12 July 2023 in Measurement Science and Technology
To reduce the influence of material particle size on coal gangue identification, a particle size identification method, and an adaptive image enhancement method are proposed, which can accurately identify the particle size of poorly segmented and mutually blocked materials, effectively reduce the reflection and blur of the image surface and enhance the texture details. Through the research of coal gangue images with different particle sizes, it is found that the image quality and feature curve distribution of small particle size are different from those of large particle size, and the gradient features are worse. In this paper, the accurate identification of particle size is realized using the difference in image quality and texture, and the identification rate is 99.25%. Through the image enhancement method in this paper, 33.41% of the reflection on the image surface is removed, and the average gradient is improved by 74.01%, which effectively improves the image quality and the ability to express texture information. This algorithm has high environmental adaptability, and the identification rate can reach 99.16% in moderate illumination, 98.33% in dim illumination, and 96.33% in strong illumination. This research provides a valuable idea for image processing and identification technology based on machine vision.
19 December 2022 in Measurement Science and Technology
To improve the foreground segmentation and location accuracy of complex coal gangue images with gray histogram distribution close to the unimodal shape, a contour detection algorithm of the grayscale fluctuation matrix is proposed. The contour and non-contour pixels of coal and gangue images are investigated, and the result indicates that the gray values of the pixels around the contour exhibit the non-uniform distribution, and the gray value changes in different directions are significantly different. Accordingly, a grayscale fluctuation matrix is built by calculating the change amplitude of pixels in different directions, and multiple features are extracted from the grayscale fluctuation matrix to realize the target contour segmentation. Furthermore, the contour is optimized using the historical and future information of the contour image, thus effectively removing numerous false contours, reproducing some hidden contours and increasing segmentation accuracy. This method has high accuracy, and the maximum error rates of the pixel area and center coordinate of contour detection are 4.404% and 3.18% respectively. This study provides a feasible solution to the edge detection and segmentation of images with similar and complex backgrounds.
6 September 2022 in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
Aiming at the problem that the identification of coal and gangue is easily affected by external factors, a coal gangue identification method based on multi-dimensional gradient features and gray texture features is proposed. Research shows that Sobel operators with different window sizes have different degrees of interest in image textures. The larger the window, the more interested they are in fine textures. The characteristic curves obtained by different Sobel operators are quite different, and the optimal gradient features can be obtained by using various Sobel operators. The separability of gradient features is higher than that of gray texture features, and the gradient features are less affected by light. The classification model established in this paper has a recognition rate of over 97% for different mining areas, and the detection time of a single image is less than 20.5 ms. When the light intensity changes from 600 lux to 1800 lux, the fluctuation range of the F1-score in this method is only 0.26%. The fusion of multi-dimensional gradient features and gray texture features can significantly reduce the influence of external factors on the recognition model, and improve the recognition accuracy and anti-interference ability of the model.
19 November 2023 in International Journal of Coal Preparation and Utilization
9 January 2025 in IEEE Transactions on Instrumentation and Measurement
To minimize the impact of external factors on the identification of coal gangue and ensure accurate identification under complex conditions, an analysis of various external influences was conducted. A new image enhancement algorithm leveraging multi-dimensional information fusion and a novel set of features were introduced. The image quality serves as the control coefficient for performing adaptive gray mapping on RGB images, and the mapped RGB images undergo multi-level decomposition at various scales to separate high-frequency and low-frequency components. Depth texture images and regional fading masks are derived from the image depth information. Guided by the regional fading mask, the RGB image is processed at the pixel level in both spatial and frequency domains to enhance authentic textures and suppress artificial textures. By integrating the proposed depth texture features with enhanced gray, texture, and gradient features, accurate identification of coal gangue under complex conditions is achieved. Comparative analysis of recognition results from different algorithms reveals the superior recognition performance and adaptability of the proposed method, with accuracy and F 1 scores under four conditions being (97.143%, 0.970), (94.028%, 0.938), (90.310%, 0.902), and (92.237%, 0.920).
28 September 2026 in Measurement Science and Technology
The existing methods for measuring the volume of coal mainly rely on visible light imaging, laser scanning or binocular vision. However, due to insufficient lighting, high dust concentration and the difficulty in integrating additional sensing hardware in the underground x-ray dry separation system, their application is limited. Currently, the research on thickness or volume estimation based on x-rays has not systematically addressed the lateral pixel distortion and effective penetration thickness deviation problems caused by the fan-shaped beam geometry structure, which are the main sources of volume errors in actual conveyor belt imaging systems. To solve this problem, under a fixed imaging configuration, a physically-inspired semi-empirical grayscale-thickness model was established by considering tube voltage and current, source-to-target distance, material attenuation, and beam path thickness; the unknown parameters were obtained through experimental calibration. To reduce geometric bias caused by the fan-beam imaging geometry, two correction steps are introduced: (1) a pixel-level distortion correction model for the lateral direction of the conveyor belt, and (2) a thickness component correction that converts the optical path thickness inferred from the grayscale image into the thickness component perpendicular to the conveyor belt plane. On this basis, a mapping relationship between pixel size and real geometric size is established and used for pixel-wise volume integration. Experiments conducted on the calibrated setup show that the proposed corrections substantially reduce the systematic overestimation observed in the uncorrected model. Relative to the water-displacement reference, the final corrected model keeps the volume error within approximately ±6% for the current test set, demonstrating that the proposed framework provides a practical solution for online particle-volume estimation in conveyor-based x-ray dry sorting systems without additional sensing hardware.