Qualifound – a modular tool developed for quality improvement in foundries

Purpose – Castings defects are usually easy to characterize, but to eradicate them can be a difficult task. In many cases, defects are caused by the combined effect of different factors, whose identification is often difficult. Besides, the real non-quality costs are usually unknown, and even neglected. This paper aims to describe the development of a modular tool for quality improvement in foundries, and its main objective is to present the application potential and the foundry process areas that are covered and taken into account. Design/methodology/approach – The integrated model was conceived as an expert system, designated Qualifound, which performs both qualitative and quantitative analyses. For the qualitative analyses mode, the nomenclature and the description of defects are based on the classification suggested by the International Committee of the Foundry Technical Association. Thus, a database of defects was established, enabling one to associate the defects with the relevant process operations and the identification of their possible causes. The quantitative analysis mode deals with the number of produced and rejected castings and includes the calculation of the non-quality costs. Findings – The validation of Qualifound was carried out in a Portuguese foundry, whose quality system had been certified according to the ISO 9000 standards. Qualifound was used in every management area and it was concluded that the application had the required technological requisites to provide the necessary information for the foundry management to improve process quality. Originality/value – The paper presents a successful application of an informatics tool on quality improvement in foundries.

Computer-aided recognition of dental implants in X-ray images

Dental implant recognition in patients without available records is a time-consuming and not straightforward task. The traditional method is a complete user-dependent process, where the expert compares a 2D X-ray image of the dental implant with a generic database. Due to the high number of implants available and the similarity between them, automatic/semi-automatic frameworks to aide implant model detection are essential. In this study, a novel computer-aided framework for dental implant recognition is suggested. The proposed method relies on image processing concepts, namely: (i) a segmentation strategy for semi-automatic implant delineation; and (ii) a machine learning approach for implant model recognition. Although the segmentation technique is the main focus of the current study, preliminary details of the machine learning approach are also reported. Two different scenarios are used to validate the framework: (1) comparison of the semi-automatic contours against implant’s manual contours of 125 X-ray images; and (2) classification of 11 known implants using a large reference database of 601 implants. Regarding experiment 1, 0.97±0.01, 2.24±0.85 pixels and 11.12±6 pixels of dice metric, mean absolute distance and Hausdorff distance were obtained, respectively. In experiment 2, 91% of the implants were successfully recognized while reducing the reference database to 5% of its original size. Overall, the segmentation technique achieved accurate implant contours. Although the preliminary classification results prove the concept of the current work, more features and an extended database should be used in a future work.