Applying Deep Learning Techniques to Cultural Heritage Images Within the INCEPTION Project

详细信息    查看全文

• 关键词：Deep learning ; CNN ; Semantic information ; Cultural heritage
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：10059
• 期：1
• 页码：25-32
• 全文大小：3,370 KB
• 参考文献：1.Sebastian, R., Bonsma, P., Bonsma, I., Ziri, A.E., Parenti, S., Lerones, P.M., Llamas, J., Maietti, F., Turillazzi, B., Iadanz, E.: Roadmap for IT research on a heritage-BIM interoperable platform within INCEPTION. In: SBE 16 MALTA, Europe and the Mediterranean Towards a Sustainable Built Environment (2016)
  2.Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., Rabinovich, A.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
  3.Shankar, S., Robertson, D., Ioannou, Y., Criminisi, A., Cipolla, R.: Refining architectures of deep convolutional neural networks. In: Conference on Computer Vision and Pattern Recognition (2016)
  4.Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision (2015). arXiv preprint arXiv:​1512.​00567
  5.Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jozefowicz, R., Jia, Y., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Schuster, M., Monga, R., Moore, S., Murray, D., Olah, C., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Viégas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: large-scale machine learning on heterogeneous systems (2015). Software tensorflow.​org
  6.Sharma, P., Schoemaker, M., Pan, D.: Automated Image Timestamp Inference Using Convolutional Neural Networks. Stanford University Report (2016)
  7.Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv technical report (2014)
  8.Makantasis, K., Doulamis, A.D., Doulamis, N.D., Ioannides, M.: In the wild image retrieval and clustering for 3D cultural heritage landmarks reconstruction. Multimed. Tools Appl. 75(7), 3593–3629 (2016)CrossRef
  
• 作者单位：Jose Llamas (21)
  Pedro M. Lerones (21)
  Eduardo Zalama (22)
  Jaime Gómez-García-Bermejo (22)
  
  21. CARTIF Foundation, Parque Tecnológico de Boecillo, Valladolid, Spain
  22. ITAP-DISA, University of Valladolid, Valladolid, Spain
  
• 丛书名：Digital Heritage. Progress in Cultural Heritage: Documentation, Preservation, and Protection
• ISBN：978-3-319-48974-2
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：10059

文摘

The digital documentation of cultural heritage (CH) often requires interpretation and classification of a huge amount of images. The INCEPTION European project focuses on the development of tools and methodologies for obtaining 3D models of cultural heritage assets, enriched by semantic information and integration of both parts on a new H-BIM (Heritage - Building Information Modeling) platform. In this sense, the availability of automated techniques that allow the interpretation of photos and the search using semantic terms would greatly facilitate the work to develop the project. In this article the use of deep learning techniques, specifically the convolutional neural networks (CNNs) for analyzing images of cultural heritage is assessed. It is considered that the application of these techniques can make a significant contribution to the objectives sought in the INCEPTION project and, more generally, the digital documentation of cultural heritage.