Robustness enhancement and evaluation of image information extraction

摘要

A method for recognition of features appearing in an input image includes upsampling the input image to generate an enlarged image including an increased number of pixels relative to the input image. The enlarged image is decimated to generate a plurality of intermediate images, each of the intermediate images including a different subset of the pixels in the enlarged image. An image recognition algorithm is applied to the intermediate images so as to generate respective recognition results, which are compared to generate an identification of the features appearing in the input image.