Zoran Anišić

Introducing Mass Customization to SMEs in Furniture Industry: A Case Study

Even though much insights has been gained by academic research on mass customization (MC), companies still suffer from a lack of guidelines and supports that help them in the process of implementing MC. The paper presents an approach to help small and medium enterprises (SMEs) in implementing MC by illustrating its actual application in SME operating in the furniture industry. Possibilities of MC implementation in the case company and more generally in the SME furniture manufacturers are discussed in the conclusions of the work.

Implementation guidelines for mass customization: current characteristics and suggestions for improvement

Abstract Interest in mass customization (MC) is increasing in both industry and academia. Academic research on MC implementation guidelines (IGs) has, however, lagged behind other research streams in the MC literature. The present article reviews the existing literature on MC-IGs and inductively derives a classification scheme for prior research findings to identify potential areas for further research. While the issue of what enables MC has been intensively researched, investigation of several questions is still required, such as which enablers should be implemented and in what sequence, depending on the specific context in which MC is pursued. Other areas for future study of MC-IGs include applicability context specifications, as-is analysis tools, hindrance factors and required resources. This article complements previous MC literature reviews by providing an overview of MC-IGs available in the literature, identifying the building blocks of MC-IGs and proposing a definition of MC-IGs that can be used as a basis for future research in MC implementation.

Binary Classification of Images for Applications in Intelligent 3D Scanning

Three-dimensional (3D) scanning techniques based on photogrammetry, also known as Structure-from-Motion (SfM), require many two-dimensional (2D) images of an object, obtained from different viewpoints, in order to create its 3D reconstruction. When these images are acquired using closed-space 3D scanning rigs, which are composed of large number of cameras fitted on multiple pods, flash photography is required and image acquisition must be well synchronized to avoid the problem of ‘misfired’ cameras. This paper presents an approach to binary classification (as ‘good’ or ‘misfired’) of images obtained during the 3D scanning process, using four machine learning methods—support vector machines, artificial neural networks, k-nearest neighbors algorithm, and random forests. Input to the algorithms are histograms of regions determined to be of interest in the detection of image misfires. The considered algorithms are evaluated based on the prediction accuracy that they achieved on our dataset. The average prediction accuracy of 94.19% is obtained using the random forests approach under cross-validation. Therefore, the application of the proposed approach allows the development of an ‘intelligent’ 3D scanning system which can automatically detect camera misfiring and repeat the scanning process without the need for human intervention.

Role of Background Subtraction in Creating Human Body Point Clouds from Photographs

In this paper we research the influence of background subtraction on photogrammetry pipeline when creating 3D print ready human body data. Background subtraction is a technique in image processing where image background is removed from the image and only foreground is left for further processing. The goal of the paper is to assess whether background subtraction could influence positively or negatively the photogrammetric processing of photographs. The research is aimed at the freely available software that natively does not support background subtraction, but also does not forbid the use of background subtraction. We aim to find out whether the software could benefit from adding background subtraction algorithms into their processing pipelines.