Renata Maria Abrantes Baracho, Beatriz Valadares Cendón Chapter 13. An image based retrieval system for engineering drawings Abstract: The study presents the conceptual model, the classification scheme and the prototype of an image retrieval system for engineering drawings. The model integrates concepts and techniques of information science and computer science, joining human interpretation and automated processing, and using textual and visual metadata as access points for retrieval. The paper discusses the tests and the case study used to optimize and validate the system proposed. The tests, using a database of 332 drawings, show the feasibility of the system which presented 90.3 % recall using a similarity rate of 70 % on average. Human and automatic processing for indexing and the classification scheme were important factors in reducing processing time. Keywords: Image retrieval, image based retrieval system, image retrieval system, concept based retrieval, engineering drawing retrieval system, information retrieval system, technical drawings, engineering drawings, technical drawing indexing, visual metadata Renata Maria Abrantes Baracho (corresponding author), Assistant Professor, School of Information Science, Federal University of Minas Gerais, renatabaracho@eci.ufmg.br Beatriz Valadares Cendón, Associate Professor, School of Information Science, Federal University of Minas Gerais Introduction The motivation for the current study was the difficulty in information retrieval of engineering drawings required for decision-making, as well as the need to achieve greater efficiency in the process of encountering information in large sets of drawings. Current information retrieval systems for engineering drawings use textual data to index and retrieve drawing files, and do not normally consider visual data. Information retrieval in data-bases that may contain thousands of drawings frequently depends on someone who participated in the project, and it is impaired when that person is no longer part of the process. rassmussen_neal_indexing.indb 314 15.08.12 11:42