When the camera imaging method and the detector array method are used to obtain the laser spot image after atmospheric transmission, the image sequence will contain the actual spot image information and the background information of the test system. During the data processing, the image sequence needs to be segmented to eliminate Image background information firstly. Considering that the brightness, contrast, and structure of the images collected by the system will change significantly before and after the laser irradiation measurement system, a method of image structure similarity is proposed to segment the background information of the image sequence. The method of dynamic template is used to calculate the similarity of the light spot sequence, and the similarity threshold is set to complete the segmentation and elimination of the background information of the image. Experiments show that the background segmentation method of image sequence based on structural similarity can quickly and accurately achieve segmentation of background information. The research results can provide a certain theoretical basis and method accumulation for establishing a perfect data processing method in the laser parameter measurement system.
Because of its high positioning accuracy, easy identification and high stability, circular markers are widely used in patient positioning in the medical field. However, during radiotherapy, the marker points on the patient's body surface are blocked by the thermoplastic film that fixes the patient, which makes it difficult to extract and locate the center of the marker points. Commonly used circular marker positioning algorithms cannot accurately locate the markers when there are a large number of random deletions. Therefore, a marker center positioning algorithm for this situation is needed. First, the image is converted to the HSV color space to extract the landmark points through threshold processing; then the Canny edge detection algorithm is used to extract the edges of the landmarks under the occlusion; then the Graham scanning method is used to obtain the convex hull points of the edge points. Finally, the improved least squares circle fitting algorithm is used to fit the convex hull points to locate the center of the marker. Verified by experiment, the accuracy of this method for extracting the center of the circular marker is within 0.05 pixel, and the positioning accuracy is much higher than that of the gray-scale centroid method under the same circumstances.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.