Describing texture is a very challenging problem for many image-based expert and intelligent systems (e.g. defective product detection, people re-identification, abnormality investigation in medical imaging and remote sensing applications$\dots$) since the process of texture classification relies on the quality of the extracted features. Indeed, detecting and extracting features is a hard and time-consuming task that requires the intervention of an expert, notably when dealing with challenging textures. Thus, machine learning-based descriptors have emerged as another alternative to deal with the difficulty of feature extracting. In this work, we propose a new operator, which we named Local Edge Signature (LES) descriptor, to locally represent texture. The proposed texture descriptor is based on statistical information on edge pixels’ arrangement and orientation in a specific local region, and it is insensitive to rotation and scale changes. A genetic programming-based approach is then fitted to automatically learn a global texture descriptor that we called Genetic Texture Signature (GTS). In fact, a tree representation of individuals is used to generate global texture features by applying elementary operations on LES elements at a set of keypoints, and a fitness function evaluates the descriptors considering intra-class homogeneity and inter-class discrimination properties of their generated features. The obtained results, on six challenging texture datasets (Brodatz, Outex_TC_00000, Outex_TC_00013, KTH-TIPS, KTH-TIPS2b and UIUCTex), show that the proposed classification method, which is fully automated, achieves state-of-the-art performance, especially when the number of available training samples is limited.

对于许多基于图像的专家和智能系统（例如，缺陷产品检测，人员重新识别，医学成像和遥感应用中的异常调查），描述纹理是一个非常具有挑战性的问题$\dots$），因为纹理分类过程取决于提取特征的质量。实际上，检测和提取特征是一项艰巨且耗时的任务，需要专家的干预，尤其是在处理具有挑战性的纹理时。因此，基于机器学习的描述符已经成为解决特征提取困难的另一种选择。在这项工作中，我们提出了一个新的运算符，我们将其命名为Local Edge Signature（LES）描述符，以局部表示纹理。提出的纹理描述符基于关于边缘像素在特定局部区域中的排列和方向的统计信息，并且对旋转和缩放变化不敏感。然后，基于遗传编程的方法将被适配为自动学习全局纹理描述符，我们将其称为遗传纹理签名（GTS）。实际上，个体的树表示用于通过在一组关键点上对LES元素应用基本运算来生成全局纹理特征，而适应度函数会考虑类内同质性和其生成特征的类间区分属性来评估描述符。在六个具有挑战性的纹理数据集（Brodatz，Outex_ TC _ 00000，Outex _ TC _ 00013，KTH-TIPS，KTH-TIPS2b和UIUCTex），表明所提出的分类方法是完全自动化的，可实现最新的性能，尤其是当可用数量较多时训练样本有限。