Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : JRSI (Jurnal Rekayasa Sistem dan Industri)

Design and Development Classifications A Defect in Clay Tiles Using A Method of Support Factor Machine (SVM) Rais Yufli Xavierullah; Murman Dwi Prasetio; Denny Sukma Eka Atmaja
Jurnal Rekayasa Sistem & Industri Vol 7 No 02 (2020): Jurnal Rekayasa Sistem & Industri
Publisher : School of Industrial and System Engineering, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jrsi.v7i2.420

Abstract

Quality control is a system that can assist a company in maintaining and maintaining product quality sothat product defects do not occur. PT. XYZ is a company in the clay tile industry. Every month, PT. XYZhas products due to defects with an average of 2225 precarious. One of the problems that occurred at PT.XYZ is an inspection process that only uses sight. The use of sight can carry the risk of increased operatingcosts due to faulty examinations, failure to get business, and rework. With the development of technology,it can overcome this problem by finding artificial detectors using measurement methods, imagepreprocessing, and algorithms to detect defect. In this study using the Support Vector Machine (SVM)method in classifying defects. Taking pictures directly in this study using raspberry pi and making thealgorithm system using pyhton software. This study uses a linear kernel in the SVM algorithm. The resultsin this study concluded that the highest accuracy rate was 88.6% using a linear kernel.
Object/Product Identification for Stock Taking Activities using Object Recognition Concept Muhammad Nashir Ardiansyah; Prafajar Sukssesanno Muttaqin; Murman Dwi Prasetio; Nia Novitasari
Jurnal Rekayasa Sistem & Industri Vol 8 No 01 (2021): Jurnal Rekayasa Sistem & Industri
Publisher : School of Industrial and System Engineering, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25124/jrsi.v8i1.455

Abstract

Stock taking activity is as a routine product inspection activity to check the inventory accuracy and helpreduce the risks of stealing, damage, and obsolete inventories. This activity can be categorized as timeconsuming and expensive activity. In addition, this activity needs a lot of concentration and prone tohuman errors and mistakes. This study aims to replace human manual inspection in terms of object typeand quantity with objects identification to reduce errors, time, and costs. Digital image processing in theform of Object Recognition is used in this study to determine the type of object and the number of objects.The results showed that the detection rate of a single product reached 90% which was influenced by theangle of an image and the detection rate of object quantity reaches 81% in average in real environmentwith a certain condition. It is expected that costs of inventory inspection and warehousing activities can bereduced, as well as the improvement in terms of efficiency and effectiveness can be achieved.