Application of image-based acquisition techniques for additive manufacturing using canny edge detection
Publish place: Journal of Computational and Applied Research in Mechanial Engineering، Vol: 10، Issue: 2
Publish Year: 1400
نوع سند: مقاله ژورنالی
زبان: English
View: 290
This Paper With 14 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JCARME-10-2_009
تاریخ نمایه سازی: 11 خرداد 1400
Abstract:
Edge is an indispensable characteristic of an image, defined as the contour between two regions with significant variance in terms of surface reflectance, illumination, intensity, color, and texture. Detection of edges is a basic requirement for diverse contexts for design automation. This study presents a guideline to assign appropriate threshold and sigma values for the Canny edge detector to increase the efficiency of additive manufacturing. The algorithm uses different combinations of threshold and sigma on a color palette, and the results are statistically formulated using multiple regression analysis with an accuracy of ۹۵.۹۳%. An image-based acquisition technique system is designed and developed for test applications to create three-dimensional objects. In addition, a graphical user interface is developed to convert a selected design of a complex image to a three-dimensional object with the generation of Cartesian coordinates of the detected edges and extrusion. The developed system reduces the cost and time of developing an existing design of an object for additive manufacturing by ۲۰% and ۷۰%, respectively.
Keywords:
Authors
Ahalya Ravendran
School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Thammasat University, Pathumthani, Thailand.
Suchada Rianmora
School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Thammasat University, Pathumthani, Thailand.
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :