Skip to main content

​
Quantitative Water Pollution Analysis System Integrating GLCM Image Features with Schlieren Imaging Technology

Jia-Ming Zhou, Wen-Lin Chu, and Bo-Lin Jian

​
Abstract

This work presents an integrated water pollution analysis system that combines a Z-type schlieren optical setup with near-infrared spectroscopy to monitor microparticles generated during the thermal degradation of plastic materials in water. The proposed framework exploits the high sensitivity of schlieren imaging to visualize subtle density variations and employs near-infrared spectral measurements to assist particle size and concentration assessment. A feature extraction pipeline based on Gray Level Co-occurrence Matrix (GLCM) is developed, where contrast, correlation, energy, and homogeneity calculated over multiple distances and directions serve as inputs to a turbidity prediction model. Experiments on PP plastics thermally degraded between 60–100°C for 60 minutes, with synchronized measurements from a standard turbidimeter, establish a correspondence database between image-derived features and turbidity values. Preliminary results indicate that microparticle structures formed under different degradation conditions exhibit clearly distinguishable texture signatures, demonstrating the feasibility of the proposed approach as a quantitative, high-precision tool for microplastic-related water pollution monitoring and future turbidity prediction model development. The study incorporates flow velocity sensors for cross-validation to ensure analytical reliability. This innovative methodology not only reveals the blocking effects of masks on airflow propagation pathways and velocities but also provides objective scientific data to support public health epidemic prevention strategies, demonstrating significant practical application value.

​
Keywords

  • Color Schlieren Techniques
  • Microplastic pollution
  • Gray Level Co-occurrence Matrix (GLCM)
  • Turbidity prediction
  • Plastic thermal degradation

​
Sample Results

The upper-left panel shows the dual-light-source schlieren optical setup, which captures refractive-index gradient variations caused by microparticles in water through a precision lens assembly and CMOS camera. This design achieves extremely high sensitivity to micrometer-scale plastic thermal degradation products.

The image processing pipeline begins with the original low-contrast schlieren image (upper-center gray block), proceeds through contrast enhancement and noise suppression to produce an enhanced image (second from right), and renders microparticle density disturbances as bright localized features. The rightmost image shows automated object detection results, where green contours delineate microparticle boundaries and red dots mark centroid positions, enabling real-time counting and size statistics. The four lower images illustrate the multi-stage transformation for GLCM texture feature extraction. The left binarization mask separates foreground from background; the grayscale intensity field retains the original light-intensity information for subsequent statistical computation; the third image quantifies texture statistics in a specific direction (e.g., contrast or energy spatial distribution); and the rightmost heatmap integrates GLCM features across multiple directions (0°, 45°, 90°, 135°) and distance parameters, with a 0–250 color scale encoding numerical values — red high-value regions correspond to areas of high microparticle density or peak texture complexity.

The experimental design uses PP plastics thermally degraded at 60–100°C for 60 minutes, with simultaneous recording of standard turbidimeter readings and schlieren image data. Microparticle structures produced under different degradation conditions exhibit distinguishable textures in the four-dimensional GLCM feature space (contrast, correlation, energy, homogeneity), providing preliminary validation of the feasibility of predicting turbidity values from optical features and offering a high-precision prototype tool for non-contact microplastic pollution quantitative monitoring.

Demo

​
BibTeX Citation

@inproceedings{zhou2025automation,
  author    = {Jia-Ming Zhou and Wen-Lin Chu and Bo-Lin Jian},
  title     = {Quantitative Water Pollution Analysis System Integrating GLCM Image Features with Schlieren Imaging Technology},
  booktitle = {The 22nd International Conference on Automation Technology (Automation 2025)},
  year      = {2025},
  month     = {November},
  address   = {Kaohsiung, Taiwan}
  url       = {https://automation2025.nsysu.edu.tw}
}