Number-Driven Perceptual Segmentation of Natural Color Images for Easy Decision of Optimal Result

Maeda, Junji; Kawano, A.; Saga, Sato; Suzuki, Yusuke

doi:10.1109/icip.2007.4379143

Cited by 8 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Grana et al [6] uses Otsu's threshold to automatically segment the melanoma image and obtains a smoothed lesion border through spline-based interpolation. Silveira et al [7] makes comparisons among: adaptive thresholding (AT), gradient vector flow (GVF) [8], adaptive snake (AS) [9], level set method of Chan (C-LS) [10], expectation maximization level set (EM-LS) [11] and fuzzy-based split-and-merge algorithm (FBSM) [12], and AS is found to be the best. Region-based approaches have been widely researched and used as comparisons.…”

Section: Related Workmentioning

confidence: 99%

Adaptive segmentation based on multi-classification model for dermoscopy images

Xie

et al. 2015

Front. Comput. Sci.

View full text Add to dashboard Cite

Segmentation accuracy of dermoscopy images is important in the computer-aided diagnosis of skin cancer and a wide variety of segmentation methods for dermoscopy images have been developed. Considering that each method has its strengths and weaknesses, a novel adaptive segmentation framework based on multi-classification model is proposed for dermoscopy images. Firstly, five patterns of images are summarized according to the factors influencing segmentation. Then the matching relation is established between each image pattern and its optimal segmentationmethod. Next, the given image is classified into one of the five patterns by the multi-classification model based on BP neural network. Finally, the optimal segmentation method for this image is selected according to the matching relation, and then the image is effectively segmented. Experiments show that the proposed method delivers better accuracy and more robust segmentation results compared with the other seven state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Adaptive segmentation based on multi-classification model for dermoscopy images

Xie

et al. 2015

Front. Comput. Sci.

View full text Add to dashboard Cite

show abstract

“…In Maeda et al [10] and Silveira et al [12], the fuzzy method, combined with both splitting and merging techniques, was used to segment dermoscopy images. This combination, originally proposed by Maeda et al [87,88], generates an algorithm for the unsupervised perceptual segmentation of natural colour images using a fuzzybased homogeneity measure, which performs the fusion of colour and texture features. The algorithm includes four steps: simple splitting, local merging, global merging and boundary refinement.…”

Section: Segmentation Based On Artificial Intelligencementioning

confidence: 99%

Computational methods for the image segmentation of pigmented skin lesions: A review

Oliveira

Filho

et al. 2016

Computer Methods and Programs in Biomedicine

204

View full text Add to dashboard Cite

show abstract

“…Observation 2 states that, among the color changes, only those belonging to a lesion boundary are important in image segmentation, and color changes inside a lesion or in the background should be ignored. We transform our images that are in RGB color coordinates into images that are in CIELAB or CIE 1976 L*a*b* color coordinates [14]. CIELAB is a color space standardized by the CIE (Commission Internationale de l'E´ clairage) in 1976 to measure color differences.…”

Section: Preprocessingmentioning

confidence: 99%

“…Therefore, we will move an initial boundary pixel to the pixel in its neighborhood having a locally maximum gradient magnitude. Region boundaries in an image are best described by pixels with locally maximum gradient magnitudes [14][15][16][17]. Pixels with locally maximum gradient magnitudes can be determined without any user interaction; therefore, the process is automatic.…”

Section: Region Refinementmentioning

confidence: 99%

Automatic Segmentation of Skin Melanoma Images Using Hybrid Method

Kaur¹,

Joshi²

2017

IJARCSSE

View full text Add to dashboard Cite

Melanoma is a cancerous lesion in the pigment-bearing basal layers of the epidermis and is the most deadly form of skin cancer, yet it is also the most treatable, with a cure rate for early-stage melanoma of almost 100%. Therefore, there is a need to develop computer-aided diagnostic systems to facilitate the early detection of melanoma. The first step in these systems is skin lesion segmentation. The next essential step is feature extraction and pattern analysis procedures to make a diagnosis. According to the literature, pigment network or reticular pattern is an important diagnostic parameter for melanoma. We decided to work on this automatic melanoma detection system. In this work a brief study has been carried out about the existing segmentation methods adopted by different scholars and a neural network based method is presented for effective segmentation of the melanoma images. In previous work, various methods i.e. Region refinement, adaptive thresholding (AT), gradient vector flow (GVF),adaptive snake (AS);fuzzy-based split-and-merge algorithm (FBSM), k-nearest neighbor, k-means, log filtering etc. has been proposed for the segmentation of melanoma images but their drawback is improper segmentation and more complexity and calculation time . Our method uses testing and training property of neural networks in which a neural object has been created by training it with normal skin and lesion pixels and then same object is used for segmenting other images having similar intensity values. Experimental results shows better results in terms of accuracy values of final segmentation.

show abstract

Number-Driven Perceptual Segmentation of Natural Color Images for Easy Decision of Optimal Result

Cited by 8 publications

References 12 publications

Adaptive segmentation based on multi-classification model for dermoscopy images

Adaptive segmentation based on multi-classification model for dermoscopy images

Computational methods for the image segmentation of pigmented skin lesions: A review

Automatic Segmentation of Skin Melanoma Images Using Hybrid Method

Contact Info

Product

Resources

About