Abstract
In addition to photo data, many digital cameras and smartphones capture Exif metadata which contain information about the camera parameters used when a photo was captured. While most semantic image recognition approaches only use pixel data for classification decisions, this work aims to examine whether Exif data can improve image classification performed by Convolutional Neural Networks (CNNs). We compare the classification performance and training time of fusion models that use both, image data and Exif metadata, for image classification in contrast to models that use only image data. The most promising result was obtained with a fusion model which was able to increase the classification accuracy for the selected target concepts by \(7.5\%\) compared to the baseline, while the average total training time of all fusion models was reduced by \(7.9\%\).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
The dataset containing references to the Flickr images has been published with the DOI “10.48564/unibafd-vmm4f-m4y33”. The source code associated with this publication has also been published with the DOI “10.48564/unibafd-q73v9-wz721”. The corresponding GitHub repository can be accessed through the provided references.
References
Arbinger, C., Bullin, M., Henrich, A.: Exploiting geodata to improve image recognition with deep learning. In: Companion Proceedings of the Web Conference 2022, WWW 2022, pp. 648–655. ACM, New York, NY, USA (2022). https://doi.org/10.1145/3487553.3524645
Boutell, M., Luo, J.: Beyond pixels: exploiting camera metadata for photo classification. Pattern Recogn. 38(6), 935–946 (2005). https://doi.org/10.1016/j.patcog.2004.11.013, https://www.sciencedirect.com/science/article/pii/S0031320304003978
Electronics, J., Information Technology Industries Association, J.: Exchangeable image file format for digital still cameras: Exif version 2.32. Technical report, Camera & Imaging Products Association, May 2019. https://www.cipa.jp/std/documents/download_e.html?DC-008-Translation-2019-E
Emmanuel, T., Maupong, T., Mpoeleng, D., Semong, T., Mphago, B., Tabona, O.: A survey on missing data in machine learning. J. Big Data 8(1), 140 (2021). https://doi.org/10.1186/s40537-021-00516-9
Fisher, A., Rudin, C., Dominici, F.: All models are wrong, but many are useful: learning a variable’s importance by studying an entire class of prediction models simultaneously. J. Mach. Learn. Res. JMLR 20, 177 (2019)
Flickr: The app garden, API Documentation. www.flickr.com/services/api/. Accessed 13 Dec 2022
Ghazali, J., et al.: Image classification using EXIF metadata. Int. J. Eng. Trends Technol. 1, 69–73 (2020). https://doi.org/10.14445/22315381/CATI3P211
Hand, M.: Ubiquitous photography. Polity (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630–645. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_38
Kannojia, S., Jaiswal, G.: Effects of varying resolution on performance of CNN based image classification an experimental study. Int. J. Comput. Sci. Eng. 6, 451–456 (2018). https://doi.org/10.26438/ijcse/v6i9.451456
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84–90 (2017). https://doi.org/10.1145/3065386
Ku, W., Kankanhalli, M.S., Lim, J.-H.: Using camera settings templates (“Scene Modes’’) for image scene classification of photographs taken on manual/expert settings. In: Ip, H.H.-S., Au, O.C., Leung, H., Sun, M.-T., Ma, W.-Y., Hu, S.-M. (eds.) PCM 2007. LNCS, vol. 4810, pp. 10–17. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-77255-2_2
Lazebnik, S.: Computer Vision: A Reference Guide, Object Class Recognition (Categorization), pp. 533–536. Springer, Cham (2014). https://doi.org/10.1007/978-0-387-31439-6_337
Luo, J., Boutell, M., Brown, C.: Pictures are not taken in a vacuum - an overview of exploiting context for semantic scene content understanding. IEEE Signal Process. Mag. 23(2), 101–114 (2006). https://doi.org/10.1109/MSP.2006.1598086
Maître, H.: From Photon to Pixel: The Digital Camera Handbook. Wiley, New York (2017). https://doi.org/10.1002/9781119402442, https://onlinelibrary.wiley.com/doi/abs/10.1002/9781119402442.ch1
Negoescu, R.A., Gatica-Perez, D.: Analyzing Flickr groups. In: Proceedings of the 2008 international Conference on Content-Based Image and Video Retrieval, CIVR 2008, pp. 417–426. ACM, New York, NY, USA (2008). https://doi.org/10.1145/1386352.1386406
Safonov, I.V., Kurilin, I.V., Rychagov, M.N., Tolstaya, E.V.: Image enhancement pipeline based on EXIF metadata. In: Adaptive Image Processing Algorithms for Printing. SCT, pp. 65–83. Springer, Singapore (2018). https://doi.org/10.1007/978-981-10-6931-4_3
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510–4520, June 2018. https://doi.org/10.1109/CVPR.2018.00474
Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 60 (2019). https://doi.org/10.1186/s40537-019-0197-0
Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105–6114 (2019)
Thread, F.H.F.O.: Updates on tags, May 2015. https://www.flickr.com/help/forum/en-us/72157652019487118/. Accessed 8 Nov 2022
Yu, T., Zhu, H.: Hyper-parameter optimization: a review of algorithms and applications. ArXiv arXiv:abs/2003.05689 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Lederer, R., Bullin, M., Henrich, A. (2023). Exploiting Exif Data to Improve Image Classification Using Convolutional Neural Networks. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing – ICIAP 2023. ICIAP 2023. Lecture Notes in Computer Science, vol 14233. Springer, Cham. https://doi.org/10.1007/978-3-031-43148-7_40
Download citation
DOI: https://doi.org/10.1007/978-3-031-43148-7_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43147-0
Online ISBN: 978-3-031-43148-7
eBook Packages: Computer ScienceComputer Science (R0)