Content-Based Microbial Image Retrieval

• Grant number: 24/07589-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2024
• End date: March 31, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Antonio Rafael Sabino Parmezan
• Grantee: Angela Patricia Mestas Muñante
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 19/17721-9 - The role of Chemistry in holobiont adaptation, AP.TEM

Abstract

Technological advances have driven the development of increasingly larger and more complex image databases, thus increasing the demand for effective image retrieval methods that meet users' needs. Over the past two decades, researchers have extensively studied content-based image retrieval for various applications, except for microbial culture images. This project aims to develop a content-based retrieval module for images of microorganisms cultivated on solid media. We will investigate and compare different feature extractors, multidimensional indexers, and similarity measures. Our attention will focus on reducing the semantic gap between the image feature representation and human visual perception. We will evaluate the proposed module's performance both quantitatively, in terms of precision, recall and execution time, and qualitatively. In the latter case, domain experts will analyze the search results to determine the match quality between the retrieved images and the queries.