A Machine Vision Apparatus and Method for Can-End Inspection

Chen, Tiejian; Wang, Yaonan; Xiao, Changyan; Wu, Q. M. Jonathan

doi:10.1109/tim.2016.2566442

Cited by 57 publications

(15 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is fitted through experiments, and y height = is substituted into Formula (13) to obtain the actual height of the magnetic ring. Through practical verification, ultimately, the precision of height measurement is about 0.02 mm.…”

Section: Measurement Methods Of Magnetic Ring Heightmentioning

confidence: 99%

“…Tsai and Hsieh [12] proposed a fast image alignment method by using the expectation-maximization (E-M) technique, which accomplished the positioning and defect inspection of printed circuit boards (PCBs). Furthermore, an entropy-rate clustering algorithm combined with prior shape constraint was proposed by Chen [13] to detect defects and deformations across an imaged can-end surface. Ko and Rheem [14] inspected the surface defects of solar wafers by using the local binarization method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Magnetic Ring Multi-Defect Stereo Detection System Based on Multi-Camera Vision Technology

Zhang

Gong

2020

Sensors

View full text Add to dashboard Cite

Magnetic rings are the most widely used magnetic material product in industry. The existing manual defect detection method for magnetic rings has high cost, low efficiency and low precision. To address this issue, a magnetic ring multi-defect stereo detection system based on multi-camera vision technology is developed to complete the automatic inspection of magnetic rings. The system can detect surface defects and measure ring height simultaneously. Two image processing algorithms are proposed, namely, the image edge removal algorithm (IERA) and magnetic ring location algorithm (MRLA), separately. On the basis of these two algorithms, connected domain filtering methods for crack, fiber and large-area defects are established to complete defect inspection. This system achieves a recognition rate of 100% for defects such as crack, adhesion, hanger adhesion and pitting. Furthermore, the recognition rate for fiber and foreign matter defects attains 92.5% and 91.5%, respectively. The detection speed exceeds 120 magnetic rings per minutes, and the precision is within 0.05 mm. Both precision and speed meet the requirements of real-time quality inspection in actual production.

show abstract

Section: Measurement Methods Of Magnetic Ring Heightmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Magnetic Ring Multi-Defect Stereo Detection System Based on Multi-Camera Vision Technology

Zhang

Gong

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Pinhole camera model and lens distortion model of camera calibration is widely used [9,10]. Machine vision-based canend inspection system has been discussed by Chen et al [11] and vision inspection system for beer bottle has been discussed by Duan et al [12]. Feature extraction for fill level and bottle cap inspection in the bottling machine has been proposed by Yazdi et al [13].…”

Section: Figure 1 Flow Of Product In An Assembly Linementioning

confidence: 99%

Design of Automated Visual Inspection System for Beverage Industry Production Line

Padhee¹,

Nandan²

2021

View full text Add to dashboard Cite

This paper provides an overall design and implementation perspective of a laboratory-scale automated visual inspection system for the beverage industry's production line. A case study has been undertaken where the image processing algorithm inspects the beverage bottle for any defects. Different defects such as improper labeling and improper liquid level can be detected using the image processing algorithm. A laboratory prototype of the conveyor belt has been built, and a prototype filling plant has been established to verify the simulation results.

show abstract

“…Visual inspection systems [3] benefit from being nondestructive and intuitive to use, and have received much attention in a variety of industrial settings [4]. They have been applied to aspects of rail inspection (such as track-profile measurement [5], gauge measurement [6], bogie block key inspection [7], fastening elements inspection [8]- [10], and track surface detection [11]) and also to a wide range of very diverse products (such as food cans [12], LCD panels [13], large-aperture optical elements [14], electromechanical parts [15], and film capacitors [16]). This study focuses on a promising and nondestructive system for the particular task of inspecting rail surfaces for discrete defects (RSDDs).…”

Section: Introductionmentioning

confidence: 99%

A Deep Extractor for Visual Rail Surface Inspection

2021

View full text Add to dashboard Cite

Rail surface inspection using a visual inspection system is an important task in the maintenance of railway networks. Recent inspection approaches have attempted to harness low-level features to identify visual defects. These methods' main issues are the limitations of low-level features and prior information about rail surfaces that show a wide variety of visual appearances on dynamic backgrounds. To overcome these problems, we propose a deep extractor (DE) that combines the strengths of fully convolutional networks and conditional random fields (CRFs), so that the deep network can learn the abstract features needed for the specified inspection task. Specifically, motivated by fully convolutional networks, a bilateral fully convolutional network containing two branches is proposed here: one encodedecode branch focuses semantic meaning; the other decode-encode branch encodes information on tiny defects. The two branches are aggregated to obtain a high-level feature map. Furthermore, the mean-field inference of a dense CRF with Gaussian pairwise potentials formulated as a recurrent neural network (CRF-RNN) is introduced to contribute to smoothing constraints and obtaining a fine-grained inspection result. By doing so, it can avoid offline post-processing and further lead the whole deep architecture to achieve end-toend deep learning. Compared with classical approaches, our approach outperforms state-of-art approaches in analyzing two publicly available datasets.INDEX TERMS Rail inspection, computer vision, discrete surface defects, fully convolutional networks, conditional random fields.

show abstract

A Machine Vision Apparatus and Method for Can-End Inspection

Cited by 57 publications

References 19 publications

Magnetic Ring Multi-Defect Stereo Detection System Based on Multi-Camera Vision Technology

Magnetic Ring Multi-Defect Stereo Detection System Based on Multi-Camera Vision Technology

Design of Automated Visual Inspection System for Beverage Industry Production Line

A Deep Extractor for Visual Rail Surface Inspection

Contact Info

Product

Resources

About