An Automated Computer Vision Based System for Bottle Cap Fitting Inspection

Kulkarni, Rutwik; Kulkarni, Sourav; Dabhane, Shardul; Paswan, Roshan

doi:10.1109/ic3.2019.8844942

Cited by 15 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pentingnya mendeteksi kesalahan yang terjadi sesegera mungkin. Penelitian ini membahsa sistem otomatis dimana cacat pada tutup botol dapat diidentifikasi menggunakan teknologi computer vision (Kulkarni, dkk, 2019). Semakin berkembangnya teknologi AI, otomatisasi dalam aktifitas kehidupan menjadi semakin maju salah satunya menggunakan teknologi computer vision (Song, 2020).…”

Section: Pendahuluanunclassified

Optimasi Teknologi Computer Vision pada Robot Industri Sebagai Pemindah Objek Berdasarkan Warna

MASRIL¹,

CANIAGO²

2023

ELKOMIKA

View full text Add to dashboard Cite

ABSTRAKComputer vision merupakan teknologi yang dapat mendeteksi objek yang ada disekitarnya pada penelitian ini membahas optimasi teknologi computer vison pada robot sebagai pemindah objek berdasarkan warna. Sistem pada robot terdiri dari pengenalan bola berwarna dan memindahkan bola berwarna sesuai dengan warna yang dideteksi. Teknologi computer vision pada pixy 2 camera dapat mendeteksi objek berwarna menggunakan metode deteksi real-time dengan hasil optimasi yang tinggi yaitu 0,2 detik ketika mendeteksi objek berwarna. Pengujian pengenalan objek berwarna dilakukan sebanyak tiga kali pada setiap objek berwarna dengan tingkat akurasi sebesar 100%. Optimasi computer vision dapat membantu robot mengenali objek berwarna.Kata kunci: Computer Vision, Deteksi Objek Berwarna, Pixy2 Camera, Real-Time ABSTRACTComputer vision is a technology that can detect objects that are around it. This study discusses the optimization of computer vision technology on robots as object transfers based on color. The system on the robot consists of recognizing colored balls and moving colored balls according to the detected color. Computer vision technology on the pixy 2 camera can detect colored objects using a real-time detection method with a high optimization result of 0.2 seconds when detecting colored objects. The color object recognition test was carried out three times on each colored object with an accuracy rate of 100%. Computer vision optimization can help robots recognize colored objects.Keywords: Computer Vision, Color Object Detection, Pixy2 Camera, Real-Time

show abstract

Section: Pendahuluanunclassified

Optimasi Teknologi Computer Vision pada Robot Industri Sebagai Pemindah Objek Berdasarkan Warna

MASRIL¹,

CANIAGO²

2023

ELKOMIKA

View full text Add to dashboard Cite

show abstract

“…The central server receives the image information transmitted from the edge and executes the appropriate algorithm to distinguish the qualified and defective products and detect the positive or negative sides of the bottle caps. Then, the server sends the instructions to the actuators near the production line, and the actuators complete the operations such as turning over the caps or rejecting the unqualified defective products according to the instructions [21,22].…”

Section: Introductionmentioning

confidence: 99%

Design of Hardware Acceleration in Edge Computing Device for Bottle Cap High-Speed Inspection

Liu

Peng

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

High-speed product appearance inspection is crucial for modern automated industrial production such as bottle caps. The main detection method is to capture the image of bottle caps on the high-speed conveyor belt by industrial cameras and send them to the server through edge devices for various analyses. In order to improve production efficiency, it is necessary to increase the inspection rate of bottle caps. However, the transmission rate and huge data throughput of traditional inspection methods limit the inspection rate. Because of the application requirements for improving bottle cap detection efficiency, this paper proposes a hardware acceleration design based on edge devices to improve the bottle cap detection rate significantly. In this paper, an image processing module based on FPGA is designed as the edge device, improving algorithm execution speed through pipeline processing. It realizes the edge detection of the bottle cap and the fast detection of the front or back states and can send the instructions to the actuator to correct it in time when the back bottle cap is detected. It also realizes the positioning of the bottle cap area and cuts the image. Thereby, the amount of data sent to the server is significantly reduced. We have done both functional simulation and hardware implementation. Comparing with the pure software solution, the proposed design reduces the execution time of the algorithm from 16 ms to 3.07 ms, which achieves a more than four times rate increase. The amount of data that needs to be transmitted to the server per second is reduced from 7200 Kb is reduced to 25 Kb, which reduces the transmission capacity and server cache space by more than 280 times compared to the original image. In this paper, the hardware acceleration design of edge devices and the positioning and cropping of original images can greatly reduce the transmission pressure, data calculation pressure, and buffer space requirements of the central server and improve the detection rate. This design can not only be used for bottle cap inspection but also for various machine vision fields, such as defect detection of other workpieces.

show abstract

“…This paper uses computer vision techniques which are used wildly to auto arrange tasks for varsity applications such as component identification, inspection, quality control and license plate recognition. (Cardona, 2016) (Kulkarni et al, 2019) (Ugwu et al, 2022) as well as, using for optical character recognition (OCR) and pattern recognition. (Barik & Mondal, 2010) There are several approaches have been used of computer vision to detect Multiple Choice Question MCQ answer, Abbas proposed 15 questions with answer sheet must not be rotated by 45 degrees and use rectangle for options , as he claimed some of student has a difficult to black answer (Abbas, 2009), Chinnasarn and Rangsanseri are used a histogram technique to detect answer by checking four options, then the highest black pixel on the answer is considered to be selected answer (Chinnasarn & Rangsanseri, 1999), Yimyam and Ketcham use mobile device to capture answer sheet and can obtain result of accuracy 96 (Yimyam & Ketcham, 2018), Spadaccini and Rizzo use existing framework from python library named Gamera framwork to analyze scanned document with cross over answer and he can obtain over 99% on recognition (Spadaccini & Rizzo, 2011).…”

Section: Introductionmentioning

confidence: 99%

Evaluate Response of Peach Fruits to Coating Treatments during Cold Storage

Salih

2022

UOD

View full text Add to dashboard Cite

The process of evaluating students’ answers is a time consuming and effort for teachers, therefore, based on this, Grading Multiple Choice Questions (G-MCQ) is proposed to auto-marking answer without human interaction. All the human does, is to use digital camera without using expensive ordinary document scanner and machine-read for this purpose, then, evaluating and marking each correct answer is algorithm duty. G-MCQ is based on a prepared bubble sheet that contains (54) questions with four circles options for each question, G-MCO is programmed using Python programming language, passes three main process , the first one, is a preparation of scanned document, then, second one, is to detect bookmarks, First Question Bookmark (FQB), Questions Bookmarks (QB) and Options Bookmarks (OB) positions, based on detecting FQB, QB and OB, the final one is started to detect answers which are circles positions of each question from instructor. The algorithm is tested with input images with PNG and JPG format, the result of detecting of accuracy is about 99%

show abstract

An Automated Computer Vision Based System for Bottle Cap Fitting Inspection

Cited by 15 publications

References 6 publications

Optimasi Teknologi Computer Vision pada Robot Industri Sebagai Pemindah Objek Berdasarkan Warna

Optimasi Teknologi Computer Vision pada Robot Industri Sebagai Pemindah Objek Berdasarkan Warna

Design of Hardware Acceleration in Edge Computing Device for Bottle Cap High-Speed Inspection

Evaluate Response of Peach Fruits to Coating Treatments during Cold Storage

Contact Info

Product

Resources

About