scholarly journals Approach to Automated Visual Inspection of Objects Based on Artificial Intelligence

2022 ◽  
Vol 12 (2) ◽  
pp. 864
Author(s):  
Ivan Kuric ◽  
Jaromír Klarák ◽  
Vladimír Bulej ◽  
Milan Sága ◽  
Matej Kandera ◽  
...  

The article discusses the possibility of object detector usage in field of automated visual inspection for objects with specific parameters, specifically various types of defects occurring on the surface of a car tire. Due to the insufficient amount of input data, as well as the need to speed up the development process, the Transfer Learning principle was applied in a designed system. In this approach, the already pre-trained convolutional neural network AlexNet was used, subsequently modified in its last three layers, and again trained on a smaller sample of our own data. The detector used in the designed camera inspection system with the above architecture allowed us to achieve the accuracy and versatility needed to detect elements (defects) whose shape, dimensions and location change with each occurrence. The design of a test facility with the application of a 12-megapixel monochrome camera over the rotational table is briefly described, whose task is to ensure optimal conditions during the scanning process. The evaluation of the proposed control system with the quantification of the recognition capabilities in the individual defects is described at the end of the study. The implementation and verification of such an approach together with the proposed methodology of the visual inspection process of car tires to obtain better classification results for six different defect classes can be considered as the main novel feature of the presented research. Subsequent testing of the designed system on a selected batch of sample images (containing all six types of possible defect) proved the functionality of the entire system while the highest values of successful defect detection certainty were achieved from 85.15% to 99.34%.

1990 ◽  
Author(s):  
P. COLEMAN ◽  
S. NELSON ◽  
J. MARAM ◽  
A. NORMAN

2012 ◽  
Vol 190-191 ◽  
pp. 661-665 ◽  
Author(s):  
Chen Huei Hsieh ◽  
Chi Sheng Tsai ◽  
Ting Yu Tseng ◽  
Yi Sheng Wong ◽  
Shi Zhen Zhou

The gap and the malposition of the contact of automotive relay would heavily influence its life. If the gap and the malposition of all relays can be fully inspected and the inspection operation can be incorporated into the existing automated manufacturing and testing equipment, the quality will thus be significantly promoted. To reach this goal, a visual inspection system based on the platform of LabVIEW has been developed in this paper. The visual inspection system is capable of performing the inspection of the gap and the malposition of electrical contact in 1.6 seconds for one relay, and the whole automation system can manufacture one relay for every 2 seconds.


1983 ◽  
Vol PAMI-5 (6) ◽  
pp. 563-572 ◽  
Author(s):  
Bindinganavle R. Suresh ◽  
Richard A. Fundakowski ◽  
Tod S. Levitt ◽  
John E. Overland

2011 ◽  
Vol 201-203 ◽  
pp. 1619-1622
Author(s):  
Qiang Song

This paper is concerned with the problem of automatic inspection of hot-rolled plate surface using machine vision. An automated visual inspection (AVI) system has been developed to take images of external hot-rolled plate surfaces and the detailed characteristics of the sensor system which include the illumination and digital camera are described. An intelligent surface defect detection paradigm based on morphology is proposed to detect structural defects on plate surfaces. The proposed method has been implemented and tested on a number of hot-rolled plate surfaces. The results suggest that the method can provide an accurate identification to the defects and can be developed into a commercial visual inspection system.


1993 ◽  
Vol 24 (6) ◽  
pp. 625-633 ◽  
Author(s):  
Hiroyuki Tsukahara ◽  
Masato Nakashima ◽  
Takehisa Sugawara

Author(s):  
Tatang Rohana Cucu

Pengujian kualitas menggunakan teknik pengolahan citra dan kecerdasan tiruan banyak diterapkan dalam berbagai industri, misalnya industri tekstil, perakitan kendaraan, makanan, minuman, perakitan elektronik, dan lain – lain. Pengujian model ini sering disebut dengan istilah Automated Visual Inspection System (AVIS) atau dalam bahasa Indonesia Sistem Inspeksi Visual Otomatis (SIVO). Penelitian ini mengacu pada model sistem inspeksi, di mana objek pengujiannya adalah keping Printed Circuit Board (PCB). Banyak penelitian tentang pengujian PCB yang sudah dilakukan, tetapi masih banyak yang belum memberikan hasil yang optimum, diantaranya waktu akses yang masih lambat, keakuratan data masih rendah, dan tingkat kesalahan yang masih tinggi. Berdasarkan hasil penelitian dan pengujian yang sudah dilakukan, model ANFIS sangat layak dijadikan sebagai model inferensi kecerdasan buatan dalam sistem yang berbasis inspeksi otomatis khususnya menguji kualitas keping PCB, karena terbukti model ANFIS dengan model hybrid trapesium mf memiliki tingkat kesalahan yang sangat kecil yaitu 4.0186e-007 dan untuk tingkat akurasi pengujian datanya mencapai 99%. 


Sign in / Sign up

Export Citation Format

Share Document