|
|
Journal of Medical Signals and Sensors، جلد ۴، شماره ۲، صفحات ۱۲۲-۰
|
|
|
| عنوان فارسی |
|
|
| چکیده فارسی مقاله |
|
|
| کلیدواژه‌های فارسی مقاله |
|
|
| عنوان انگلیسی |
Vessel Segmentation in Retinal Images Using Multi-Scale Line Operator and K-Means Clustering |
|
| چکیده انگلیسی مقاله |
Detecting blood vessels is an important task in retinal image analysis. The task is more challenging with the presence of bright and dark lesions in retinal images. Here, a method is proposed to detect vessels in both normal and abnormal retinal fundus images based on their linear features. First, the negative impact of bright lesions is reduced by using k-means segmentation in a perceptive space. Then, a multi-scale line operator is utilized to detect vessels while ignoring most of the dark lesions, which have intensity structures different from the line-shaped vessels in retina. The proposed algorithm is tested on two publicly available STARE and DRIVE databases. The performance of the method is measured by calculating the area under the receiver operating characteristic (ROC) curve and the segmentation accuracy. The proposed method achieves 0٫9483 and 0٫9387 localization accuracy against STARE and DRIVE respectively. |
|
| کلیدواژه‌های انگلیسی مقاله |
|
|
| نویسندگان مقاله |
وحید محمدی صفارزاده | vahid mohammadi saffarzadeh
علیرضا عصاره | alireza osareh
بیتا شادگار | bita shadgar
|
|
| نشانی اینترنتی |
http://www.jmss.mui.ac.ir/index.php/jmss/article/view/172 |
| فایل مقاله |
فایلی برای مقاله ذخیره نشده است |
| کد مقاله (doi) |
|
| زبان مقاله منتشر شده |
en |
| موضوعات مقاله منتشر شده |
|
| نوع مقاله منتشر شده |
Original Articles |
|
|
|
برگشت به:
صفحه اول پایگاه |
نسخه مرتبط |
نشریه مرتبط |
فهرست نشریات
|