MicroMatch: A Content-Based Macroscopic Microbial Image Retrieval Module

• Antonio R. S. Parmezan USP
• Angela P. M. Muñante USP
• Diego Minatel USP
• Solange O. Rezende USP

DOI: https://doi.org/10.5753/webmedia_estendido.2025.16431

Resumo

Identifying microorganisms is essential for investigating the chemical substances they produce, which have potential applications in biotechnology and pharmaceuticals. Artificial intelligence, particularly machine learning and Content-Based Image Retrieval (CBIR), provides means to make this task more efficient by improving accuracy and reducing operational costs. While supervised learning models for classification are trained to predict taxonomic groups, such as genus and/or species, with high predictive performance from microbial image collections, CBIR supports domain experts by retrieving visually similar samples from these databases, contributing to more reliable decision-making with respect to recognition. This paper presents MicroMatch, a prototype computational module for CBIR of microorganisms cultivated in Petri dishes. We describe the tool herein, covering image acquisition with a customized low-cost device and extending to the design of a similarity search framework that integrates an indexing structure and a matching engine tailored to the specific characteristics of the aforementioned multimedia data type. Through an intuitive interface, MicroMatch promises to accelerate microbial biodiscovery.

Palavras-chave: image search, feature extraction, dimensionality reduction, multidimensional indexing, information retrieval

Referências

Line H Clemmensen, Michael E Hansen, Jens C Frisvad, and Bjarne K Ersbøll. 2007. A method for comparison of growth media in objective identification of Penicillium based on multi-spectral imaging. J. Microbiol. Methods 69, 2 (2007), 249–255.

João Pedro Ribeiro da Silva and Antonio R. S. Parmezan. 2025. Assessing the feasibility of a spatio-temporal approach for recognizing microorganisms in image sequences. In CoTB, Vol. 16. UNIVALI, Itajaí, Brazil, 602–604.

Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR. OpenReview.net, Vienna, Austria, 1–21.

Danielle R. Gonçalves, Antonio R. S. Parmezan, Lucianne F. P. Oliveira, Simone P. Lira, Roberto G. S. Berlinck, and Solange O. Rezende. 2023. Petri dish imagecapturing guidelines for artificial intelligence-based microorganism recognition. In CBM. SBM, Foz do Iguaçu, Brazil, 615–1.

Kenneth J Locey and Jay T Lennon. 2016. Scaling laws predict global microbial diversity. Proc. Natl. Acad. Sci. 113, 21 (2016), 5970–5975.

Angela P. M. Muñante and Antonio R. S. Parmezan. 2025. Content-based macroscopic microbial image retrieval: Preliminary results. In CILAMCE. ABMEC, Vitória, Brazil, 1–7.

Antonio R. S. Parmezan, João Pedro Ribeiro da Silva, Diego Minatel, and SolangeO. Rezende. 2025. A spatio-temporal approach for identifying microorganisms in short image sequences. arXiv (2025).

Antonio R. S. Parmezan, Danielle R. Gonçalves, and Solange O. Rezende. 2025. A unified framework for Petri dish image acquisition and processing to promote consistency in microorganism identification. arXiv (2025).

Antonio R. S. Parmezan, Angela P. M. Muñante, Diego Minatel, and Solange O. Rezende. 2025. Content-based macroscopic microbial image retrieval. arXiv (2025).

Hedieh Sajedi, Fatemeh Mohammadipanah, and Ali Pashaei. 2020. Imageprocessing based taxonomy analysis of bacterial macromorphology using machine-learning models. Multimed. Tools Appl. 79 (2020), 32711–32730.

HongdaWang, Hatice Ceylan Koydemir, Yunzhe Qiu, Bijie Bai, Yibo Zhang, Yiyin Jin, Sabiha Tok, Enis Cagatay Yilmaz, Esin Gumustekin, Yair Rivenson, et al. 2020. Early detection and classification of live bacteria using time-lapse coherent imaging and deep learning. Light Sci. Appl. 9, 1 (2020), 118.

Han Yu, Bolin Lu, Xinyu Ouyang, Yuhang Yang, Yue Zhang, Haobo Meng, Marcin Grzegorzek, Xin Zhao, Chen Li, and Hongwei Lei. 2024. Texture features based microbiological image retrieval. In ICFEICT. Springer, Beijing, China, 470–481.

Jinghua Zhang, Chen Li, Yimin Yin, Jiawei Zhang, and Marcin Grzegorzek. 2023. Applications of artificial neural networks in microorganism image analysis: a comprehensive review from conventional multilayer perceptron to popular convolutional neural network and potential visual transformer. Artif. Intell. Rev. 56, 2 (2023), 1013–1070.

Yanling Zou, Chen Li, Kimiaki Shirahama, Tao Jiang, and Marcin Grzegorzek. 2016. Environmental microorganism image retrieval using multiple colour channels fusion and particle swarm optimisation. In ICIP. IEEE, Phoenix, USA, 2475–2479.

Yanling Zou, Chen Li, Kimiaki Shirahama, Tao Jiang, and Marcin Grzegorzek. 2017. Content-based image retrieval of environmental microorganisms using double-stage optimisation-based fusion. Inf. Eng. Express 3, 4 (2017), 43–53.

Yanling Zou, Chen Li, Kimiaki Shirahama, Florian Schmidt, Tao Jiang, and Marcin Grzegorzek. 2016. Content-based microscopic image retrieval of environmental microorganisms using multiple colour channels fusion. In Computer and Information Science. Studies in Computational Intelligence, Vol. 605. Springer, Okayama, Japan, 119–130.

Yan Ling Zou, Chen Li, Zeyd Boukhers, Kimiaki Shirahama, Tao Jiang, and Marcin Grzegorzek. 2016. Environmental microbiological content-based image retrieval system using internal structure histogram. In CORES. Springer, Wrocław, Poland, 543–552.