EREL-Net: A Remedy for Industrial Bottle Defect Detection

Patel, Nirmal; Mukherjee, Subhayan; Ying, Lihang

doi:10.1007/978-3-030-04375-9_39

Cited by 9 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It addresses challenges in visual inspection through innovative image capture techniques and proposes a heuristic segmentation method for border extraction. Additionally, it evaluates an integrated approach that combines machine learning and post-processing methods, tested on real samples [8,35], saliency detection of the glass bottle bottom [36], empty or fills bottle [37][38], port defects [39], bottle wall and bottle bottom [12], edge computing for logistics packaging box [40], bottle surface [41][42] and plastic bottle inspection on the seated cap, vials on the body dimensional [35], label alignment and surface defects [43][44]. Packaging liquid products in plastic and glass bottles stands out as one of the globally favored methods, extensively employed in the food and pharmaceutical sectors [45][46].…”

Section: Introductionmentioning

confidence: 99%

Machine Vision for Detecting Defects in Liquid Bottles: An Industrial Application for Food and Packaging Sector

Omid Farhangi,

Ehsan Sheidaee,

Asma kisalaei

2024

Cloud Computing and Data Science

View full text Add to dashboard Cite

The quality control of liquid packaging, such as cooking oils and beverages (bottled water, soft drinks, juices, etc.), is crucial due to the inherent risk of leakage. This process involves inspecting bottles for cap and seal ring defects and addressing issues arising from the gradual degradation of filling machines, leading to variations in the surface level of liquid bottles over time. Additionally, proper label placement significantly contributes to the customer-friendliness of a product. This research aims to introduce an automated vision-based rating system designed for the online inspection of defects in liquid bottles. The system is versatile, applicable to both academic and industrial settings, and can be easily adapted for use with various types of transparent liquid bottles. The defect detection metrics include three measures of distance determination and pattern matching. The equipment used in this study includes a Complementary Metal Oxide Semiconductor (CMOS) camera with a USB connection, a laptop, and a 14-speed conveyor belt, among other components. The system demonstrated an average accuracy of 95.6%, with specific accuracies for surface level, cap, and label placement at 100%, 95%, and 92%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Vision for Detecting Defects in Liquid Bottles: An Industrial Application for Food and Packaging Sector

Omid Farhangi,

Ehsan Sheidaee,

Asma kisalaei

2024

Cloud Computing and Data Science

View full text Add to dashboard Cite

show abstract

“…A series of deep learning-based methods or models after nondestructive object detection tasks have been developed in agricultural production management in which the convolutional neural network (CNN) framework, represented by Faster R-CNN [13] and YOLO [14], is undoubtedly the most widely adopted for these kinds of tasks. In addition to the two types of frameworks, some scholars have also proposed detection and classification networks based on CNN such as Erel-net, which can detect and classify product defects with a classification accuracy of 77% [15]. Compared to traditional machine vision techniques, deep learning-based methods are more likely to solve complex practical problems that would challenge the use of traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Detection of Dense Citrus Fruits by Combining Coordinated Attention and Cross-Scale Connection with Weighted Feature Fusion

et al. 2022

View full text Add to dashboard Cite

The accuracy detection of individual citrus fruits in a citrus orchard environments is one of the key steps in realizing precision agriculture applications such as yield estimation, fruit thinning, and mechanical harvesting. This study proposes an improved object detection YOLOv5 model to achieve accurate the identification and counting of citrus fruits in an orchard environment. First, the latest visual attention mechanism coordinated attention module (CA) was inserted into an improved backbone network to focus on fruit-dense regions to recognize small target fruits. Second, an efficient two-way cross-scale connection and weighted feature fusion BiFPN in the neck network were used to replace the PANet multiscale feature fusion network, giving effective feature corresponding weights to fully fuse the high-level and bottom-level features. Finally, the varifocal loss function was used to calculate the model loss for better model training results. The results of the experiments on four varieties of citrus trees showed that our improved model proposed to this study could effectively identify dense small citrus fruits. Specifically, the recognized AP (average precision) reached 98.4%, and the average recognition time was 0.019 s per image. Compared with the original YOLOv5 (including deferent variants of n, s, m, l, and x), the increase in the average accuracy precision of the improved YOLOv5 ranged from 7.5% to 0.8% while maintaining similar average inference time. Four different citrus varieties were also tested to evaluate the generalization performance of the improved model. The method can be further used as a part in a vision system to provide technical support for the real-time and accurate detection of multiple fruit targets during mechanical picking in citrus orchards.

show abstract

“…More recently, though, in order to provide cost-efficient solutions, the related literature has been focused on identifying an object's pose through single image instances, which can be acquired by monocular sensors [16]. This is achieved by either using Structure from Motion techniques via frames captured during different time instances [17,18], or through DL methods [9,[19][20][21][22], which can identify the full pose or representative local points of a given object.…”

Section: Introductionmentioning

confidence: 99%

A Product Pose Tracking Paradigm Based on Deep Points Detection

2021

View full text Add to dashboard Cite

The paper at hand presents a novel and versatile method for tracking the pose of varying products during their manufacturing procedure. By using modern Deep Neural Network techniques based on Attention models, the most representative points to track an object can be automatically identified using its drawing. Then, during manufacturing, the body of the product is processed with Aluminum Oxide on those points, which is unobtrusive in the visible spectrum, but easily distinguishable from infrared cameras. Our proposal allows for the inclusion of Artificial Intelligence in Computer-Aided Manufacturing to assist the autonomous control of robotic handlers.

show abstract

EREL-Net: A Remedy for Industrial Bottle Defect Detection

Cited by 9 publications

References 9 publications

Machine Vision for Detecting Defects in Liquid Bottles: An Industrial Application for Food and Packaging Sector

Machine Vision for Detecting Defects in Liquid Bottles: An Industrial Application for Food and Packaging Sector

Detection of Dense Citrus Fruits by Combining Coordinated Attention and Cross-Scale Connection with Weighted Feature Fusion

A Product Pose Tracking Paradigm Based on Deep Points Detection

Contact Info

Product

Resources

About