Content-Based Image Search on the Web and its Application in the Fields of Art and Culture
Ημ/νία και ώρα: 13/10/2022 (16:00-17:45)
Minas Pergantis, Aristeidis Lamprogeorgos, Andreas Giannakoulopoulos
Λέξεις Κλειδιά: reverse image search, web services, art, culture, content-based image retrieval


Searching the World Wide Web for content has been a necessary function from the early days of the Web, when it started expanding beyond the capabilities of indexing services. The usual method of searching takes the form of a query comprising of a short series of keywords, usually nouns, that are provided to the search platform (Barr et al, 2008). The results of this querying process can be a series of websites, images, records in a database or other informational or multimedia content. But when searching specifically for digital media, it is doubtful whether keywords are enough to convey the intentions of the end user. Content-based image retrieval, which means searching for images or media using an image or other medium as input instead of a query, provides an alternative that can address the limitations of the classic query based search method. Content-based search methods are necessary when there is no explicit textual annotation that describes the object of search but can also be helpful in increasing accuracy alongside text annotations (Lew et al, 2006). In the fields of Arts and Culture, digital libraries that offer visual content play a prominent role, which means that content-based searching can potentially provide an effective alternative to discovering relevant content beyond conventional means.

With Cloud computing technologies in their second decade of existence, the capabilities of online content-based search tools, provided as Web or Cloud services are constantly increasing while being more cost-effective than ever before(Qian et al, 2009). Taking into account the visual nature of the Arts this article attempts to investigate the value that these technologies can offer to developers creating applications related to the fields of Art and Cultural heritage. Web services can be used to reap the benefits of Machine Learning and Artificial Intelligence that have been the cornerstone of evolution for content-based image retrieval algorithms (Wan et al, 2014), with only a fraction of the cost and technical know-how. Unfortunately, the realm of Web services and providers can be daunting to navigate, especially since the alternatives are plentiful, while at the same time there is a noticeable lack of standardization, both in terms of what is offered and in terms of how it is priced (Ghosh et al, 2014).

In this article, a comprehensive analysis of the landscape of visual search tools, reverse image search tools and other content-based searching services is provided, with an emphasis on the way these services can be useful for developers and applications operating in the field of Art and Cultural Heritage. A detailed review of multiple popular platforms and their capabilities are presented. These capabilities range from finding other visually similar images and tracing specific content with regards to copyright, to deriving semantic insights, identifying items and even composing textual annotations based on pattern recognition techniques. A comparison between the various service providers, the capabilities they offer, the estimated costs and the feasibility of adopting and making most use out of these tools is presented. The focus of this comparison is how the various factors under consideration may impact their use in the fields of Art and Cultural Heritage. Finally, conclusions are drawn concerning the potential these services may offer to developers creating or expanding digital platforms in the world of Arts and Culture, not only in terms of increased capabilities and added functionality but also in terms of their effects on cost effectiveness or even revenue increase.


La recherche de contenu sur le World Wide Web a été une fonction nécessaire depuis les débuts du Web, lorsqu'il a commencé à s'étendre au-delà des capacités des services d'indexation. Mais lors d'une recherche spécifique aux médias numériques, il est douteux que les mots-clés suffisent à transmettre les intentions de l'utilisateur final. La récupération d'images basée sur le contenu, qui consiste à rechercher des images ou des médias en utilisant une image ou un autre support comme entrée au lieu d'une requête, offre une alternative qui peut répondre aux limites de la méthode de recherche classique basée sur une requête. Avec les technologies de cloud computing dans leur deuxième décennie d'existence, les capacités des outils de recherche basés sur le contenu en ligne, fournis sous forme de services Web ou cloud, augmentent constamment tout en étant plus rentables que jamais. Dans cet article, une analyse complète du paysage des outils de recherche visuelle, des outils de recherche d'images inversées et d'autres services de recherche basés sur le contenu est fournie, en mettant l'accent sur la manière dont ces services peuvent être utiles aux développeurs et aux applications opérant dans le domaine de l'art. et patrimoine culturel. Des conclusions sont tirées concernant le potentiel que ces services peuvent offrir aux développeurs créant ou développant des plateformes numériques dans le monde des Arts et de la Culture.


EUTIC 2022

Κοι.Σ.Π.Ε. Επιχειρούμε ΜαζίΚοι.Σ.Π.Ε. Επιχειρούμε Μαζί
Ανάγνωση ΚειμένουΑνάγνωση Κειμένου Αναγνωσιμότητα ΚειμένουΑναγνωσιμότητα Κειμένου Αντίθεση ΧρωμάτωνΑντίθεση Χρωμάτων
Επιλογές Προσβασιμότητας