The rotation, scale and translation invariance of extracted features have a high significance in image recognition. Local binary pattern (LBP) and LBP-based descriptors have been widely used in image recognition due to feature discrimination and computational efficiency. However, most of the existing LBP-based descriptors have been designed to achieve rotation invariance while fail to achieve scale invariance. Moreover, it is usually difficult to achieve a good trade-off between the feature discrimination and the feature dimension. In this work, a learning 2D co-occurrence LBP termed 2D-LCoLBP is proposed to address these issues. Firstly, a weighted joint histogram is constructed in different neighborhoods and scales of an image to represent the multi-neighborhood and multi-scale LBP (2D-MLBP) and achieve the rotation invariance. A feature learning strategy is then designed to learn the compact and robust descriptor (2D-LCoLBP) from LBP pattern pairs across different scales in the extracted 2D-MLBP to characterize the most stable local structures and achieve the scale invariance, as well as decrease the feature dimension and improve the noise robustness. Finally, a linear SVM classifier is employed for recognition. We applied the proposed 2D-LCoLBP on four image recognition tasks—texture, object, face and food recognition with ten image databases. Experimental results show that 2D-LCoLBP has obviously low feature dimension but outperforms the state-of-the-art LBP-based descriptors in terms of recognition accuracy under noise-free, Gaussian noise and JPEG compression conditions.

中文翻译：

---

2D-LCoLBP：一种用于图像识别的学习二维共现局部二进制模式

提取特征的旋转、尺度和平移不变性在图像识别中具有重要意义。由于特征区分和计算效率，局部二进制模式（LBP）和基于 LBP 的描述符已广泛用于图像识别。然而，大多数现有的基于 LBP 的描述符都被设计为实现旋转不变性，而未能实现尺度不变性。而且，通常很难在特征区分度和特征维度之间实现良好的权衡。在这项工作中，提出了一种称为 2D-LCoLBP 的学习 2D 共现 LBP 来解决这些问题。首先，在图像的不同邻域和尺度上构建加权联合直方图来表示多邻域和多尺度LBP（2D-MLBP）并实现旋转不变性。然后设计特征学习策略以从提取的 2D-MLBP 中不同尺度的 LBP 模式对中学习紧凑而稳健的描述符（2D-LCoLBP），以表征最稳定的局部结构并实现尺度不变性，并减少特征维度并提高噪声鲁棒性。最后，采用线性 SVM 分类器进行识别。我们将提出的 2D-LCoLBP 应用于四个图像识别任务——纹理、物体、面部和食物识别，具有十个图像数据库。实验结果表明，2D-LCoLBP 具有明显的低特征维数，但在无噪声、高斯噪声和 JPEG 压缩条件下的识别精度方面优于最先进的基于 LBP 的描述符。