Use of subimages in fish species identification

Abstract

Many scholarly tasks involve working with subdocuments, or contextualized fine-grain information, i.e., with information that is part of some larger unit. A digital library (DL) facilitates management, access, retrieval, and use of collections of data and metadata through services. However, most DLs do not provide infrastructure or services to support working with subdocuments. Superimposed information (SI) refers to new information that is created to reference subdocuments in existing information resources. We combine this idea of SI with traditional DL services, to define and develop a DL with SI (SI-DL). We explored the use of subimages and evaluated the use of SuperIDR, a prototype SI-DL, in fish species identification, a scholarly task that involves working with subimages. The contexts and strategies of working with subimages in SuperIDR suggest new and enhanced support (SI-DL services) for scholarly tasks that involve working with subimages, including new ways of querying and searching for subimages and associated information. The main conceptual contributions of our work are the insights gained from these findings of the use of subimages and of SuperIDR, which lead to recommendations for the design of digital libraries with superimposed information.

A formal approach for the specification of digital complex objects

“…These key concepts were further extended to consider several common DL components, services, and different contexts related to DLs. As an example, consider the CO definition [15], validated through the use of SuperIDR [23], a tool that manages images, metadata, marks, and annotations in the Ichthyology and Parasitology domain [25].…”

A mutimodal framework for geocoding digital objects

“…geographic information retrieval of scholarly digital libraries based on image, sound, text, location, and time. For example, in [95], the fish species identification task is based on narrowing down the candidate family based on locations where a specimen was found besides other usual physical characteristics. Additionally, it might be interesting to explore the combination of the ranked lists from the searches of each individual feature in order to improve the final result;…”

Arcabouço para anotação de componentes de imagem

“…Do ponto de vista comercial, por exemplo, imagens associadas a objetos vendidos por lojas virtuais vêm sendo empregadas para auxiliar potenciais clientes na escolha de produtos mais adequados a seus interesses. Na área científica destaca-se o uso de imagens em: sistemas de informação de biodiversidade [14,46]; ou no entendimento de fenômenos ambientais a partir da análise de imagens de sensoriamento remoto [20]. Do ponto de vista pessoal, um grande número de imagens vem sendo compartilhadas em redes sociais, como o Flickr 1 .…”

“…Segundo [41], objetos complexos podem ser definidos como uma única entidade que é composta de múltiplas partes, que podem ser outras entidades compostas ou uma entidade simples definida por si só como um objeto. Exemplos de aplicações que têm usado objetos complexos do tipo imagem incluem: gerenciamento de dados sobre espécies em sistemas de informação de biodiversidade [38,46]; gerenciamento de grandes coleções de impressões digitais [39] e gerenciamento de estórias de vídeos [37].…”