A novel context sensitive multilevel thresholding for image segmentation

Patra, Swarnajyoti; Gautam, Rahul; Singla, Ashish

doi:10.1016/j.asoc.2014.06.016

Cited by 84 publications

(39 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[11] utilized particle swarm optimization (PSO) and artificial bee colony (ABC) combined with Kapur's entropy and between-class variance to find the optimal multi-level thresholds. [12] adopted a novel thresholding technique via proposing an energy function to generate the energy curve of an image and taking into an account the spatial contextual information of the image. Because of the fuzziness of real life image, recently image segmentation methods based on fuzzy theory have attracted much attention which could obtain satisfactory segmentation results.…”

Section: Q3mentioning

confidence: 99%

Fuzzy entropy based optimal thresholding using bat algorithm

Wang

Liu

et al. 2015

Applied Soft Computing

View full text Add to dashboard Cite

Section: Q3mentioning

confidence: 99%

Fuzzy entropy based optimal thresholding using bat algorithm

Wang

Liu

et al. 2015

Applied Soft Computing

View full text Add to dashboard Cite

“…As a result, all microscopic images are not stained in the same scale, and the saturation values vary widely from the image to image [18]. Initial segmentation, using threshold value, does not work properly until uniform intensity scaling is done [8,17,19,39]. By examining the saturation values, it has been found that numbers of pixels are very small over a considerable range on the lower side of saturation values.…”

Section: Segmentationmentioning

confidence: 99%

“…The histogram is checked from the lowest saturation value towards the highest and the cut-off is taken at the saturation value X c such that the number of pixels over the saturation range (0 -X c ) is equal to Y1% of the total number of pixels [39]. It is define as…”

Section: Segmentationmentioning

confidence: 99%

Automatic System for Plasmodium Species Identification from Microscopic Images of Blood-Smear Samples

Ghosh¹,

Bhattacharjee

Nasipuri

2017

J Healthc Inform Res

View full text Add to dashboard Cite

Malaria spreads rapidly in a particular time of the year, and it becomes impossible to arrange sufficient number of pathologists and physician at that time, especially in remote places of the developing nations. Thus, low-cost pathological equipment, which can automatically identify and classify the type of malarial parasites from the microscopic images of blood samples, will be of great help for diagnosis and treatment of malaria. The proposed system detects malarial parasites from the microscopic images of blood samples and also categorizes them based on shape, size and texture. To capture different field images of the same sample, a fully automatic slide movement system is devised to control the slide movement under the "objective lens" of the microscope. The sensitivity and specificity of the system are found to be 91.42 and 87.36% respectively. The system has the potential to a powerful supporting tool for telemedicine with very simple operational instructions.

show abstract

“…In Eq.8 the number two is part of the Otsu's variance operator and does not represent an exponent in the mathematical sense. Moreover 1 2 2 2 in Eq.8 are the variances of 1 2 which are defined as …”

Section: Objective Functions 31 Otsu's Between Class Variancementioning

confidence: 99%

“…It is frequently used to segment an image into independent regions, which preferably compares two various true objects [1]. Thresholding is a standout amongst the most important and viable methods for image segmentation, as it works taking a threshold (th) value so that pixels, whose intensity level is higher than th are marked as first class while the rest relate to second class label.…”

Section: Introductionmentioning

confidence: 99%

Optimal Multilevel Threshold Selection for Gray Level Image Segmentation using SMS Algorithm

Kotte¹,

Kumar²

2017

IJCA

View full text Add to dashboard Cite

Image processing is one of the real research regions in the most recent four decades. Numerous researchers have contributed very great algorithms and reported outstanding results. In this paper, state of matter search optimization based multilevel thresholding is implemented for the segmentation of gray scale Images. Set of standard gray level images are considered for image segmentation. The optimal multilevel threshold is found by maximizing the very popular objectives such as between class variance (Otsu method) and Kapur's entropy. The outcomes are looked at with the aftereffects of the existing algorithms like IDSA, HSA, PSO, and BF. The outcomes uncover that the execution of state of matter search optimization algorithm based optimal multilevel threshold for image segmentation is better and has predictable execution than officially reported techniques. KeywordsMultilevel thresholding, gray scale image segmentation, state of matter search optimization, qualitative and quantitative analysis

show abstract

A novel context sensitive multilevel thresholding for image segmentation

Cited by 84 publications

References 18 publications

Fuzzy entropy based optimal thresholding using bat algorithm

Fuzzy entropy based optimal thresholding using bat algorithm

Automatic System for Plasmodium Species Identification from Microscopic Images of Blood-Smear Samples

Optimal Multilevel Threshold Selection for Gray Level Image Segmentation using SMS Algorithm

Contact Info

Product

Resources

About