We propose a novel approach to generate a binary descriptor optimized for each image patch independently. The approach is inspired by the linear discriminant embedding that simultaneously increases inter and decreases intra class distances. A set of discriminative and uncorrelated binary tests is established from all possible tests in an offline training process. The patch adapted descriptors are then efficiently built online from a subset of features which lead to lower intra-class distances and thus, to a more robust descriptor. We perform experiments on three widely used benchmarks and demonstrate improvements in matching performance, and illustrate that per-patch optimization outperforms global optimization.

中文翻译：

---

二进制在线学习描述符


我们提出了一种新颖的方法来独立生成针对每个图像块优化的二进制描述符。该方法受到线性判别嵌入的启发，线性判别嵌入同时增加类间距离并减少类内距离。根据离线训练过程中所有可能的测试建立一组有区别且不相关的二元测试。然后，根据特征子集在线有效地构建适应补丁的描述符，这会导致较低的类内距离，从而形成更鲁棒的描述符。我们对三个广泛使用的基准进行实验，展示匹配性能的改进，并说明每个补丁优化优于全局优化。