Selection of adaptive edge-like features during object detection

摘要

A method of recognizing an object of interest in an image includes extracting a first set of features from within the image. Each extracted feature in the first set of features is then classified as either edge-like or blob-like. A second set of features is retrieved from the first set and the number of edge-like features included in the second set of features is compared to an edge for blob-like features included in the first set of extracted features Based on the relative number of features. According to the second set of features, the object of interest in the image is detected.