Method of extracting visual descriptor using feature selection and system for the same

摘要

A method and system for extracting a visual descriptor using a feature selection are provided. The system includes an image input unit configured to receive an image, a candidate feature point group detecting unit configured to detect a point having a local maximum or minimum of local region filtering in scale-space images as being included in a candidate feature point group, a feature point selecting unit configured to calculate an importance for each candidate feature point, depending on its characteristics, select the candidate feature point as a feature point when its importance is greater than the predetermined threshold value, a dominant orientation calculating unit configured to calculate a dominant orientation of the selected feature point and a visual descriptor extracting unit configured to extract a patch for each feature point, according to its scale, location and dominant orientation, and extract a visual descriptor from the patch.

主权项

1. A system for extracting a visual descriptor using a feature selection, the system comprising:
an image input unit configured to receive an image; a candidate feature point group detecting unit configured to detect a point having a local maximum or minimum of local region filtering in scale-space images as being included in a candidate feature point group; a feature point selecting unit configured to calculate an importance for each candidate feature point included in the candidate feature point group, depending on characteristics of the candidate feature point, select the candidate feature point as a feature point when the importance of the candidate feature point is greater than the predetermined threshold value, and delete the candidate feature point when the importance of the candidate feature point is not greater than the predetermined threshold value; a dominant orientation calculating unit configured to calculate a dominant orientation of the feature point selected by the feature point selecting unit; and a visual descriptor extracting unit configured to extract a patch for each feature point selected by the feature point selecting unit, according to scale, location and dominant orientation of the feature point, and extract a visual descriptor from the patch, wherein the dominant orientation calculating unit is configured to: receive a scale-space layer and feature points detected from the scale-space layer; for each scale space layer in scale space images, calculate a dominant orientation of the feature point after calculating a gradient map of the scale-space layer when the number of the feature points detected from the scale-space layer is larger than or equal to the a threshold value; and calculate a dominant orientation of the feature point by direct calculation of gradient without gradient map when the number of the feature points detected from the scale-space layer is below the threshold value.