http://irplus.eng.usm.my:8080/ir_plus/viewContributorPage.action;jsessionid=B4F668D11C735A0FCADE88469E09562E?personNameId=4382 Contributor Page for: Zuliani Zulkoffli EngLib USM http://irplus.eng.usm.my:8080/ir_plus/institutionalPublicationPublicView.action;jsessionid=B4F668D11C735A0FCADE88469E09562E?institutionalItemVersionId=5843 Pengenalpastian separa posisi objek diperlukan bagi pemeriksaan objek di industri pembuatan. Ini dapat mengurangkan masa yang diperlukan bagi pemeriksaan keseluruhan objek produk. Pembangunan sistem pengenalpastian separa posisi melibatkan beberapa bahagian utama iaitu perolehan imej data, pra-proses, pemprosesan dan kalibrasi kamera. Perolehan imej data melibatkan dua sumber iaitu data model CAD dan data imej sebenar. Bahagian pra-proses mengandungi penskalaan, segmentasi imej dan pendaftaran imej. Untuk segmentasi imej, kaedah segmentasi pencirian tahap tinggi kotak luar objek dicadangkan. Bagi peringkat pra-proses, pembangunan pengkalan data model CAD menyerupai persekitaran pemeriksaan dijalankan. Objek diwakilkan melalui gabungan luas objek dan garisan sempadan objek. Dengan perwakilan bentuk ini, posisi objek dikenalpasti dengan menghubungkan pengkalan data model CAD kepada imej objek yang diperiksa. Teknik yang dicadangkan untuk pengenalpastian separa posisi yang diuji dan pengkalan data adalah Pernyataan Fourier 1D, Kaedah Jarak Euclidean, Pernyataan Fourier 2D Subspace matrik dan padanan templat. Perolehan pengenalpastian separa posisi objek melalui kaedah padanan templat menunjukkan keputusan yang memuaskan. Objek-objek yang diuji dalam kajian ini adalah objek komponen automotif, bahagian bawah objek komponen automotif, papan Arduino, tetikus computer, objek berlabel dan plak penyambung USB. Kajian menerusi kaedah padanan templat ini diteruskan bagi pengkalan data CAD yang mengandungi 360 imej bagi ujian pengenalpastian separa posisi berketepatan ±1 darjah. Sepuluh ujian pengenalpastian separa posisi dijalankan bagi setiap objek. Kesemua ujian menunjukkan pengenalpastian yang betul dengan skor 10/10 bagi semua objek yang diuji. Purata masa pemprosesan bagi ujian ±1 darjah adalah 1032.6s bagi komponen automotif, bahagian bawah komponen automotif adalah 997.7s, papan Arduino adalah 948.5s, tetikus komputer adalah 150.9s, plak penyambung USB adalah 1198.7s dan komponen automotif berlabel adalah 972.1s. Bagi ujian komponen automotif dihubungkan pengkalan data CAD berterabur pula menemberikan masa purata bagi sepuluh percubaan posisi adalah 974.0s. Seterusnya ujian pengenalpastian posisi dihubungkan kepengkalan data CAD yang mengandungi pelbagai model CAD. Tiga ujian bagi setiap objek dijalankan. Kesemua objek diuji memperolehi skor 3/3 bagi komponen automotif, 3/3 bagi bahagian bawah komponen automotif, 3/3 bagi papan Arduino, 3/3 bagi tetikus komputer dan 3/3 bagi plak penyambung USB. Selanjutnya, pemeriksaan kecacatan objek dilaksanakan dan mendapati pengesanan kecacatan berjaya dikenalpasti. Pendaftaran imej stereo menggunakan kaedah padanan pada titik tengah panjang hipotenus kotak luar objek telah dijalankan bagi objek sebenar dan model CAD. Didapati ujian persamaan antara pendaftaran imej stereo objek sebenar dan model CAD berada dalam julat 81.9% dan 91.8%. __________________________________________________________________________________ Partial pose estimation identification is required for inspection in manufacturing industry. By knowing the partial pose estimation before inspection, overall inspection processing time can be reduced. System development for partial pose estimation identification consists of a few main parts which are image acquisition, pre-processing, processing and camera calibration. Image acquisition is divided into CAD image acquisition and Projection Real Image (PRI) acquisition. Image pre-processing consists of image rescaling, image segmentation and image registration. In image segmentation, high level feature of Outer Box object segmentation method was proposed. In pre-processing development section, the development of CAD model database imitates inspection environment was implemented. The object was represented by the area combined with the edge information of the object. Within this shape representation, partial pose estimation was identified by linking the CAD model database to the inspected object. A few techniques were suggested in pre-processing stage which included 1D Fourier Descriptor, Euclidean Distance, 2D Fourier Descriptor Subspace Matrix and template matching. Partial pose estimation identification using template matching method showed a high performance result. The tested objects were automotive component, bottom automotive component, Arduino board, computer mouse, labelled object and USB connector. Study on template matching was preceded for 360 images CAD model for partial pose estimation identification of ±1 degree accuracy. Ten tests of partial pose estimation were carried out. All the testsshowed the right identification with score 10/10. Average processing time consumption in this ±1 degree accuracy was 1032.6s for automotive component, 997.7s for bottom automotive component, 948.5s for Arduino board, 1198.7s for USB connector and 972.1s for labelled automotive component. For automotive component, partial pose estimation identification linked to random CAD model database gave 974.0s average processing time for ten trials. Then, partial pose estimation identification linked to various CAD models data was studied. Three tests for every object were carried out and gained 3/3 score for automotive component, 3/3 score for bottom automotive component, 3/3 score for Arduino board and 3/3 score for USB connector. After that, study on surface inspection was carried out. Stereo image registration through centre hypotenuse length of outer box method was implemented. The similarity of both CAD stereo image registration and real object stereo image registration resulted in the range of 81.9% to 91.8%. Mon, 02 Mar 2020 16:31:28 +0800 institutional_item_version_id:5843