Computer Science – Computer Vision and Pattern Recognition
Scientific paper
2010-09-06
Skin Research and Technology 15 (2009) 314-322
Computer Science
Computer Vision and Pattern Recognition
Scientific paper
10.1111/j.1600-0846.2009.00357.x
Background: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Due to the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. Methods: In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Results: The method is tested on a set of 428 dermoscopy images. The localization error is quantified by a metric that uses dermatologist determined borders as the ground truth. Conclusion: The results demonstrate that the method presented here achieves both fast and accurate localization of lesions in dermoscopy images.
Celebi Emre M.
Iyatomi Hitoshi
Schaefer Gerald
Stoecker William V.
No associations
LandOfFree
Approximate Lesion Localization in Dermoscopy Images does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Approximate Lesion Localization in Dermoscopy Images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Approximate Lesion Localization in Dermoscopy Images will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-299237