IEEE Trans Biomed Eng. 2018 Oct;65(10):2267-2277. doi: 10.1109/TBME.2018.2791567. Epub 2018 Jan 10.
This paper introduces the "encoded local projections" (ELP) as a new dense-sampling image descriptor for search and classification problems. The gradient changes of multiple projections in local windows of gray-level images are encoded to build a histogram that captures spatial projection patterns. Using projections is a conventional technique in both medical imaging and computer vision. Furthermore, powerful dense-sampling methods, such as local binary patterns and the histogram of oriented gradients, are widely used for image classification and recognition. Inspired by many achievements of such existing descriptors, we explore the design of a new class of histogram-based descriptors with particular applications in medical imaging. We experiment with three public datasets (IRMA, Kimia Path24, and CT Emphysema) to comparatively evaluate the performance of ELP histograms. In light of the tremendous success of deep architectures, we also compare the results with deep features generated by pretrained networks. The results are quite encouraging as the ELP descriptor can surpass both conventional and deep descriptors in performance in several experimental settings.
本文提出了“编码局部投影”（ELP）作为一种新的密集采样图像描述符，用于搜索和分类问题。对灰度图像局部窗口中多个投影的梯度变化进行编码，以构建一个直方图，该直方图捕获空间投影模式。在医学成像和计算机视觉中，投影都是一种传统技术。此外，强大的密集采样方法，如局部二值模式和方向梯度直方图，被广泛用于图像分类和识别。受这些现有描述符的许多成果的启发，我们探索设计一类新的基于直方图的描述符，特别应用于医学成像。我们在三个公共数据集（IRMA、Kimia Path24 和 CT Emphysema）上进行实验，以比较 ELP 直方图的性能。鉴于深度架构的巨大成功，我们还将结果与预训练网络生成的深度特征进行比较。结果令人鼓舞，因为在几个实验设置中，ELP 描述符的性能可以超过传统描述符和深度描述符。
