IS&T | Library

CAPT 2024 Latest Innovations on Printing and Packaging Technologies

Abstract

The bearing vibration fault monitoring of advanced printing systems is crucial for ensuring system reliability, improving print quality, and enhancing production efficiency. In consideration of the high noise and strong interference attributes of bearing vibration signals of printing equipment caused by complex environmental factors, the original data noise interference is suppressed by a diagnostic approach for rolling bearing vibration signal faults combined Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Dung Beetle Optimization-Support Vector Machine (DBO-SVM) proposed in this article. This method suppresses noise interference in the original data by decomposing and reconstructing vibration signals, and innovatively proposes the DBO-optimized SVM to address the problems of poor anti-interference ability and weak generalization ability of a single intelligent diagnostic method, effectively improving the fault diagnosis rate. First, the decomposition by CEEMDAN effectively overcomes the difficulties of modal aliasing and significant reconstruction errors found in traditional empirical mode decomposition (EMD). The optimal component reconstruction strategy considering the Correlation Coefficient and the Variance Contribution Rate is designed to obtain the vibration signal after noise reduction. Second, to effectively avoid the limitation of heavily relying on expert experience for hyperparameter adjustment, a DBO-SVM model is constructed utilizing a heuristic beetle optimization algorithm, dynamically optimizing the key kernel function parameters and penalty factors of SVM. Finally, the algorithm’s performance was tested using public datasets and self-tested data from Case Western Reserve University. The results indicate that the proposed approach achieves greater diagnostic accuracy and exhibits robust generalization.

Digital Library: JIST

FastTrack Article

6 0

Research on Multi-objective Static Scheduling of Intelligent Printing Workshop based on Learning Effect

intelligent printing workshop
production scheduling
static scheduling
improved NSGA-II algorithm

Linlin Liu, Chenglin Zhao, Shengjie Liu, Ke Lin, Ji Lu, Guangshun Nie, Yaping Zheng

Pages 1 - 8, © Society for Imaging Science and Technology 2025

DOI

10.2352/J.ImagingSci.Technol.2025.69.3.030418

ACDM 2024 Digital Media Special Issue

Abstract

In traditional printing enterprises, production scheduling is highly complex. This is due to the wide variety of products, scattered processes, uneven automation levels, frequent changes in plans, and low standardization. These factors turn scheduling into a multi-objective optimization problem with multiple constraints. Based on flexible demand for production scheduling in an intelligent printing workshop, this study integrates the learning effect of production personnel with the static scheduling problem found in printing workshops. Under the constraints of resource, operation, and process layers, this study establishes a multi-objective static scheduling optimization model for printing workshops, with the goals of minimizing the penalties for makespan of orders, total load time of equipment, maximum load time of bottleneck equipment, total production cost of orders, total quality failure rate of orders and total order delay/early completion time; and proposes an improved NSGA-II algorithm that is suitable for solving complex large-scale scheduling problems existing in printing workshops. The effectiveness and rationality of design model and algorithm are verified by combining with Kacem dataset, Brandimarte standard examples and actual enterprise cases.

Digital Library: JIST

FastTrack Article

3 0

6D Pose Estimation based on High-Resolution Heatmap Regression for Virtual and Reality Fusion Interaction

virtual reality
6D pose estimation

Xinyan Yang, Ying Ma, Feiran Sun, Yinghao Yang, Long Ye

Pages 1 - 10, © Society for Imaging Science and Technology 2025

DOI

10.2352/J.ImagingSci.Technol.2025.69.1.010414

Abstract

During the process of virtual and reality fusion interaction, accurately estimating and mapping real-world objects to their corresponding virtual counterparts is crucial for enhancing the overall interaction experience. This paper focuses on studying the pose estimation of real-world targets within this fusion context. To address the challenge of achieving precise pose estimation from single-view RGB images captured by basic devices, a high-resolution heatmap regression method is proposed. This algorithm strikes a balance between accuracy and complexity. To tackle issues stemming from inadequate utilization of semantic information in feature maps during heatmap regression, a lightweight upsampling method based on content awareness is introduced. Additionally, to mitigate resolution and accuracy loss due to quantization errors during pose calculation caused by predicted keypoints on the heatmap, a keypoint optimization module incorporating Gaussian dimensionality reduction and pose estimation strategy based on high-confidence keypoints is presented. Quantitative experimental results demonstrate that this method outperforms comparative algorithms on the LINEMOD dataset, achieving an accuracy rate of 85.7% based on the average distance index. Qualitative experiments further illustrate the successful achievement of precise real-to-virtual space pose estimation and mapping in interactive scene applications.

Digital Library: JIST

FastTrack Article

Enhancing Compound Emotion Recognition via Ensemble Representation Learning

8 0

deep neural networks
ensemble model
compound emotion recognition
deep learning

Sana Ullah, Guangyao Zhou, Jie Ou, Zhaokun Wang, Wenhong Tian

Pages 1 - 13, © Society for Imaging Science and Technology 2025

DOI

10.2352/J.ImagingSci.Technol.2025.69.4.040501

CAPT 2024 Latest Innovations on Printing and Packaging Technologies

Abstract

Innovations in computer vision have steered research towards recognizing compound facial emotions, a complex mix of basic emotions. Despite significant advancements in deep convolutional neural networks improving accuracy, their inherent limitations, such as gradient vanishing/exploding problem, lack of global contextual information, and overfitting issues, may degrade performance or cause misclassification when processing complex emotion features. This study proposes an ensemble method in which three pre-trained models, DenseNet-121, VGG-16, and ResNet-18 are concatenated instead of utilizing individual models. It is a significant layer-sharing method, and we have added dropout layers, fully connected layers, activation functions, and pooling layers to each model after removing their heads before concatenating them. This enables the model to get a chance to learn more before combining the individual learned features. The proposed model uses an early stopping mechanism to prevent it from overfitting and improve performance. The proposed ensemble method surpassed the state-of-the-art (SOTA) with 74.4% and 71.8% accuracy on RAF-DB and CFEE datasets, respectively, offering a new benchmark for real-world compound emotion recognition research.

Digital Library: JIST

FastTrack Article

5 0

Study on the Preparation of Oxidized Nanocellulose with Cationic Guar Gum Hydrogel Coated Paper and its Properties

oxidized nanocellulose
cationic guar gum
coated paper
barrier properties

Yong Lv, Ci Song, Lei Dai, Yu Meng

Pages 1 - 9, © Society for Imaging Science and Technology 2025

DOI

10.2352/J.ImagingSci.Technol.2025.69.3.030412

Abstract

In order to meet societal needs for green packaging and improve the barrier performance of paper packaging materials, oxidized cellulose nanofibrils (OCNF) were prepared via oxidization of cellulose nanofibrils (CNF) with sodium periodate. Complex hydrogels were fabricated by compounding OCNF with cationic guar gum (CGG). OCNF/CGG hydrogel was used to coat the base paper. The water vapor barrier and oil resistance properties of the coated paper were evaluated. Inkjet and electrostatic color printers were employed to evaluate the digital printability of the coated paper. Results showed that there was a cross-linking reaction between OCNF and CGG during OCNF/CGG hydrogel fabrication process. When OCNF content was increased in OCNF/CGG hydrogel, the water vapor permeability (WVP) of the coated paper first increased and then decreased at the same coating weight. Experimental data determined that the best water vapor barrier and oil resistance performance was when the ONCF content was 0.4 wt%. The highest oil resistance index value obtained was 12. The oxygen transmission rate (OTR) reached 4.84 cm³/(m² ⋅ 24 h ⋅ atm), which exceeded that of common plastic packaging films such as PET and PA. Furthermore, inkjet printing had a greater color gamut and tone reduction performance for OCNF/CGG hydrogel coated on base paper. The coated paper sized by OCNF/CGG hydrogel met the basic proofing requirements for digital printing has broad application prospects in the field of personalized packaging materials and labels.

Digital Library: JIST

FastTrack Article

Multi-view Cupping Spots Image Stitching Algorithm based on Canny SIFT

7 0

cupping spot
Canny SIFT algorithm
splicing
matching

Zhu Mengyan, Qin Jianhua, Li Xi, Zeng Guifen, Xu Baolin

Pages 1 - 7, © Society for Imaging Science and Technology 2025

DOI

10.2352/J.ImagingSci.Technol.2025.69.2.020511

CAPT 2024 Latest Innovations on Printing and Packaging Technologies

Abstract

This study proposes a multi-view cupping spots image stitching method based on Canny SIFT to address issues such as limited field of view and unclear details of cupping spots during automatic cupping process. First, the image is preprocessed using bilateral filtering, and Canny edge detection is introduced to generate feature descriptors in combination with SIFT feature extraction algorithm. Then, RANSAC algorithm is utilized to screen and eliminate the mismatched feature points in order to obtain the optimal perspective transformation matrix. Finally, the weighted average fusion algorithm and morphological operations are combined to realize the multi-view cupping spots image splicing. Experimental results show that the algorithm proposed in this study improved the accuracy of feature matching for cupping spots images by 5% and 26% compared with the traditional SIFT and ORB algorithms, respectively. Moreover, the splicing speed also improved by 63%. The proposed method not only extracts more stable feature points, but also deals better with the problem of detailed features after fusion due to its improved splicing speed and quality.

Digital Library: JIST

FastTrack Article

40 0

Class-Aware Visual Prompt Learning for Vision Language Models

vision-language models
visual prompt learning
few-shot learning

Sihui Zhang, Zhijiang Li

DOI

10.2352/J.ImagingSci.Technol.2025.69.3.030415

Abstract

Vision-language pre-trained (VLP) models, such as CLIP, have exhibited remarkable performance in downstream tasks with excellent generalization capabilities. Meanwhile, textual and visual prompt learning have been widely adopted to enhance VLP model performance in downstream tasks. However, a challenging issue in visual prompt learning is the inferior ability on few-shot recognition tasks, the inability to capture specific class information. Thus, we propose a class-aware visual prompt learning method to enhance the perceptual abilities of VLP model with an independent class prompting module, which consists of trainable prompts for each class. As class-aware prompts tend to be inaccurate in the training process, we developed an intra-class compactness loss and inter-class dispersion loss to enhance the intra-class consistency. Finally, we introduced attention-based adapter layers to tackle the prompt selection issue. Extensive experiments demonstrated that our method achieved superior efficiency and effectiveness, surpassing previous visual prompting methods in a series of downstream datasets.

Digital Library: JIST

FastTrack Article

Waste Image Classification based on Convolutional Neural Network with Series-parallel Attention Module

28 0

waste classification
deep learning
convolutional block attention module
DenseNet-121

Jianyue Wang

DOI

10.2352/J.ImagingSci.Technol.2025.69.2.020510

Abstract

The rapid evolution of modern society has triggered a surge in the production of diverse waste in daily life. Effective implementation of waste classification through intelligent methods is essential for promoting green and sustainable development. Traditional waste classification techniques suffer from inefficiencies and limited accuracy. To address these challenges, this study proposed a waste image classification model based on DenseNet-121 by adding an attention module. To enhance the efficiency and accuracy of waste classification techniques, publicly available waste datasets, TrashNet and Garbage classification, were utilized for their comprehensive coverage and balanced distribution of waste categories. 80% of the dataset was allocated for training, and the remaining 20% for testing. Within the architecture of DenseNet-121, an enhanced attention module, series-parallel attention module (SPAM), was integrated, building upon convolutional block attention module (CBAM), resulting in a new network model called dense series-parallel attention neural network (DSPA-Net). DSPA-Net was trained and evaluated alongside other CNN models on TrashNet and Garbage classification. DSPA-Net demonstrated superior performance and achieved accuracies of 90.2% and 92.5% on TrashNet and Garbage classification, respectively, surpassing DenseNet-121 and alternative image classification algorithms. These findings underscore the potential for executing efficient and accurate intelligent waste classification.

Digital Library: JIST

FastTrack Article

Real-Time Detection of Chip Markers based on Small-DETR Approach

25 0

small target detection
semi-automatic labeling
RT-DETR network
rapid real-time detection

Honglei Wei, Meng Huang

DOI

10.2352/J.ImagingSci.Technol.2025.69.2.020507

ACDM 2024 Digital Media Special Issue

Abstract

To address the challenges in chip logo detection, such as the small size of the logos making them difficult to be detected accurately and the slow convergence speed of traditional models, we propose a real-time detection algorithm for small objects, called small-DETR. First, to reduce production costs and enhance efficiency, we employ a semi-automated data annotation method based on template matching instead of traditional manual annotation, generating label files for model training and testing. Subsequently, building upon the RT-DETR algorithm, we enhance the feature fusion module in cross-scale feature fusion module (CCFM) using semantics and details injection (SDI) module from U-Net v2. This improvement aims to retain detailed image information, accurately capturing edges, textures, and subtle variations within the marks. Lastly, employing FasterNet as the backbone network for the detection model, we optimize the existing network structure using partial convolution (PConv) to reduce redundant computations and improve convergence speed. Experimental results demonstrate that small-DETR model achieves satisfactory convergence in just 200 cycles, with a detection precision of 91.8% and a loss value of 6.1%. Compared to other models, small-DETR exhibits outstanding performance within shorter training periods, providing robust support for real-time chip pin mark detection in industrial contexts.

Digital Library: JIST

FastTrack Article

17 0

Big-Data-driven Part Anomaly Detection under Smart Manufacturing: A Study based on GAM–Boost Technology

smart manufacturing anomaly detection
high-dimensional feature selection
GAM
data-driven feature transformation
Bayesian optimization
XGBoost

Lifeng Lu, Zhanjun Si, ZhanShuo Liu, TongDa Mei

DOI

10.2352/J.ImagingSci.Technol.2025.69.1.010404