Copyright © 2018 Authors. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. International Journal of Engineering & Technology, 7 (4.5) (2018) 355-359 International Journal of Engineering & Technology Website: www.sciencepubco.com/index.php/IJET Research paper Shape based Object Retrieval Technique for Vehicular Spare Parts Ravi Hosur 1,* , Dr. Dayanand G Savakar 2 and Shilpa Madabhavi 3 1 Assistant Professor, Computer Science & Engineering Department, BLDEA’s V.P.Dr.P.G.HALAKATTI College of Engg. & Tech., Vijayapur, Karnataka(INDIA) 2 Professor, Department of Computer Science, Dr. P. G. Halakatti Post Graduate Centre, "Vachana Sangama", Rani Channamma University-Toravi, Vijayapur, Karnataka(INDIA) 3 MCA Department, BLDEA's V.P.Dr.P.G.HALAKATTI College of Engg. & TechVijayapur, Karnataka(INDIA) *Corresponding author E-mail:mca.hosur@bldeacet.ac.in Abstract Shape based object retrieval technique is an application used for the automatic retrieval of vehicular spare parts based on the input image, this application can be useful in the automobile industry/shop for the retrieval of specific object from the group of objects. For the re- trieval process first the database has been designed to store different shapes of nuts that are hexagon and square. With the application of median filter and wiener filters in the preprocessing step, the canny edge-detector for identifying the edges and to ascertain shape of the input and database images the convex hull approach is applied. This system is successful in retrieving the shape of the images which already exist in the database and the method results with the accuracy of 82.1875% Keywords: Shape, objects, Vehicular parts, retrieval, automobile, edge. 1. Introduction The shape-based object retrieval system is an application used for automatic retrieval of vehicular spare parts. The automatic retriev- al of the vehicular spare parts in the automobile industry is one of the important needs, because searching of the specific part from the group of the objects consumes more time and energy. The smart system in the automobile industry will be used to separate the different spare parts of the vehicle. Instead of manual search- ing we can make the automatic search by using this application this reduces the human effort and saves time. We can specify the shape based object retrieval technique as the system for fetching the images from the database of the automobile industry/shop, the database consisting of the different images of the vehicular spare parts of different shapes of nuts such as hexagon and square. The earlier image retrieval techniques use the text for the retrieval process, in the text based approach the search is done through keywords which will not provide accurate results. In the later days content based approach has been developed, which work on the observable characters of the image and the characters are color, shape and texture. Among all the three contents important charac- ter for the retrieval process is shape, hence in the proposed work the shape is considered as the one of the important feature for the retrieval of the vehicular objects. For the preprocessing step medi- an filter or wiener filter is used depending on the noise present in the image, then edge based segmentation is performed by using canny-edge detection algorithm. As compared to other edge iden- tification techniques, this approach provides better edges including both strong and weak edges. After applying the canny edge mech- anism it provides the distinct edges which are already exist in the image and then by applying convex hull method the shape is ob- tained from the image. Images which already exist in the database are retrieved when shape of the input and database image are matched. The automatic retrieval of the vehicular spare parts in the automo- bile industry/shop is one of the important needs. Manual searching is the drawback so to overcome that, this application has been designed by considering one of the important content of the im- age, which is shape. The retrieval process is carried out by consid- ering the shape, block diagram and algorithm discussed above show the working procedure of the proposed work 2. Literature Survey [1] Image retrieval can be performed by using different contents of the image like color, texture and shape are used. By observing these contents shape is one of the important content for retrieving the images. In the proposed method image retrieval is done by applying 2-D Fourier transform the Fourier descriptor (FD) is used on the polar shape image. [2] The technique which works on the content of the image treats shape as one of the feature among the other features which are used for retrieval. In the proposed method two important shape descriptors are used for retrieving the shape of the image, the de- scriptors are region based and contour based. By using these pro- cedures retrieval procedure is performed. [3] In the different types of applications like remote sensing, crime prevention, for searching browsing and retrieving the images the different devices are required. Because of this the various ap- proaches are introduced. In the earlier days the text based ap-