ORIGINAL PAPER
Research on image preprocessing algorithm based on mixed denoising and texture weakening of ore images
1
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology
Submission date: 2024-06-20
Final revision date: 2024-09-07
Acceptance date: 2024-11-19
Publication date: 2024-12-17
Corresponding author
Hui Luo
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology
School of Mechanical and Electrical Engineering, Jiangxi University of Science and Technology
Gospodarka Surowcami Mineralnymi – Mineral Resources Management 2024;40(4):107-130
KEYWORDS
TOPICS
Rational and efficient development and utilization of mineral resourcesPreparation and processing of mineral raw materials
ABSTRACT
Ore particle size information is an important basis for mining enterprises to regulate crushing parameters, due to the complex and harsh environment during the acquisition of ore images on the conveyor belt, resulting in the existence of a variety of composite noise interference in the motion target image, the surface texture characteristics of the ore and the edge of the fuzzy and other problems, thus affecting the effective acquisition of ore particle size information. To address the above issues, an image-denoising network based on global and local feature extraction and an edge enhancement algorithm for texture feature weakening is proposed. The denoising network consists of a shallow local feature extraction module and a Transformer-based U-Net global feature extraction module, which aims to combine the powerful global modeling capability of the Transformer with the local modeling advantage of convolutional network, and reconstructs the image resolution through the dual up-sampling structure, to realize the accurate output of contextual detail information. A texture weakening method based on wavelet transform and fast non-local averaging is proposed to smooth the image and weaken the texture characteristics of the ore surface, and edge sharpening is combined with Bilateral-USMR to enhance the edges of the ore particles to realize the preprocessing of the ore image. The preprocessing results were objectively evaluated and experimentally verified. The results show that the image preprocessing method improves the accuracy of image segmentation and the applicability of the ore particle size measurement technology in complex environments.
ACKNOWLEDGEMENTS
Supported by the National Natural Science Foundation of China under the project “Study on the damage evolution and dissociation mechanism of encapsulated mineral interface under multi-point symmetric ultrasonic loading” (52364025).
CONFLICT OF INTEREST
The Authors have no conflicts of interest to declare.
METADATA IN OTHER LANGUAGES:
Polish
Badania nad algorytmem wstępnego przetwarzania obrazu opartym na mieszanym odszumianiu i osłabianiu tekstury obrazów rudy
hybrydowe odszumianie obrazu, osłabienie cech tekstur, wzmocnienie krawędzi, entropia tekstur
Informacje o wielkości cząstek rudy stanowią dla przedsiębiorstw wydobywczych ważną podstawę do regulowania parametrów kruszenia ze względu na złożone i trudne środowisko podczas akwizycji obrazów rudy na przenośniku taśmowym, co skutkuje występowaniem różnorodnych zakłóceń szumu złożonego w ruchomym obrazie docelowym, właściwości tekstury powierzchni rudy i krawędzi rozmytej oraz inne problemów, wpływających w ten sposób na skuteczne pozyskiwanie informacji o wielkości cząstek rudy. Aby rozwiązać powyższe kwestie, zaproponowano sieć odszumiającą obraz opartą na globalnej i lokalnej ekstrakcji cech oraz algorytm wzmacniania krawędzi w celu osłabienia cech tekstury. Sieć odszumiająca składa się z płytkiego modułu ekstrakcji cech lokalnych i modułu globalnej ekstrakcji cech U-Net opartego na transformatorze, którego celem jest połączenie potężnych możliwości globalnego modelowania transformatora z przewagą lokalnego modelowania sieci splotowej i rekonstrukcja rozdzielczości obrazu poprzez podwójną strukturę próbkowania w górę, aby uzyskać dokładne dane wyjściowe szczegółowych informacji kontekstowych. Zaproponowano metodę osłabiania tekstury opartą na transformacji falkowej i szybkim uśrednianiu nielokalnym w celu wygładzenia obrazu i osłabienia właściwości tekstury powierzchni rudy, a wyostrzanie krawędzi wiązało się z dwustronnym-USMR w celu uwydatnienia krawędzi cząstek rudy w celu realizacji wstępnej obróbki obrazu rudy. Jej wyniki zostały obiektywnie ocenione i zweryfikowane eksperymentalnie. Pokazują one, że metoda wstępnego przetwarzania obrazu poprawia dokładność segmentacji obrazu i możliwość zastosowania technologii pomiaru wielkości cząstek rudy w złożonych środowiskach.
REFERENCES (22)
1.
Canny, J. 1986. A Computational Approach to Edge Detection. IEEE transactions on pattern analysis and machine intelligence 8(6), pp. 679–698, DOI: 10.1109/TPAMI.1986.4767851.
2.
Dabov et al. 2007 – Dabov, K., Foi, A., Katkovnik, V. and Egiazarian, K. 2007. Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE transactions on image processing: a publication of the IEEE Signal Processing Society 16(8), pp. 2080–2095, DOI: 10.1109/TIP.2007.901238.
3.
Fan et al. 2022 – Fan, C.M., Liu, T.J. and Liu, K.H. 2022. SUNet: Swin transformer UNet for image denoising. IEEE International Symposium on Circuits and Systems (ISCAS). pp. 2333–2337, DOI: 10.48550/arXiv.2202.14009.
4.
Guo et al. 2019 – Guo, S., Yan, Z., Zhang, K., Zuo, W., Zhang, L. 2019. Toward convolutional blind denoising of real photographs. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 1712–1722, DOI: 10.1109/CVPR.2019.00181.
5.
Guo et al. 2024 – Guo, X., Xu, L., Cheng, C. and Huo, J. 2024. Image denoising algorithm based on weighted kernel norm minimization and improved wavelet threshold function. Journal of National University of Defense Technalogy 46(2), pp. 238–246.
6.
He et al. 2019 – He, J.W., Dong, C., Qiao, Yu. 2019. Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers. 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), DOI: 10.1109/CVPR.2019.01131.
8.
Lei et al. 2019 – Lei, Z., Su, W. and Hu, Q. 2019. Multimode Decomposition and Wavelet Threshold Denoising of Mold Level Based on Mutual Information Entropy. Entropy 21(2), DOI: 10.3390/e21020202.
9.
Liu, J.S. 2021. Research On Real-World Image Denoising Based On Deep Neural Network. Xidian University.
10.
Maheswari, D. and Radha, V. 2010. Noise Removal In Compound Image Using Median Filter. International Journal on Computer Science and Engineering 2(4), pp. 1359–1362.
11.
Mallat, S. 1989. A theory for multiresolution signal decomposition. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(7), pp. 674–693, DOI: 10.1109/34.192463.
12.
Ronneberger et al. 2015 – Ronneberger, O., Fischer, P. and Brox, T. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241, DOI: 10.1007/978-3-319-24574-4_28.
13.
Sedaghatjoo et al. 2024 – Sedaghatjoo, Z., Hosseinzadeh, H. and Bigham, B.S. 2024. Local Binary Pattern(LBP) Optimization for Feature Extraction, DOI: 10.48550/arXiv.2407.18665.
14.
Tan et al. 2024 – Tan, T., Wang, K. and Zhou, W. 2024. Edge Detection of Plant Root Images Based on Improved Canny Algorithm.Photonics & Electromagnetics Research Symposium (PIERS). Tomasi, C. and Manduchi, R. 1998. Bilateral filtering for gray and color images. Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271), DOI: 10.1109/ICCV.1998.710815.
15.
Uğur et al. 2019 – Uğur, E., Dang, N.H.T., Le, M.H. and Serdar, E. 2019. An Iterative Mean Filter for Image Denoising. IEEE Access. 7(1), pp. 167847–167859, DOI: 10.1109/ACCESS.2019.2953924.
16.
Wang, Y. 2019. Research on Multi-Feature Fusion for Image Texture Analysis. Nanjing University of Aeronautics and Astronautics.
17.
Wang et al. 2020 – Wang, Y., Huang, H., Xu, Q., Liu, J., Liu, Y. and Wang, J. 2020. Practical Deep Raw Image Denoising on Mobile Devices. [In:] Computer Vision – ECCV 2020. 12351, pp. 1–16, DOI: 10.1007/978-3-030-58539-6_1.
18.
Yan, F.J. and Li, B.Z. 2022. Spectral graph fractional Fourier transform for directed graphs and its application. Signal Processing 210, DOI: 10.48550/arXiv.2203.10199.
19.
Yue, Z.S., Zhao, Q., Zhang, L. and Meng, D.Y. 2020. Dual Adversarial Network: Toward Real-World Noise Removal and Noise Generation. Computer Science – Computer Vision and Pattern Recognition, pp. 41–58, DOI: 10.48550/arXiv.2007.05946.
20.
Zhang et al. 2017 – Zhang, K., Zuo, W., Chen, Y., Meng, D. and Zhang, L. 2017. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Transactions on Image Processing 26(7), pp. 3142–3155, DOI: 10.1109/TIP.2017.2662206.
21.
Zhang, X.B. 2022. Two-step non-local means method for image denoising. Multidimensional Systems and Signal Processing 33(6), pp. 341–366, DOI: 10.1007/s11045-021-00802-y.
22.
Zhao et al. 2019 – Zhao, Y., Jiang, Z., Men, A. and Ju, G. 2019. Pyramid Real Image Denoising Network. IEEE Visual Communications and Image Processing (VCIP), DOI: 10.1109/VCIP47243.2019.8965754.
| eISSN: | 2299-2324 |
| ISSN: | 0860-0953 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
