs). The SWM forward function is composed of linear operations (i.e., convolution and weighted combinations) interleaved with non-linear steermax operations. We experimentally demonstrate the effectiveness of the proposed operators for classifying natural textures. Our scheme outperforms recent approaches on several test suites of the Outex and the CUReT databases.
我们提出了一种纹理算子，以旋转不变的方式对图像方向的特定类别局部组织（LOID）进行编码。LOID 是视觉理解的关键，也是流行方法（如局部二值模式（LBP）和尺度不变特征变换（SIFT））成功的原因。虽然 LBP 和 SIFT 产生了手工制作的图像表示，但我们建议以旋转不变的方式学习 LOID 的特定于数据的表示。图像算子基于可旋转的圆谐小波（CHW），为自然纹理的特征提供了丰富而紧凑的初始表示。通过使用从局部引导图像梯度构建的移动帧（MF）纹理表示来保留所需的 LOID 的位置和方向，这些表示对刚体运动具有不变性。在第二步中，我们使用支持向量机学习初始 CHW 表示的多类整形矩阵，从而产生称为可旋转小波机（SWM）的数据驱动 MF。SWM 前向函数由线性操作（即卷积和加权组合）与非线性 steermax 操作交织而成。我们通过实验证明了所提出的算子在分类自然纹理方面的有效性。我们的方案在 Outex 和 CUReT 数据库的多个测试套件上优于最新的方法。
