Exploring Diversified Similarity with Kundaha

Santos, Lucio F. D.; Blanco, Gustavo; Oliveira, Daniel de; Traina, Agma J. M.; Traina, Caetano; Bedo, Marcos V. N.

doi:10.1145/3269206.3269220

Cited by 6 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CBIR systems are commonly designed and implemented for specific domains, such as Medical [Bedo and et. al 2016;Santos et al 2018], agricultural [Ruiz et al 2018], remote sensing [Rosu et al 2017], and social networks [Maigrot et al 2017]. Such lack of a general solution is mainly due to the variety of parameters involved in the search process, e.g., feature vector extractor, distance function, query operator, and relevance feedback technique, which can impact negatively in the quality of CBIR results [Bedo and et.…”

Section: Final Resultsmentioning

confidence: 99%

“…It leads to the so-called "CBIR gap" where result sets include nearly-duplicate data, which prevents the exploration of relevant portions of the search space and skew any decision-making process. The bridging of such gap is carried out with user-oriented relevance feedback cycles [Xioufis et al 2015;Santos et al 2018] or result diversification [Santos et al 2018]. While relevance feedback cycles are a burdensome task that may drive the user to give up the search [Santos and et.…”

Section: Final Resultsmentioning

confidence: 99%

“…al 2011a], (3) Poikilo [Drosou and Pitoura 2013], (4) VikS [Santos and et. al 2014], and (5) Kundaha [Santos et al 2018]. Those tools target the parameter tuning problem for a domain, as follows:…”

Section: Final Resultsmentioning

confidence: 99%

See 2 more Smart Citations

J-EDA: A workbench for tuning similarity and diversity search parameters in content-based image retrieval

Novaes¹,

Santos

Carvalho

et al. 2021

jidm

Self Cite

View full text Add to dashboard Cite

Similarity searches can be modeled by means of distances following the Metric Spaces Theory and constitute a fast and explainable query mechanism behind content-based image retrieval (CBIR) tasks. However, classical distance-based queries, e.g., Range and k-Nearest Neighbors, may be unsuitable for exploring large datasets because the retrieved elements are often similar among themselves. Although similarity searching is enriched with the imposition of rules to foster result diversification, the fine-tuning of the diversity query is still an open issue, which is is usually carried out with and a non-optimal expensive computational inspection. This paper introduces J-EDA, a practical workbench implemented in Java that supports the tuning of similarity and diversity search parameters by enabling the automatic and parallel exploration of multiple search settings regarding a user-posed content-based image retrieval task. J-EDA implements a wide variety of classical and diversity-driven search queries, as well as many CBIR settings such as feature extractors for images, distance functions, and relevance feedback techniques. Accordingly, users can define multiple query settings and inspect their performances for spotting the most suitable parameterization for a content-based image retrieval problem at hand. The workbench reports the experimental performances with several internal and external evaluation metrics such as P × R and Mean Average Precision (mAP), which are calculated towards either incremental or batch procedures performed with or without human interaction.

show abstract

Section: Final Resultsmentioning

confidence: 99%

Section: Final Resultsmentioning

confidence: 99%

See 1 more Smart Citation

J-EDA: A workbench for tuning similarity and diversity search parameters in content-based image retrieval

Novaes¹,

Santos

Carvalho

et al. 2021

jidm

Self Cite

View full text Add to dashboard Cite

show abstract

“…This scenario brings out the need for processing the available data effectively and efficiently. The appropriate analysis of the available information can help authorities in emergency situations (CHINO et al, 2015;OLIVEIRA et al, 2016), supporting education and medical decision-making (SANTOS et al, 2018;FERREIRA et al, 2018), as well as speeding-up pipelines known to be time-consuming (STEGMAIER et al, 2014;HE et al, 2017;ULMAN et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Conquering knowledge from images: improving image mining with region-based analysis and associated information

Cazzolato¹

View full text Add to dashboard Cite

show abstract

“…Interface do Kundaha para realização de consultas por similaridade e diversidade.Fonte:Santos et al (2018).…”

unclassified

Classificação de úlceras venosas dermatológicas para apoio a consultas por similaridade utilizando superpixels e aprendizado profundo

Blanco¹

Self Cite

View full text Add to dashboard Cite

Sistemas de recuperação de imagens por conteúdo (do inglês "Content-based Image Retrieval"-CBIR) têm sido cada vez mais utilizados em diversas aplicações de tratamento e análise de imagens, devido a dois fatores: CBIR é um procedimento que pode ser feito automaticamente, permitindo tratar o grande volume de imagens adquiridos em hospitais, e também é a base para o processamento de consultas por similaridade. No contexto médico tais sistemas auxiliam em diversas tarefas, desde treinamento de profissionais até em sistemas de auxílio a diagnóstico (do inglês "Computer-Aided Diagnosis"-CAD). Um sistema computacional capaz de comparar e classificar imagens obtidas em exames de pacientes utilizando uma base prévia de conhecimento poderia agilizar o atendimento da população e fornecer aos especialistas informações relevantes de forma rápida e simples. Neste trabalho, o foco foi na análise de imagens de úlceras venosas. Foram desenvolvidas duas técnicas para classificação dessas imagens. A primeira, denominada Counting-Labels Similarity Measure (CL-Measure) possui a vantagem de lidar com imagens segmentadas de forma automática, por superpixels, e ser versátil o suficiente para permitir adaptação para outros domínios. A ideia principal do CL-Measure consiste na criação de sub-imagens baseadas em uma classificação prévia, calcular a distância entre elas e agregar as distâncias parciais obtidas a partir de uma função apropriada. A segunda técnica, denominada Quality of Tissues from Dermatological Ulcers (QTDU), faz uso de redes convolucionais (CNNs) para rotulação dos superpixels com a vantagem de compor todo o processo de identificação de características e classificação, dispensando a necessidade de identificar qual o extrator de características mais adequado para o contexto em questão. Experimentos realizados sobre a base de imagens analizada, utilizando 179572 superpixels divididos em 4 classes, indicam que a QTDU é a abordagem mais eficaz até o momento para o contexto de classificação de imagens dermatológicas, com médias de AUC=0,986, sensitividade=0,97, e especificidade=0,974 superando as abordagens anteriores baseadas em aprendizado de máquina em 11, 7% e 8, 2% considerando o coeficiente KAPPA e F-Measure, respectivamente.

show abstract

Exploring Diversified Similarity with Kundaha

Cited by 6 publications

References 9 publications

J-EDA: A workbench for tuning similarity and diversity search parameters in content-based image retrieval

J-EDA: A workbench for tuning similarity and diversity search parameters in content-based image retrieval

Conquering knowledge from images: improving image mining with region-based analysis and associated information

Classificação de úlceras venosas dermatológicas para apoio a consultas por similaridade utilizando superpixels e aprendizado profundo

Contact Info

Product

Resources

About