OCT image data of cotton, polyester and wool based fabrics to train and test deep learning algorithms for automated material classification

The data consists of raw OCT images, all in portable network graphics format in 3 zip files. Each folder contains OCT scans taken from random places over one of the fabrics only. Therefore folders Wool1, Wool2 and Wool3 each consist of OCT scans of three separate fabrics that consisted of purely wool fibers. Similarly folders Cotton1, Cotton2 and Cotton3 consist of OCT scans of three separate fabrics that consisted of purely cotton fibers. Again folders Polyester1, Polyester2 and Polyester3 consist of OCT scans of three separate fabrics that consisted of purely polyester. 2-D mode of the ThorImage OCT software was switched on to take OCT- B images of the fabrics with the Thorlabs CAL110C1 device with a 2mm fixed scan length. Every single OCT scan is a separate image, with the time and date of the scan stamped in the corresponding portable network graphics file. The file in Folder Cotton1 with name OCTImage 045631_07172020.png therefore corresponds to an OCT scan of a cotton fabric taken at 04:56:31 on July 17, 2020.

本数据集包含原始光学相干断层扫描（Optical Coherence Tomography，OCT）图像，所有图像均以可移植网络图形（Portable Network Graphics，PNG）格式存储，打包于3个压缩文件中。每个文件夹仅包含针对单一织物随机区域采集的OCT扫描图像。因此，Wool1、Wool2与Wool3三个文件夹分别包含3种纯羊毛纤维织物的OCT扫描图像；类似地，Cotton1、Cotton2与Cotton3三个文件夹分别包含3种纯棉纤维织物的OCT扫描图像；Polyester1、Polyester2与Polyester3三个文件夹则分别包含3种纯聚酯纤维织物的OCT扫描图像。实验采用Thorlabs CAL110C1设备，开启ThorImage OCT软件的二维模式采集织物的OCT B扫描图像，扫描长度固定为2mm。每一次OCT扫描均对应一张独立的PNG图像，扫描的时间与日期均标注于对应图像的文件名中。例如，Cotton1文件夹中名为OCTImage 045631_07172020.png的文件，对应2020年7月17日04时56分31秒采集的纯棉织物OCT扫描图像。