Texture-less object recognition using contour fragment-based features with bisected local regions

摘要

The present invention relates to an object recognition method using a contour division based feature having a bisected local region. According to the present invention, there is provided a method of recognizing an object using a contour division based feature having a divided local region, the method comprising: receiving image data and recognizing a shape of the object in the image data; Detecting an outline in an object recognized in the image data, and extracting a feature point based on a contour division basis of each object; A feature descriptor for a feature point extracted from a contour division basis of each object is calculated on a local area divided along a normal line based on a contour division; Defining a new pair descriptor between the feature descriptors for the feature point; Calculating a pair descriptor vector corresponding to the pair descriptor; Performing spectral matching between the extracted model data and the image data for the contour division based object; And improving the spectral match resu .