Invention Grant
US08811684B2 Image recognition method 有权
图像识别方法

Image recognition method
Abstract:
The present invention provides an image recognition method for recognizing a plurality of objects in an image, wherein each object is composed of a plurality of image segments. The image recognition method includes the steps of: sequentially acquiring every pixel of the image; identifying a start point of a newly detected image segment; recording information of the newly detected image segment pixel-by-pixel from the start point; identifying an end point of the newly detected image segment; recognizing an object to which the newly detected image segment belongs according to the start point and the end point of the newly detected image segment; and identifying an invalid object or a merged object thereby releasing the data space thereof.
Public/Granted literature
Information query
Patent Agency Ranking
0/0