International Conference on Quality Control by Artificial Vision最新文献_第4页

Unveiling the secrets of paintings: deep neural networks trained on high-resolution multispectral images for accurate attribution and authentication 揭开画作的秘密:在高分辨率多光谱图像上训练深度神经网络，以获得准确的归属和认证

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.3000286

Michael E. Sander, Tom Sander, Maxime Sylvestre

{"title":"Unveiling the secrets of paintings: deep neural networks trained on high-resolution multispectral images for accurate attribution and authentication","authors":"Michael E. Sander, Tom Sander, Maxime Sylvestre","doi":"10.1117/12.3000286","DOIUrl":"https://doi.org/10.1117/12.3000286","url":null,"abstract":"Attribution and authentication of paintings are difficult tasks, often based on human expertise. In this work, we present SpectrumArt: a new dataset of multispectral (13 channels) image patches of paintings acquired at very high resolution (800 pixels per mm2 ). We train deep neural networks on SpectrumArt for attribution (i.e., authorship classification) and authentication (i.e., whether of undisputed origin). For attribution, we obtain an accuracy of 92% on a test set of patches coming from unseen paintings. We also propose two classification metrics for attribution of full paintings based on the prediction for the patches: majority vote and entropy weighted vote. Both metrics lead to an attribution score of 100% on unseen paintings. For authenticity testing, our model agrees with the experts’ conclusions on genuine and fake paintings, and provides new insights into the authenticity of paintings where the expert community is divided by proposing a spectral matching score between the painting and an artist. To validate the important advantage of our data collection method, we show that the use of 13 channels instead of 3 and the high resolution of the data significantly improve the accuracy of our models.","PeriodicalId":295011,"journal":{"name":"International Conference on Quality Control by Artificial Vision","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124835614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Visual impression estimation system considering attribute information 考虑属性信息的视觉印象估计系统

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2691716

Yukiya Taki, K. Kato, Kazunori Terada, Kensuke Tobitani

引用次数: 0

Handling noisy annotations in deep supervised learning 在深度监督学习中处理噪声注释

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2692547

Ichraq Lemghari, Sylvie Le-Hégarat, Emanuel Aldea, Jennifer Vandoni

引用次数: 0

Enhanced key-point detection for plenoptic imaging 增强的全光成像关键点检测

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2692367

M. Al Assaad, S. Bazeille, Thomas Josso-Laurain, A. Dieterlen, C. Cudel

引用次数: 0

Combining unsupervised and supervised deep learning approaches for surface anomaly detection 结合无监督和监督深度学习方法的地表异常检测

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2688559

Domen Rački, Dejan Tomazevic, D. Skočaj

{"title":"Combining unsupervised and supervised deep learning approaches for surface anomaly detection","authors":"Domen Rački, Dejan Tomazevic, D. Skočaj","doi":"10.1117/12.2688559","DOIUrl":"https://doi.org/10.1117/12.2688559","url":null,"abstract":"Anomaly detection in an unsupervised manner has become the go-to approach in applications where data labeling proves problematic. However, these approaches aren’t completely unsupervised, since they rely on the weak knowledge of the dataset distribution into anomalous and anomaly-free subsets and typically require post-training threshold calibration in order to perform anomaly detection. Yet, they do not take advantage of available positive samples during training. In contrast, fully supervised approaches have proven to be more accurate and more efficient, however, they require a sufficient number of anomalous images to be labeled on a per-pixel level, which represents a labour-intensive task. In this paper, we propose a new hybrid approach that utilizes the best of both worlds. We use an unsupervised approach to build a model for generating pseudo labels, followed by a supervised approach in order to robustify anomaly detection. Moreover, we extend this approach with an active learning schema, that results in learning with mixed supervision. We achieve several improvements, i.e., the utilization of available positive image samples, improved anomaly detection performance, and the retention of real-time performance. The proposed approach yields results that are comparable to the fully supervised approach, and at the very least, reduces the number of required labeled anomalous samples.","PeriodicalId":295011,"journal":{"name":"International Conference on Quality Control by Artificial Vision","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117052944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

XRANet: an extra-wide, residual and attention-based deep convolutional neural network for semantic segmentation XRANet:一种用于语义分割的超宽、残差和基于注意力的深度卷积神经网络

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2692337

Roger Booto Tokime, M. Akhloufi

引用次数: 0

A shape-from-silhouette method for 3D reconstruction of a convex polyhedron 凸多面体三维重建的轮廓形方法

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.3000368

Baptiste Brument, L. Calvet, Robin Bruneau, J. Mélou, Simone Gasparini, Y. Quéau, F. Lauze, Jean-Denis Durou

引用次数: 0

Neural detection of spheres in images for lighting calibration 用于光照校正的图像中球体的神经检测

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.3000202

Laurent Fainsin, J. Mélou, L. Calvet, A. Carlier, Jean-Denis Durou

引用次数: 0

Gloss assessment with deep photometric stereo: application to human skin 光泽评估与深度光度立体:应用于人体皮肤

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2692082

Clément Joubert, B. Bringier, Julien Garnier, M. Khoudeir, N. Amalric

引用次数: 0

Hierarchical lossless image coding using CNN predictors considering prediction error distribution 考虑预测误差分布的CNN预测器分层无损图像编码

International Conference on Quality Control by Artificial Vision Pub Date : 2023-07-28 DOI: 10.1117/12.2691664

Kazuki Nakashima, Ryo Nakazawa, Hideharu Toda, H. Aomori, T. Otake, I. Matsuda, S. Itoh

引用次数: 0