Automatic tumor segmentation of breast ultra-sound images using a distance-regularized level-set evolution method with initial contour obtained by guided image filter, L0 gradient minimization smoothing pre-processing, and morphological features
碩士 === 國立清華大學 === 電機工程學系所 === 105 === Due to the speckle noise and low contrast in breast ultrasound images, it is hard to locate the contour of the tumor by using a single method. In this thesis, a new method for finding an initial contour is proposed, which can improve the result of DRLSE on the s...
Main Authors: | Hsieh, Hsun, 謝 洵 |
---|---|
Other Authors: | Jong, Tai-Lang |
Format: | Others |
Language: | zh-TW |
Published: |
2017
|
Online Access: | http://ndltd.ncl.edu.tw/handle/t6z6cs |
Similar Items
-
Automatic tumor segmentation of ultra-sound breast images using a distance-regularized level-set evolution method with initial contour based on morphology
by: Niu, Tsai Wen, et al.
Published: (2016) -
Contour evolution scheme for variational image segmentation and smoothing
by: Mahmoodi, Sasan, et al.
Published: (2007) -
SAR Image Coastline Detection Based on Regional Distance Regularized Geometric Active Contour Models
by: JIANG Dawei, et al.
Published: (2016-09-01) -
Improved L0 Gradient Minimization with L1 Fidelity for Image Smoothing.
by: Xueshun Pang, et al.
Published: (2015-01-01) -
Medical Image Automatically Retrieves The Contours Of Bone Images
by: Shin-Hao Chen, et al.
Published: (2008)