METHOD OF EXTRACTING TEMPORAL AND SPATIAL COMBINATION MARKERS FOR MORPHOLOGICAL IMAGE DIVISION

摘要

1. the art that the invention defined in the claims; The present invention relates to a process will extract space-time binding markers.; 2. The invention attempts to solve the technical challenges; The present invention is image segmentation visually possible to sense the marker extraction with a, and more accurate and meaningful when using the extracted space-time binding marker to the blanket logical segmentation By extracting the marker using a spatial and time information at the same time that aims to provide a space-available markers combined extraction methods.; 3. Resolution of the subject matter of the invention,; The present invention, a first step for extracting a marker area by using spatial information from the video frame after quantization and simplifying the current image frame; A second step of extracting a current image frame and the previous image frame by using the time information from the time marker; And by combining the spatial markers and wherein the time markers extracted from the second extraction step in the first step and a third step of extracting a combined space-time marker.; 4. An important use of the invention,; The present invention is used to fight the watershed algorithm, when the logical partition blanket video.