公开(公告)号：US08073290B2

公开(公告)日：2011-12-06

申请号：US11815449

申请日：2006-01-31

Applicant: Toni Werner Vomweg ,  Heiner Faber ,  Dirk Mayer

Inventor： Toni Werner Vomweg ,  Heiner Faber ,  Dirk Mayer

IPC: G06K9/00

CPC classification number: G06T3/0075 ,  G06T7/33 ,  G06T7/38 ,  G06T2207/30068

Abstract: A method of registering biomedical images to reduce imaging artifacts caused by object movement is disclosed, wherein a certain number of features or landmarks is automatically defined and tracked in a first and second image to be registered to determine the optical flow vector between the first and second image. Registration then takes place by applying the inverse optical flow to the second image. The automatic feature selection step is carried out by determining the mean signal intensity in a defined neighborhood for every pixel, which mean signal intensity is then compared to a predetermined threshold. If the mean signal intensity value of said neighborhood is higher than the predetermined threshold the pixel is defined as a feature and is added to a list of features to be tracked.

Abstract translation: 公开了一种记录生物医学图像以减少由物体运动引起的成像伪像的方法，其中在要注册的第一和第二图像中自动定义和跟踪一定数量的特征或标志，以确定第一和第二图像之间的光学流动矢量 图片。 然后通过将逆光流应用于第二图像来进行登记。 自动特征选择步骤通过确定每个像素的限定邻域中的平均信号强度来进行，这意味着信号强度然后与预定阈值进行比较。 如果所述邻域的平均信号强度值高于预定阈值，则将像素定义为特征，并将其添加到要跟踪的特征列表。

公开(公告)号：US20080292214A1

公开(公告)日：2008-11-27

申请号：US11815449

申请日：2006-01-31

Applicant: Toni Vomweg ,  Heiner Faber ,  Dirk Mayer

Inventor： Toni Vomweg ,  Heiner Faber ,  Dirk Mayer

IPC: G06K9/00 ,  G06K9/32

CPC classification number: G06T3/0075 ,  G06T7/33 ,  G06T7/38 ,  G06T2207/30068

Abstract: A method of registering biomedical images to reduce imaging artefacts caused by object movement is disclosed, wherein a certain number of features or landmarks is automatically defined and tracked in a first and second image to be registered to determine the optical flow vector between the first and second image. Registration then takes place by applying the inverse optical flow to the second image. The automatic feature selection step is carried out by determining the mean signal intensity in a defined neighborhood for every pixel, which mean signal intensity is then compared to a predetermined threshold. If the mean signal intensity value of said neighborhood is higher than the predetermined threshold the pixel is defined as a feature and is added to a list of features to be tracked.

Abstract translation: 公开了一种登记生物医学图像以减少由物体运动引起的成像伪影的方法，其中在要注册的第一和第二图像中自动定义和跟踪一定数量的特征或界标，以确定第一和第二图像之间的光学流动矢量 图片。 然后通过将逆光流应用于第二图像来进行登记。 自动特征选择步骤通过确定每个像素的限定邻域中的平均信号强度来进行，这意味着信号强度然后与预定阈值进行比较。 如果所述邻域的平均信号强度值高于预定阈值，则将像素定义为特征，并将其添加到要跟踪的特征列表。