CoMMonS: Challenging Microscopic Material Surface Dataset

As one of the research directions at OLIVES Lab @ Georgia Tech, we focus on recognizing textures and materials in real-world images, which plays an important role in object recognition and scene understanding. Aiming at describing objects or scenes with more detailed information, we explore how to computationally characterize apparent or latent properties (e.g. surface smoothness) of materials, i.e., computational material characterization, which moves a step further beyond material recognition. For this purpose, we introduce a large, publicly available dataset named challenging microscopic material surface dataset (CoMMonS). We utilize a powerful microscope to capture high-resolution images with fine details of fabric surfaces. The CoMMonS dataset consists of 6,912 images covering 24 fabric samples in a controlled environment under varying imaging conditions such as lighting, zoom levels, geometric variations, and touching directions. This dataset can be used to assess the performance of existing deep learning-based algorithms and to develop our own method for material characterization in terms of fabric properties such as fiber length, surface smoothness, and toweling effect. Please refer to our GitHub page for code, papers, and more information.

作为佐治亚理工学院OLIVES实验室的研究方向之一，我们专注于识别现实世界图像中的纹理和材料，这在物体识别和场景理解中扮演着至关重要的角色。为了更详细地描述物体或场景，我们探讨如何计算性地表征材料的显性或潜在属性（例如表面光滑度），即计算材料表征，这相较于材料识别更进一步。为此，我们引入了一个大型、公开可用的数据集，命名为挑战性微观材料表面数据集（CoMMonS）。我们利用高精度的显微镜捕捉织物表面的精细细节图像。CoMMonS数据集包含6,912张图像，涵盖了24种织物样本，在受控环境中，通过不同的成像条件（如光照、放大倍数、几何变化和触摸方向）进行采集。此数据集可用于评估现有基于深度学习的算法的性能，并开发我们自己的用于材料表征的方法，具体涉及织物属性，如纤维长度、表面光滑度和吸水性。请参阅我们的GitHub页面以获取代码、论文和更多信息。