Research on identification of ink marks based on machine learning and laser-induced breakdown spectroscopy

Feng, Jinjun; Wan, Enlai; Han, Boyuan; Chen, Ziang; Liu, Xiaoyuan; Liu, Yuzhu

doi:10.2351/7.0000895

Cited by 2 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent research combines laser-induced breakdown spectroscopy (LIBS) and machine learning to achieve diverse goals. One aspect involves enhancing judicial expertise by analyzing ink marks in handwriting identification using LIBS and machine learning (Feng et al 2023). Another facet addresses the misclassification of recyclable waste, employing LIBS and machine learning to create an effective online source tracing system (Chen et al 2023).…”

Section: Introductionmentioning

confidence: 99%

One-dimensional convolutional neural networks with infrared spectroscopy for classifying the origin of printing paper

Hwang,

Park,

Kim

et al. 2024

BioRes

View full text Add to dashboard Cite

Herein, the challenge of accurately classifying the manufacturing origin of printing paper, including continent, country, and specific product, was addressed. One-dimensional convolutional neural network (1D CNN) models trained on infrared (IR) spectrum data acquired from printing paper samples were used for the task. The preprocessing of the IR spectra through a second-derivative transformation and the restriction of the spectral range to 1800 to 1200 cm-1 improved the classification performance of the model. The outcomes were highly promising. Models trained on second-derivative IR spectra in the 1800 to 1200-cm-1 range exhibited perfect classification for the manufacturing continent and country, with an impressive F1 score of 0.980 for product classification. Notably, the developed 1D CNN model outperformed traditional machine learning classifiers, such as support vector machines and feed-forward neural networks. In addition, the application of data point attribution enhanced the transparency of the decision-making process of the model, offering insights into the spectral patterns that affect classification. This study makes a considerable contribution to printing paper classification, with potential implications for accurate origin identification in various fields.

show abstract

Section: Introductionmentioning

confidence: 99%

One-dimensional convolutional neural networks with infrared spectroscopy for classifying the origin of printing paper

Hwang,

Park,

Kim

et al. 2024

BioRes

View full text Add to dashboard Cite

show abstract

“…It works by analyzing the emission spectra of a cooling plasma that was formed by focusing a pulsed laser into a small area of a sample [6]. This yields almost instant information about the elements comprising the sample that, with more complex analysis, can even be used to classify groups within or between samples across a growing variety of fields [7][8][9]. Besides, the technique itself requires no sample preparation, a significant advantage for this industrial context, making it more suitable for an at-line analysis of a non-planar topology, such as of a cork stopper.…”

Section: Introductionmentioning

confidence: 99%

Characterization of Functional Coatings on Cork Stoppers with Laser-Induced Breakdown Spectroscopy Imaging

Ferreira,

Guimarães,

Oliveira

et al. 2023

Sensors

View full text Add to dashboard Cite

Evaluating the efficiency of surface treatments is a problem of paramount importance for the cork stopper industry. Generically, these treatments create coatings that aim to enhance the impermeability and lubrification of cork stoppers. Yet, current methods of surface analysis are typically time-consuming, destructive, have poor representativity or rely on indirect approaches. In this work, the use of a laser-induced breakdown spectroscopy (LIBS) imaging solution is explored for evaluating the presence of coating along the cylindrical surface and in depth. To test it, several cork stoppers with different shaped areas of untreated surface were analyzed by LIBS, making a rectangular grid of spots with multiple shots per spot, to try to identify the correspondent shape. Results show that this technique can detect the untreated area along with other features, such as leakage and holes, allowing for a high success rate of identification and for its performance at different depths, paving the way for future industry-grade quality control solutions with more complex surface analysis.

show abstract

Research on identification of ink marks based on machine learning and laser-induced breakdown spectroscopy

Cited by 2 publications

References 24 publications

One-dimensional convolutional neural networks with infrared spectroscopy for classifying the origin of printing paper

One-dimensional convolutional neural networks with infrared spectroscopy for classifying the origin of printing paper

Characterization of Functional Coatings on Cork Stoppers with Laser-Induced Breakdown Spectroscopy Imaging

Contact Info

Product

Resources

About