Image and Multimedia Data Science Laboratory (IMSCIENCE)
Image and Multimedia Data Science Laboratory (IMScience)

IMScience, previously VIPLAB, is a research lab hosted at and certified by PUC Minas (Belo Horizonte Campus, Brazil), and it has started its operation in 2004. The main project areas are: digital image, video and audio processing; multimedia indexing and retrieval; multimedia content analysis. Many projects have been conducted with cooperation of other institutions and/or labs, such as NPDI/DCC/UFMG, IC/UNICAMP, TEXMEX/IRISA and ESIEE/FRANCE. And, besides the projects developed with the participation of several graduate and undergraduate students, IMScience has also been involved in bilateral programs for international cooperation such as FAPEMIG-INRIA, CAPES-BRAFITEC and CAPES-COFECUB.


(in Portuguese) Estamos recrutando alunos de Iniciação Científica e Trabalho de Conclusão de Curso para atuar em projetos de: (i) COVID; (ii) Irradiação solar; e (iii) Análise de tecidos histológicos. Caso tenha interesse, não hesite em nos contactar.
A partnership between IMScience and ESCO have started in Dec 2020 in order to apply image analysis to identify ground engaging tool.
IMScience leads the Observatório COVID at PUC Minas. Other researches groups also participate of this initiative: LEASDLE, Graduate Program in Geography and Graduate Program in Dentistry.
IMScience was officially considered, in 2020, as an Associated Team of LinkMedia Team (IRISA/France).
Acceptance of CAPES/COFECUB project involving Brazil-France being coordinated by Prof. Silvio - December, 2018
First defensis in English in our Graduate Program in Informatics - 20th November, 2017
Special Session at IJCNN 2018 co-organized by members of our team
Talk of Prof. Silvio at IME/USP - 26th October, 2017
Participation of Prof. Silvio as invited speaker at Workshop FAPEMIG/PUC Peru - 05-06th October, 2017


Multimedia information processing (= audio, images, videos, …)

Very large unstructured database (or semi-structured)
Different modals for describing the information (= multimodality)
Different ways for describing the information (= multifeature)

Approaches in different levels

Low - Selection and combining of descriptors/ Data indexing and retrieval
Medium - Data mining / Identification of components: objs, people, places,…
High - Knowledge discovery: violency, trend topics, …


postal address Computer Science Department, Rua Walter Ianni, 255 - São Gabriel - BH/MG/Brazil - CEP: 31980110
office address Office L306
facsimile \(+55 (31) 3439 5204\)
telephone \(+55 (31) 3439 5204\)
e-mail sjamil at pucminas dot br

Supported by