An Improved Python-Based Image Processing Algorithm for Flotation Foam Analysis

Zhang, Wenkang; Liú, Dan; Wang, Chun-Jing; Liu, Ruitao; Wang, Daqian; Yu, Longzhou; Wen, Shuming

doi:10.3390/min12091126

Cited by 9 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, using deep learning-based machinevision technology to monitor and identify the foam surface characteristic information during the flotation production process in real-time can guide the adjustment of relevant production elements and improve the mineral resource utilisation and economic efficiency of coal washing plants. Owing to factors such as uneven illumination and water vapour generation, foam images obtained at the production site often have low brightness and contrast, and uneven greyscale distributions, hindering the recognition and extraction of features (Zhang et al, 2019;Ju et al, 2022;Zhang et al, 2022). Zhang et al (2019) employed the SSR algorithm (Jobson et al, 1997), which uses the original foam image minus the low-frequency components of the image obtained after log transformation.…”

Section: Introductionmentioning

confidence: 99%

Coal slurry foam image enhancement based on multiscale convolutional network

Huang,

Wang,

Zhu

et al. 2024

Physicochem. Probl. Miner. Process.

View full text Add to dashboard Cite

Collecting information on the flotation foam characteristics is important for controlling flotation production conditions. Foam images acquired during coal slurry flotation are affected by factors such as ambient lighting, contributing to uneven grayscale images with low brightness and contrast. Brightness enhancement of foam images is often required when using network models to extract feature information from the images. The paper proposes a foam image brightness enhancement algorithm based on a multiscale convolutional neural network. The method employs a skip connection structure based on a summation connection design based on logarithmic functions and introduces a loss function based on logarithmic transformation in the network. At the same time, branching networks of different complexity are designed in the network to further help alleviate the gradient vanishing problem. The experimental results show that when evaluating the quality of images after brightness enhancement of foam images and the public dataset MIT, the numerical results of using the proposed skip connection structure in the proposed network are overall better than using the resblock structure, and the proposed loss function is better than is better than using the L2 loss function. The proposed network greatly improves the visual effect of flotation foam images and lays the foundation for feature extraction of flotation foam images and intelligent flotation production.

show abstract

Section: Introductionmentioning

confidence: 99%

Coal slurry foam image enhancement based on multiscale convolutional network

Huang,

Wang,

Zhu

et al. 2024

Physicochem. Probl. Miner. Process.

View full text Add to dashboard Cite

show abstract

“…A huge boost in popularity for the image processing and computer vision application was achieved with the increase in popularity of Python programming language and the implementation of various image processing frameworks such as OpenCV (for C++ initially and Python afterwards) and the development of machine learning and deep learning frameworks [ 6 , 7 ].…”

Section: Introductionmentioning

confidence: 99%

Detecting Machining Defects inside Engine Piston Chamber with Computer Vision and Machine Learning

Abagiu

Cojocaru

Manta

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper describes the implementation of a solution for detecting the machining defects from an engine block, in the piston chamber. The solution was developed for an automotive manufacturer and the main goal of the implementation is the replacement of the visual inspection performed by a human operator with a computer vision application. We started by exploring different machine vision applications used in the manufacturing environment for several types of operations, and how machine learning is being used in robotic industrial applications. The solution implementation is re-using hardware that is already available at the manufacturing plant and decommissioned from another system. The re-used components are the cameras, the IO (Input/Output) Ethernet module, sensors, cables, and other accessories. The hardware will be used in the acquisition of the images, and for processing, a new system will be implemented with a human–machine interface, user controls, and communication with the main production line. Main results and conclusions highlight the efficiency of the CCD (charged-coupled device) sensors in the manufacturing environment and the robustness of the machine learning algorithms (convolutional neural networks) implemented in computer vision applications (thresholding and regions of interest).

show abstract

“…The algorithm enhances the segmentation and extraction of similar highlights, but interference problems such as noise and highlight edges are still not solved, which leads to an offset of the segmentation line. Zhang et al [14] used the proposed region adaptive and multi-scale Retinex image compensation methods to solve interference problems such as noise and bright edges by improving the uniformity of brightness. The most successful of these methods are those of Zhang et al and Peng et al Zhang et al used optimized markers to implement the watershed algorithm [15] , and Peng et al used optimal markers and edge constraints to improve the watershed algorithm [16] .…”

mentioning

confidence: 99%

Flotation foam image segmentation based on highlight overlap correction and multiple edge constraints

Yang,

Sun

2024

Preprint

View full text Add to dashboard Cite

Bubble size contains important indicative information, which is closely related to flotation production conditions and process indicators. However, due to the different sizes of bubbles in the flotation process and the complexity of the shooting light environment, satisfactory results cannot be obtained from the existing image segmentation methods. In this paper, an improved watershed algorithm based on multiple edge constraints and highlight collegiate positivity is proposed. First, three algorithms are designed to extract and classify foam highlights of the same size, namely, small foam, medium foam and large foam, and special overlap correction and fusion are applied to these three foams. Then, the bubble boundaries are extracted using the Laplace operator, and the segmentation line is constrained with a positive and inverse 45-degree gradient images as multiple edges to ensure the integrity of the segmentation line. Finally, the fused highlight markers are used to deoptimize the external constraint line for watershed segmentation. The tests show that the method is suitable for multiple sizes of fuzzy edges and foam image segmentation. The experimental results show that the accuracy and robustness of the proposed segmentation algorithm are significantly better than other methods, and the proposed method is suitable for foam image segmentation with fuzzy edges and diverse sizes.

show abstract

An Improved Python-Based Image Processing Algorithm for Flotation Foam Analysis

Cited by 9 publications

References 25 publications

Coal slurry foam image enhancement based on multiscale convolutional network

Coal slurry foam image enhancement based on multiscale convolutional network

Detecting Machining Defects inside Engine Piston Chamber with Computer Vision and Machine Learning

Flotation foam image segmentation based on highlight overlap correction and multiple edge constraints

Contact Info

Product

Resources

About