Indonesian Journal of Electrical Engineering and Computer Science Vol. 18, No. 2, May 2020, pp. 790~798 ISSN: 2502-4752, DOI: 10.11591/ijeecs.v18.i2.pp790-798  790 Journal homepage: http://ijeecs.iaescore.com Partial pose estimation of 3D rigid object system using outer box method Z. Zulkoffli 1 , Elmi Abu Bakar 2 1 Department of Mechanical and Mechatronic Engineering, UCSI University, Malaysia 2 School of Aerospce Engineering, University Science Malaysia, Malaysia Article Info ABSTRACT Article history: Received Sep 3, 2019 Revised Nov 5, 2019 Accepted Nov 19, 2019 This article introduces a novel approach for identify partial pose estimation using template matching method. The algorithms performs 2D correlation matching on tested image to CAD database by using regional shape representation in order to get the similar object pose in CAD database. The descriptor named outer box method, it is useful for rescale or aligning object size in both different images of tested image and CAD database image and also provide interest point for segmentation in image registration stage. The proposed algorithm were experimentally shown to be robust to apply on scale changes, various complex shape, unstructured CAD database and mixed CAD model database. Last part, the identified pose and its retrieved pose angle was calculated and achi eved high accuracyin range ±0.388˚ to ±1.471˚. Keywords: CAD/CAVI Correlation matching Partial pose estimation Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Zuliani Zulkoffli, Department of Mechanical and Mechatronic Engineering, UCSI University, Jalan Menara Gading 1, Taman Connaught, Kuala Lumpur, Malaysia. Email: Zuliani@ucsiuniversity.edu.my 1. INTRODUCTION Pose estimation is a desired position and orientation of the inspected object before inspection or before robot manipulation task will take place [1]. Technological advancement on product design modelling influenced on product shape complexity [2]. Shape complexity such as free form line, almost symmetrical shape, and product features such as hole, fillet, chamfer brings difficulty on product pose estimation and inspection. This task usually done by dedicated tools, fixtures, and other part presentation devices [3]. The problem with this approach is that it takes undesirable amounts of debug and support time and is sometimes very expensive. By knowing the object pose before inspection will contributes on less time consuming for overall object inspection. External surface of whole object inspection is an essential technology operation in the production line of diverse objects [3, 4]. Although there are many methods proposed for evaluation of partial pose estimation, most of them are sensitive to noise such as shadow and insufficient object internal information especially for almost symmetrical part [2]. To address the problems, we propose a robust global shape representation using threshold binary region shape description with outer box interest point method. This outer box interest points contributes to object rescaling alignment and image registration. Previous study presented various techniques on CAD image database development [5] using .stl data, image data acquisition for surface inspection [6], pre-processing techniques on image registration [7-18], features extraction such as Vote-based 3D shape recognition and registration [19], edges extraction [20], reflection symmetric [21], DoG-based detector presented by deriving scale-invariant mesh features for image registration [22], Local Procustes Regression (LPR) [23], Estimation-by-Completion (EbC) [24] and Customized three-dimensional template matching [25-27] has been conducted. However, issues in pose