Quality Control of PET Bottles Caps with Dedicated Image Calibration and Deep Neural Networks

Abstract

Product quality control is currently the leading trend in industrial production. It is heading towards the exact analysis of each product before reaching the end customer. Every stage of production control is of particular importance in the food and pharmaceutical industries, where, apart from visual issues, additional safety regulations are demanded. Many production processes can be controlled completely contactless through the use of machine vision cameras and advanced image processing techniques. The most dynamically growing sector of image analysis methods are solutions based on deep neural networks. Their major advantages are fast performance, robustness, and the fact that they can be exploited even in complicated classification problems. However, the use of machine learning methods on high-performance production lines may be limited by inference time or, in the case of multiformated production lines, training time. The article presents a novel data preprocessing (or calibration) method. It uses prior knowledge about the optical system, which enables the use of the lightweight Convolutional Neural Network (CNN) model for product quality control of polyethylene terephthalate (PET) bottle caps. The combination of preprocessing with the lightweight CNN model resulted in at least a five-fold reduction in prediction and training time compared to the lighter standard models tested on ImageNet, without loss of accuracy.

Endoscopic image recognition method of gastric cancer based on deep learning model

“…In 2006, Professor Hinton from the University of Toronto in Canada proposed the concept of DL (Lecun et al, 2019). Since then, DL has continuously made breakthroughs in computer vision and other fields (Black et al, 2019; Malesa & Rajkiewicz, 2021; Ponti et al, 2017; Kohlhepp, 2020; Xiang & Yanwei, 2020; Ioannidou et al, 2017). In recent years, DL algorithms have been applied in various fields, especially in the medical field (Greenspan et al, 2016; Nogales et al, 2021; Alden et al, 2020; Zhang & Dong, 2020).…”

Deep Neural Network Model-Assisted Reconstruction and Optimization of Chinese Characters in Product Packaging Graphic Patterns and Visual Styling Design

“…Compared to manual inspection, machine vision has great advantages in terms of speed and accuracy. Reference [21] used Blob Analysis on a smart camera to detect missing bottles and breaks in the packaging of specific colour Chinese characters; [22] used Speeded Up Robust Feature (SURF) with a support vector machine (SVM) to detect defects.…”

“…To compare the performance of this network with that of the reference network, two control groups were set up: one was the original MobileNetv2 with an input size of 224 × 224 × 3, and the other was this network (LocalNet_224) with an input size of 224 × 224 × 3. All three sets of experiments were trained using Stochastic Gradient Descent (SGD) [17], and the learning rate was adjusted using a cosine annealing strategy [18], as shown in Figure 12(a), with an initial learning rate of 0.1, a minimum learning rate of 1 × 10 −8 , a momentum factor of 0.9, and a weight decay factor of 0.0003. e original MobileNetv2 network converged the fastest with a stable loss of 0.004, Local Net converged the second fastest with a stable loss of 0.005, and LocalNet_224 converged the slowest with a To verify the classification performance of the networks in this article, tests were evaluated on the test set constructed above, and a test control experimental group was also set up, including two lightweight networks-ShufflENetv2 [19] and Squeeze Net [20]-and two machine learning methods-Local Binary Pattern (LBP) [21] feature-based SVM and Extreme Learning Machine (ELM) [22]. e control group was pretrained on the training set.…”

A Survey on Machine Learning based Smart Maintenance and Quality Control Solutions

“…Moreover, it can be applied in dynamic environments that often change because it is contactless; while numerous methods based on sensing require some sort of physical interaction, therefore they are less flexible or not flexible at all. Nonetheless, image processing is almost always slower than applying binary classification (including inference and training time) purely based on sensor or telemetric data; therefore, the applicability of this technique in the case of fast, high-throughput assembly or production lines is limited [58], [59].…”

“…However, image processing is usually a computation heavy task; therefore, in certain cases, it can be beneficial to apply prior knowledge to increase the system's performance. The authors of [59] designed and implemented a Convolutional Neural Network-based quality control system for PET bottle caps, which system is supported by image calibration to enable using a custom, lightweight architecture. In spite of that, not so customizable CV frameworks that enable fast prototyping are extremely popular in OQC systems: e.g., a well-known one is the "You only look once" (YOLOv3) [61].…”