MIJ 2025, Volume 134, Number 5 (pp. 20 to 26)
[ACTIVE]
Search Engine Image Optimization
Metadata
- Publisher
- SMPTE
- Doc Type
- Journal Article
- Content Type
- Original Research
- Abbreviated Title
- SMPTE Motion Imaging Jour.
- Volume
- 134, No. 5, pp. 20–26
- Abstract
- Vector-based image search, which represents images and search queries as vectors in a high-dimensional space, performs image search by identifying images whose vector representations closely match the vector representation of the query. Search engine optimization has been traditionally achieved by using relevant keywords to increase organic search engine discoverability. For images to be surfaced as a result of a search query, these relevant keywords have been inserted into the page that hosts the image or embedded directly into an image as metadata that can be decoded and indexed by a text-based search engine. However, when a search engine uses vectors to operate, the static nature of an image's vector representation prevents adaptation of content to increase discoverability. In this paper, we present a novel approach to alter an image in a way that enhances its discoverability with a known vector-based search engine while minimizing the visual impact of these alterations for the average user. The alteration is guided by the maximization of intended search queries and the minimization of unwanted search queries.
- Publication Date
- 2025-09-01
- DOI
10.5594/JMI.2025/FVEV7398- ISSN
- Print:
1545-0279| Electronic:2160-2492 - Link
- https://doi.org/10.5594/JMI.2025/FVEV7398
- Author(s)
- Jean-Yves CouleaudMathew AdamsNing Xu
- Keyword(s)
- Vector Search, Image Search Engine Optimization
- Copyright
- © 2025 SMPTE
Bibliographic Reference(s)
- James Han, “How to Build a Visual Search Engine.” [Online]. Available: Medium: https://medium.com/analytics-vidhya/how-to-build-a-visual-search-engine-64046e58ad2f. EXTERNAL
- Ian J. Goodfellow, Jonathon Shlens & Christian Szegedy, “Explaining and Harnessing Adversarial Examples,” Internat Conf. Learning Representations, 2015. EXTERNAL
- Christian Szegedy, Wojciech Zaremba, Lya Sutskever, Joan Bruna, Dumitru Erhan, Ian Goodfellow, Rob Fergus, “Intriguing Properties of Neural Networks,” Internat. Conf. on Learning Representations, 2014. EXTERNAL
- Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, “Universal adversarial perturbations,” Proc. IEEE Conf. Comput. Vis. Pattern Recognit. pp.1765–1773, 2017. EXTERNAL
- Nicolas Papernot, Patrick McDaniel, Ian Goodfellow, Somesh Jha, Z. Berkay Celik, Ananthram Swami, “Practical black-box attacks against machine learning,” Proc. 2017 ACM Asia Conf. Comput. Commun. Secur., pp.506–519, 2017. EXTERNAL
- Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever, “Learning Transferable Visual Models From Natural Language Supervision,” CoRR, vol. abs/2103.00020, 2021. EXTERNAL
- Christian Szegedy, Vincent Vanhoucke, Sergey Loffe, Jonathon Shlens, Zbig-niew Wojna, “Rethinking the Inception Architecture for Computer Vision,” vol. abs/1512.00567, 2015. EXTERNAL
- Stanislav Fort, “Adversarial examples and their generalization for the OpenAI CLIP model.” [Online]. Available: https://github.com/stanislavfort/OpenAI_CLIP_adversarial_examples/blob/main/OpenAI_CLIP_adversarial_images_playground.ipynb. EXTERNAL
- Aaron Tello-Wharton, “Hackers Guide to Resisting the AI Apocalypse.” 2021. [Online]. Available: blog.majestic.com. EXTERNAL
Source Data (JSON)
Full registry record with provenance metadata. Open directly: /api/doc/10.5594-JMI.2025-FVEV7398.json
Reference Tree
Explore all references and references to this document, as a navigable tree.
Open Reference TreeReference this Doc
Plain text (ISO 690 compliant)
Preview:
Jean-Yves Couleaud, Mathew Adams, and Ning Xu; Search Engine Image Optimization, MIJ 2025, Volume 134, Number 5 (pp. 20 to 26); SMPTE, 2025. Available at https://doi.org/10.5594/JMI.2025/FVEV7398
Snippet:
Jean-Yves Couleaud, Mathew Adams, and Ning Xu; Search Engine Image Optimization, MIJ 2025, Volume 134, Number 5 (pp. 20 to 26); SMPTE, 2025. Available at https://doi.org/10.5594/JMI.2025/FVEV7398
HTML (ISO 690 compliant)
Preview:
Jean-Yves Couleaud, Mathew Adams, and Ning Xu; Search Engine Image Optimization, MIJ 2025, Volume 134, Number 5 (pp. 20 to 26); SMPTE, 2025. Available at https://doi.org/10.5594/JMI.2025/FVEV7398
Snippet:
<span class="citation">Jean-Yves Couleaud, Mathew Adams, and Ning Xu; <cite>Search Engine Image Optimization</cite>, MIJ 2025, Volume 134, Number 5 (pp. 20 to 26); SMPTE, 2025. Available at <a href="https://doi.org/10.5594/JMI.2025/FVEV7398" target="_blank" rel="noopener">https://doi.org/10.5594/JMI.2025/FVEV7398</a></span>
SMPTE's HTML Pub
Preview:
Jean-Yves Couleaud, Mathew Adams, and Ning Xu; Search Engine Image Optimization, MIJ 2025, Volume 134, Number 5 (pp. 20 to 26); SMPTE, 2025
doi: 10.5594/JMI.2025/FVEV7398
url: https://doi.org/10.5594/JMI.2025/FVEV7398
doi: 10.5594/JMI.2025/FVEV7398
url: https://doi.org/10.5594/JMI.2025/FVEV7398
Snippet:
<li> Jean-Yves Couleaud, Mathew Adams, and Ning Xu; <cite id="bib-10-5594-jmi-2025-fvev7398">Search Engine Image Optimization</cite>, MIJ 2025, Volume 134, Number 5 (pp. 20 to 26); SMPTE, 2025 <span class="doi">10.5594/JMI.2025/FVEV7398</span> </li>