A novel content-based image retrieval system with feature descriptor integration and accuracy noise reduction

Vieira, Gabriel da Silva; Fonseca, Afonso U.; Sousa, Naiane Maria de; Felix, Juliana Paula; Soares, Fabrízzio

doi:10.1016/j.eswa.2023.120774

Cited by 10 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although there have been considerable advances, mostly concentrated on the ability to process large volumes of images and on the use of deep learning models, CBIR systems still have several problems, namely concerning their effectiveness and reliability [ 44 – 50 ], which highlights a gap between the results achieved by existing solutions and those expected from a system to be used by the market, particularly in the area of Intellectual Property [ 41 ], where lack of precision can lead to lawsuits.…”

Section: Introductionmentioning

confidence: 99%

DarwinGSE: Towards better image retrieval systems for intellectual property datasets

António,

Valente,

Mora

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

A trademark’s image is usually the first type of indirect contact between a consumer and a product or a service. Companies rely on graphical trademarks as a symbol of quality and instant recognition, seeking to protect them from copyright infringements. A popular defense mechanism is graphical searching, where an image is compared to a large database to find potential conflicts with similar trademarks. Despite not being a new subject, image retrieval state-of-the-art lacks reliable solutions in the Industrial Property (IP) sector, where datasets are practically unrestricted in content, with abstract images for which modeling human perception is a challenging task. Existing Content-based Image Retrieval (CBIR) systems still present several problems, particularly in terms of efficiency and reliability. In this paper, we propose a new CBIR system that overcomes these major limitations. It follows a modular methodology, composed of a set of individual components tasked with the retrieval, maintenance and gradual optimization of trademark image searching, working on large-scale, unlabeled datasets. Its generalization capacity is achieved using multiple feature descriptions, weighted separately, and combined to represent a single similarity score. Images are evaluated for general features, edge maps, and regions of interest, using a method based on Watershedding K-Means segments. We propose an image recovery process that relies on a new similarity measure between all feature descriptions. New trademark images are added every day to ensure up-to-date results. The proposed system showcases a timely retrieval speed, with 95% of searches having a 10 second presentation speed and a mean average precision of 93.7%, supporting its applicability to real-word IP protection scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%