A new structure of decision tree based on oriented edges gradient map for circles detection and the analysis of nano-particles

Akrout, Belhassen

doi:10.1016/j.micron.2021.103055

Cited by 9 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Berus et al [25] built a Laplacian Pyramid [26] to detect edges from multiple resolutions and concatenated them to determine particle grain sizes for aluminum alloy material. Akrout [27] improved the circular Hough transform [24] by building a decision tree [28] based on an oriented edges gradient map to detect circles from nanoimages with better efficiency and robustness. Recently, Manee et al [29] modified Mask R-CNN [18] by RetinaNet [30] to measure dense crystal sizes from video microscopy images.…”

Section: Related Workmentioning

confidence: 99%

Automatic measurement of slug flow processes from in‐line videos

Qian,

Hulsizer,

Mou

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

Slug flow processes draw much attention in chemical and pharmaceutical manufacturing thanks to their ability to eliminate downtime costs and batch‐to‐batch variation. Using in‐line video can monitor the current process status and improve the stability of the slug flow. However, there are no effective image processing methods aiming at such videos from chemical experiments due to limited training sample size and the variety of experimental settings. The paper proposes a training‐free method to automatically detect and measure the slugs from in‐line videos. Multiple image features are fused to identify the slug shapes under various lighting conditions, a six‐point model is fitted to achieve better volume estimation, and a consistency score is estimated to quantify the detection uncertainty. The proposed algorithm achieves similar results to manual labeling for various types of slug flow processes, improving the accuracy of slug column estimation by a large margin compared to the existing automatic methods. Finally, using it to monitor the slug flow process's stability and the change of the slug volume in an injection point are demonstrated. The method not only shows that handcrafted image features have the capability for detection and segmentation from chemical experiment images but also paves the road for a training‐based algorithm for the task.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic measurement of slug flow processes from in‐line videos

Qian,

Hulsizer,

Mou

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…But it had difficulty ensuring the accuracy of large-diameter circles with occlusions when multiple small arcs were reserved. Akrout 24 proposed a method to detect circles based on an oriented edge gradient graph and decision tree, and the circle parameters were calculated based on the characteristics of right triangles inside the circle, which makes it also difficult to apply to large-region occlusion.…”

Section: Related Workmentioning

confidence: 99%

“…Nevertheless, the chance of randomly sampling points from the same circle is low for images with occlusions, noise, or complex scenes. In addition, there are numerous methods for detecting circle parameters using the geometric characteristics of circles, such as rays, 17 gradients, 18 symmetry, 19 intersecting lines, 20 , 21 inscribed triangles, 22 – 24 etc. However, as pointed out in the literature, when calculating the power peak histogram using the ray, it is necessary to set multiple parameter points for multiple calculations.…”

Section: Introductionmentioning

confidence: 99%

Circle detection algorithm based on neighborhood density clustering

Li,

Wang,

Zhang

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

.Circle detection in images is one of the key technologies in machine vision, pattern recognition, and artificial intelligence. However, conventional circle detection methods are sensitive to complex scenes, noise, and occlusion in images. Solving the impact of these situations is still the focus of circle detection algorithm research. Therefore, a circle detection algorithm based on neighborhood density clustering (NDC) is proposed. The proposed algorithm calculates circle parameters of connected regions after extracting corners, corroding the corners, and marking the connected regions. Then, NDC of the circle parameters is executed to classify arcs belonging to the same circle into one category to acquire a virtual connected region. And the circle parameters of the virtual connected region are clustered using NDC again to obtain the circle parameter dataset of the circle to be detected. The precise circle parameters are further estimated by calculating the centroid of each category. To prevent false positives, candidate circles are verified through a ratio rule. Extensive experiments using both synthetic and real images were performed. The results compared with those of representative state-of-the-art methods demonstrate that the proposed algorithm can be applied to a variety of complex scenes and has several advantages: good anti-occlusion effect, more robustness against noise, high accuracy, and better performance.

show abstract

“…e goal is that as each node of the decision tree develops, part of the data set will be labeled with the classified data, making the data set purer than before. In general, the information gain is chosen as a function of determining the purity of the information [13].…”

Section: User Classification Based On Decision Tree Algorithmmentioning

confidence: 99%

A Big Data Technique for Internet Financial Risk Control

Xie

Shi

2022

Mobile Information Systems

View full text Add to dashboard Cite

The danger of losing funds on an investment or business enterprise is referred to as financial risk. Credit risk, liquidity risk, and operational risk are some of the most prevalent and different financial hazards. Financial risk control is an organizational activity that seeks to detect, monitor, and manage exposure to different risks associated with the usage of financial services. Conventional accounting risk control has relatively great timeliness and unpredictability; therefore, traditional accounting risk identification has numerous difficulties, such as high error rate, low precision, lengthy time, and risk. As a result, this research provides a unique financial risk control strategy in the Internet environment based on big data. First, the decision tree algorithm is used to classify the users who can face financial risks. Simultaneously, the user’s personal credit information is established and represented mathematically, and the 5C mathematical model is obtained. In this way, the user’s credit degree can be judged more accurately, and the user’s credit rating can be obtained, allowing quantitative analysis of users to be realized. Second, construct and weight the financial risk system index of the Internet in accordance with the existing financial system. Finally, the Internet financial risk control model based on big data is built, and the financial risk early warning threshold range is determined to achieve Internet financial risk control. The experimental findings reveal that the method’s risk identification error rate is minimal, accuracy is high, and control time is quick. It can match the actual risk level, which shows that the control effect of this method is good.

show abstract

A new structure of decision tree based on oriented edges gradient map for circles detection and the analysis of nano-particles

Cited by 9 publications

References 20 publications

Automatic measurement of slug flow processes from in‐line videos

Automatic measurement of slug flow processes from in‐line videos

Circle detection algorithm based on neighborhood density clustering

A Big Data Technique for Internet Financial Risk Control

Contact Info

Product

Resources

About