Segmentation and analysis of damages in composite images using multi-level threshold methods and geometrical features

Fredo, A. R. Jac; Abilash, R.; Kumar, C. Suresh

doi:10.1016/j.measurement.2017.01.002

Cited by 23 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past several automated algorithms have been developed for analyzing microscopic images, counting of cells and quanti cation of different cellular phenomena [9][10][11][12][13][14][15][16]. Segmentation and detection are the two major requirements for analyzing microscopic images.…”

Section: Introductionmentioning

confidence: 99%

Investigation of time dependent growth of HepG2 cancerous cells using deep learning and shape metrics

Ronickom

2023

Preprint

View full text Add to dashboard Cite

Study of growth of Human hepatocellular carcinoma cells (HepG2) cells provide useful information for clinical study of megestrol acetate for the treatment of Hepatocellular carcinoma. In this study, we analyzed the growth of HepG2 liver cancerous cells using image processing methods. Initially, the HepG2 cells were cultured and microscopic images were captured in bright field mode at time of seeding (00 h) followed by 06 h and 18 h. We segmented the cells using Tsallis and deep learning methods and the average size of colonies were calculated using shape metrics. Finally, we correlated the cell density obtained using MTT assay with the average size of colonies calculated from the Tsallis and deep learning segmented images. Results show that deep learning methods were able to segment the cells more precisely than Tsallis method. The average colony area calculated from the deep learning segmented images increases with time and concentration. The cell growth and adhesion pattern measured by deep leaning method showed good consistency with spectroscopic observations. The process pipeline provides a new way to assess cell adhesion and proliferation with capabilities in measuring their occupied surface area. The framework documented can be a promising tool to automate cancerous cell growth by evaluating average colony size for studying normal and pathological conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation of time dependent growth of HepG2 cancerous cells using deep learning and shape metrics

Ronickom

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, these classical methods perform good capability only in the case of a lower threshold level. When the number increases, the computational time will present exponential growth [18]. Therefore, further researches that made creative use of meta-heuristic algorithms are proceeding to reduce the time complexity and maintain image segmentation accuracy.…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid Harris Hawks Optimization for Color Image Multilevel Thresholding Segmentation

2019

View full text Add to dashboard Cite

Multilevel thresholding has got more attention in recent years with various successful applications. However, the implementation becomes more and more complex and time-consuming when the number of thresholds is high, and color images which contain more information are even worse. Therefore, this paper proposes an alternative hybrid algorithm for color image segmentation, the advantages of which lie in extracting the best features from the high performance of two algorithms and overcoming the limitations of each algorithm to some extent. Two techniques, Otsu's method, and Kapur's entropy, are used as fitness function to determine the segmentation threshold values. Harris hawks optimization (HHO) is a novel and general-purpose algorithm, and the hybridization of HHO is fulfilled by adding another powerful algorithm-differential evolution (DE), which is known as HHO-DE. More specifically, the whole population is divided into two equal subpopulations which will be assigned to HHO and DE algorithms, respectively. Then both algorithms operate in parallel to update the positions of each subpopulation during the iterative process. In order to fully demonstrate the superior performance of HHO-DE, the proposed method is compared with the seven state-of-the-art algorithms by an array of experiments on ten benchmark images. Meanwhile, five measures, including the average fitness values, standard deviation (STD), peak signal to noise ratio (PSNR), structure similarity index (SSIM), and feature similarity index (FSIM), are used to evaluate the performance of each algorithm. In addition, Wilcoxon's rank sum test for statistical analysis and the comparison with the super-pixel method are also conducted to verify the superiority of HHO-DE. The experimental results reveal that the proposed method significantly outperforms other algorithms. Hence, the HHO-DE algorithm is a remarkable and promising tool for multilevel thresholding color image segmentation.

show abstract

“…Image segmentation has always been the basic work of image processing research, and is a very challenging work. Color image segmentation is mainly based on threshold segmentation [1]- [3], clustering segmentation [4]- [6], region segmentation [7]- [9] and neural network segmentation [10]- [12]. Thresholding methods involve selecting a set of thresholds using some characteristics defined from images.…”

Section: Introductionmentioning

confidence: 99%

Multilevel Color Image Segmentation Based on GLCM and Improved Salp Swarm Algorithm

Xing

Jia

2019

IEEE Access

View full text Add to dashboard Cite

The grayscale co-occurrence matrix (GLCM) can be adapted to segment the image according to the pixels, but the segmentation effect becomes worse as the number of threshold increases. To solve this problem, we propose an improved salp swarm algorithm (LSSA) to optimize GLCM, with the novel diagonal class entropy (DCE) as the fitness function of the GLCM algorithm. At the same time, in order to increase the optimization ability of traditional SSA algorithm, Levy flight (LF) strategy should be improved. Through experiments on the LSSA algorithm of the color natural images, the satellite images, and the Berkeley images, the segmentation quality of the segmented images is evaluated by peak signal-to-noise ratio, feature similarity, probability rand index, variation of information, global consistency error, and boundary displacement error. The experimental results show that the segmentation ability of the GLCM-LSSA algorithm is superior to other comparison algorithms and has a good segmentation ability.

show abstract

Segmentation and analysis of damages in composite images using multi-level threshold methods and geometrical features

Cited by 23 publications

References 15 publications

Investigation of time dependent growth of HepG2 cancerous cells using deep learning and shape metrics

Investigation of time dependent growth of HepG2 cancerous cells using deep learning and shape metrics

A Novel Hybrid Harris Hawks Optimization for Color Image Multilevel Thresholding Segmentation

Multilevel Color Image Segmentation Based on GLCM and Improved Salp Swarm Algorithm

Contact Info

Product

Resources

About