Butterfly Effect in Chaotic Image Segmentation

Marginean, R.; Andreica, Anca; Dioşan, Laura; Bálint, Zoltán

doi:10.3390/e22091028

Cited by 6 publications

(4 citation statements)

References 39 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the process of image recognition and processing, image segmentation is an indispensable key technology. It divides the tested image into several parts according to specific attributes through some technical means, which is a key step from image processing to image analysis [28]. ere are many existing image segmentation methods, including segmentation methods based on image features and segmentation methods based on specific theoretical tools [29].…”

Section: Image Identificationmentioning

confidence: 99%

Application of Structural Deformation Monitoring Based on Close‐Range Photogrammetry Technology

Liu

2021

Advances in Civil Engineering

View full text Add to dashboard Cite

The problem of structural deformation monitoring has always been a research hotspot in engineering architecture. Research on structural deformation monitoring is the main way to solve the risk of engineering construction. Based on using close-range photogrammetry technology to monitor structural deformation, combining with image recognition technology to collect and process image data, and using the conditions of direct linear transformation and collinear equation to calculate based on the extracted coordinates of the measuring point, finally, according to the coordinates of the measuring point and the deflection value of the bridge structure, the study is carried out. Experiment: first, five sets of data are used to calibrate the close-range photogrammetry equipment of measurement point accuracy are analyzed, then the bridge piers and the measurement point coordinates, the lasso, under different load on the accuracy of close-range photogrammetry technology is analyzed, according to the relevant data of the error of the close-range photogrammetry technology are analyzed, and through the calculation of different measurement methods to analyze the direct linear transformation manifested in the article. The final results show that the X-axis coordinate range of the measured points in the auxiliary spatial coordinate system is 25∼40, Y-axis coordinate range is 8∼36, and Z-axis coordinate range is 10∼35. The coordinates of measuring points of bridge cables are distributed in the fourth quadrant of the spatial coordinate system. The accuracy values of all coordinates of the measuring points under the close-range photogrammetry equipment are less than 0.1 mm, indicating that the close-range photogrammetry equipment has a good effect on the calibration of measuring points, and the error generated when the load action of each measuring point of the bridge cable is 10 N is greater than that generated when the load action is 20 N. In different calculation and measurement methods, the results obtained by total station measurement and calculation method are reduced by about 0.04∼0.07 m compared with the actual value; the results obtained by direct linear transformation method are increased by about 0.02∼0.04 m compared with the actual value; and the results obtained by other measurement and calculation methods are increased by about 0.04∼0.06 m compared with the actual value.

show abstract

Section: Image Identificationmentioning

confidence: 99%

Application of Structural Deformation Monitoring Based on Close‐Range Photogrammetry Technology

Liu

2021

Advances in Civil Engineering

View full text Add to dashboard Cite

show abstract

“…The feasibility to automatically generate seeds for GrowCut is shown; besides, authors suggest a method to automate seed generation for the segmentation task in heart images. In addition, a conventional GrowCut cellular automaton using chaotic features is enhanced in [19]. This development employs an extended, stochastic neighborhood, where randomly-selected remote neighbors reinforce the conventional local neighbors.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Numerical Validation for an Algorithm Based on Cellular Automata to Reduce Noise in Digital Images

2022

View full text Add to dashboard Cite

Given the grid features of digital images, a direct relation with cellular automata can be established with transition rules based on information of the cells in the grid. This document presents the modeling of an algorithm based on cellular automata for digital images processing. Using an adaptation mechanism, the algorithm allows the elimination of impulsive noise in digital images. Additionally, the comparison of the cellular automata algorithm and median and mean filters is carried out to observe that the adaptive process obtains suitable results for eliminating salt and pepper type-noise. Finally, by means of examples, the result of the algorithm are shown graphically.

show abstract

“…The edge detection problem has been approached using cellular automata with fixed rules, e.g., linear rules [ 5 ] or custom, threshold-based rules [ 6 ]. Cellular automata models have also been applied to image segmentation, a related computer vision problem [ 7 ]. Additionally, there are methods which rely on automatically finding suitable rules by performing an exhaustive search [ 8 ], or by applying other models for this task, such as cellular learning automata [ 9 ] or particle swarm optimization (PSO) [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization

Dumitru

Dioşan

Andreica

et al. 2021

Entropy

Self Cite

View full text Add to dashboard Cite

Edge detection is a fundamental image analysis task, as it provides insight on the content of an image. There are weaknesses in some of the edge detectors developed until now, such as disconnected edges, the impossibility to detect branching edges, or the need for a ground truth that is not always accessible. Therefore, a specialized detector that is optimized for the image particularities can help improve edge detection performance. In this paper, we apply transfer learning to optimize cellular automata (CA) rules for edge detection using particle swarm optimization (PSO). Cellular automata provide fast computation, while rule optimization provides adaptability to the properties of the target images. We use transfer learning from synthetic to medical images because expert-annotated medical data is typically difficult to obtain. We show that our method is tunable for medical images with different properties, and we show that, for more difficult edge detection tasks, batch optimization can be used to boost the quality of the edges. Our method is suitable for the identification of structures, such as cardiac cavities on medical images, and could be used as a component of an automatic radiology decision support tool.

show abstract

Butterfly Effect in Chaotic Image Segmentation

Cited by 6 publications

References 39 publications

Application of Structural Deformation Monitoring Based on Close‐Range Photogrammetry Technology

Application of Structural Deformation Monitoring Based on Close‐Range Photogrammetry Technology

Modeling and Numerical Validation for an Algorithm Based on Cellular Automata to Reduce Noise in Digital Images

A Transfer Learning Approach on the Optimization of Edge Detectors for Medical Images Using Particle Swarm Optimization

Contact Info

Product

Resources

About