Author/Authors :
Hossein Sarikhani Sharif University of technology - Department of computer engineering, Tehran, Iran , Ebrahim Abdollahian Sharif University of technology - Department of computer engineering, Tehran, Iran , Mohsen Shirpour Sharif University of technology - Department of computer engineering, Tehran, Iran , Alireza Javaheri Sharif University of technology - Department of computer engineering, Tehran, Iran , Mohammad Taghi Manzuri Sharif University of technology - Department of computer engineering, Tehran, Iran
كليدواژه :
repeatability , valley pattern , hill pat-tern , scale invariance , rotation invariance , center of curve , keypoint extraction
چكيده لاتين :
In this paper a method for extracting keypoints from human brain MR images is proposed. These keypoints are obtained based on curved structures in the brain MR images. These keypoints are center of boundaries that are included in a circle and are selected based on gradient of the image. These keypoints and their descriptors are scale and rotation invariant. The proposed method is compared with other well-known methods with repeatability measure and ROC curves. Experimental results show that proposed method performs better than other well-known methods and its advantages is more significant in severe deformations.
