Home >The Catalogue>Datasets> ITI, Wood Anomaly Detection One Class Classification

Wood Anomaly Detection One Class Classification

Creative Commons Attribution 4.0 (CC-BY-4.0)
Agriculture, Fisheries, Forestry and Food, Industry 4.0, Science and Technology
No personal data
* Please note that the classification is taken from the original source
Wood anomaly detection learning exclusively from non-abnormal wooden textures In particular, this dataset addresses the anomaly detection problem by capturing several views from wooden textured objects from the same class. The anomalous regions of these images were manually labeled at pixel level. Furthermore, each image has been labelled by two different teams in order to increase its confidence merging the final labels. The objects contained 4 possible anomalies: crack, stain, porosity, and knot. These four were combined into a single label, namely, anomalous. To summarize, the goal is to develop an algorithm that learns from a "normal" wooden texture what "normal" is and infers if a wooden texture under inspection is anomalous. Therefore, the algorithm takes an image and outputs an error map (the same size as the input image) with an anomaly score for each pixel. The dataset is divided into three partitions: train, validation, and test. Train and validation datasets are exclusively built from "normal" wooden textures and the test dataset includes both "normal" and anomalous wooden textures. The division of the "normal" textures has been divided 60% to train, 20% validation, and 20% to test. All anomalous textures are in the test dataset. The structure of the dataset consists of three main folders: "train", "val" and "test". "train" and "val" directories only contain the images related to each partition as there is no need for label masks. However, the "test" directory contains two folders: "images" and "masks". The "images" directory contains the test images and "masks" contains the masks of only the anomalous images. Should an image name from the "images" directory not be in "masks", it implies that the image isn't anomalous. Moreover, the "masks" directory contains two subdirectories: "masksAND" and "masksXOR". These directories divide the regions of the images that were labeled unanimously by the two teams (masksAND) and the regions that were labeled by only one team (masksXOR). This division arises on the grounds of a more rightful evaluation of the algorithms. We cannot impose an algorithm to detect areas that not even humans can agree upon. Although, if the algorithm detects as anomalous any pixel within this region, we cannot penalize the score. Hence, this region should be omitted from the evaluation metrics. For this reason, we propose to ignore masksXOR regions and only masksAND labels should be mandatory, as anomalous pixels, in the evaluation metrics. Acknowledgments Images were acquired using a ZG3D device Please use the following reference when citing: Perez-Cortes, J. C., Perez, A. J., Saez-Barona, S., Guardiola, J. L., & Salvador, I. (2018). A System for In-Line 3D Inspection without Hidden Surfaces. Sensors, 18(9), 2993.
Disclaimer: This data is provided by a third party. The DIH identifying this data has no responsibility for its content. Please check the provided link to the data for license terms and potential usage restrictions. In case personal data is included in the dataset, the third party who provides the dataset is the data controller of such personal data. Please note that if you use the datasets for your own purposes, you become an independent data controller and are solely responsible for your compliance with relevant data protection laws relating to the processing and security of personal data, with particular reference, but not limited to, the provisions of the General Data Protection Regulation (GDPR), as applicable to the personal data included in the data.


ITI Data Cycle Hub