Automated Real-Time Vision Quality Inspection Monitoring System

Rahman, Nor Nabilah Syazana Abdul; Saad, Norhashimah Mohd; Abdullah, Abdul Rahim; Hassan, Mehdi; Basir, Muhammad Sufyan Safwan Mohamad; Noor, N. S. M.

doi:10.11591/ijeecs.v11.i2.pp775-783

Cited by 6 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pre-processing stage is then computed in order to normalize the image [16], improve the image intensity [17], suppress the unwanted distortion and enhance the features [18]. The process involved converting the sample images of RGB components to HSV representations [19].…”

Section: Image Acquisition and Pre-processing Stagementioning

confidence: 99%

Automated vision based defect detection using gray level co-occurrence matrix for beverage manufacturing industry

Saad

Abdullah

Hasan

et al. 2021

IJ-AI

View full text Add to dashboard Cite

Defect inspection emerged as an important role for product quality monitoring process since it is a requirement of International Organization for Standardization (ISO) 9001. The used of manual inspection is impractical because of time consuming, human error, tiredness, repetitive and low productivity. Small and medium enterprises (SMEs) are industries that having problems in maintaining the quality of their products due to small capital provided. Therefore, automatic inspection is a promising approach to maintain product quality as well as to resolve the existing problems related to delay outputs and cost burden. This article presents a computerized analysis to detect color concentration defects that occur in beverage production based on texture information provided by gray level co-occurrence matrix (GLCM). Based on the texture information, GLCM cross-section is computed to extract the parameters for features of color concentration. The distance value between two colors is then computed using co-occurrence histogram. The defect results either pass or reject is determined using Euclidean distance and rule-based classification. The experimental results show 100% accuracy which makes the proposed technique can implimented for beverage manufacturing inspection process.

show abstract

Section: Image Acquisition and Pre-processing Stagementioning

confidence: 99%

Automated vision based defect detection using gray level co-occurrence matrix for beverage manufacturing industry

Saad

Abdullah

Hasan

et al. 2021

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Efficient quality inspection is one of the cornerstones of successful manufacturing companies. Since human visual inspection is error-prone and subjective, there has been a movement towards automatic defect detection systems [1], more than that, recently we witness the transition to the era of quality 4.0, which we can define as a mature quality system that sought to leverage industry 4.0 technologies. In fact artificial intelligence and machine learning [2] had proven their abilities to perform quality inspection [3].…”

Section: Introductionmentioning

confidence: 99%

Product defect detection based on convolutional autoencoder and one-class classification

Chaabi¹,

Hamlich²,

Garouani³

2023

IJ-AI

View full text Add to dashboard Cite

To meet customer expectations and remain competitive, industrials try constantly to improve their quality control systems. There is hence increasing demand for adopting automatic defect detection solutions. However, the biggest issue in addressing such systems is the imbalanced aspect of industrial datasets. Often, defect-free samples far exceed the defected ones, due to continuous improvement approaches adopted by manufacturing companies. In this sense, we propose an automatic defect detection system based on one-class classification (OCC) since it involves only normal samples during training. It consists of three sub-models, first, a convolutional autoencoder serves as latent features extractor, the extracted features vectors are subsequently fed into the dimensionality reduction process by performing principal component analysis (PCA), then the reduced-dimensional data are used to train the one-class classifier support vector data description (SVDD). During the test phase, both normal and defected images are used. The first two stages of the trained model generate a low-dimensional features vector, whereas the SVDD classifies the new input, whether it is defect-free or defected. This approach is evaluated on the carpet images from the industrial inspection dataset MVTec anomaly detection (MVTec AD). During training, only normal images were used. The results showed that the proposed method outperforms the state-of-the-art methods.

show abstract

“…The multivariate analysis method was combined with machine vision for testing rice seed varieties with a success rate above 83% [5]. In the soft drink bottle industry, color classification and Available online at: http://e-jurnal.lppmunsera.org/index.php/JSMI Jurnal Sistem dan Manajemen Industri ISSN (Print) 2580-2887 ISSN (Online) 2580-2895 level checks have been successfully detected by automatic vision checks using a raspberry pi as a controller [6]. The same thing is done for bottle companies by conducting automatic visual inspections to detect defects and locations.…”

Section: Introductionmentioning

confidence: 99%

Design and implementation of intelligent electronic component inspection based on PLC and vision system

Ikatrinasari,

Herlambang,

Kosasih

2023

j. sist. manaj. ind.

View full text Add to dashboard Cite

Customer demands for product quality are increasingly complex, requiring better inspection accuracy. It is not enough if done manually because it requires high costs and varying operator accuracy. Automatic vision inspection was developed to check the product quality of terminal-type electronic components To solve this problem. Design intelligent inspection uses a conveyor driven by a stepper motor, a photosensor to calculate product distance, guides position to direct the product, a vision camera to detect product quality, cylinder ejection for product selection, and PLC as a control system. The process of detecting normal and abnormal product quality is carried out using computer logic control, then separating the abnormal product into the reject box through the ejection cylinder. The machine speed is 60 pieces/minute. The system evaluation results are carried out on three parts of the system: the success rate on the vision camera is 100%, automatic product sorting through the cylinder ejection rate success is 100%, and the success rate for product positioning is 97.5%. This research provides a useful reference for developing intelligent automatic inspection technology in electronic components.

show abstract

Automated Real-Time Vision Quality Inspection Monitoring System

Cited by 6 publications

References 12 publications

Automated vision based defect detection using gray level co-occurrence matrix for beverage manufacturing industry

Automated vision based defect detection using gray level co-occurrence matrix for beverage manufacturing industry

Product defect detection based on convolutional autoencoder and one-class classification

Design and implementation of intelligent electronic component inspection based on PLC and vision system

Contact Info

Product

Resources

About