Image preprocessing for character recognition

摘要

Various embodiments provide an image pre-processing method to accelerate image computing tasks. For example, an image is obtained from a camera of a portable computing device. Salient features of the image are identified by a number of techniques, such as identifying feature points, identifying gradients within the image, and other techniques and methods discussed herein. Based at least in part on the identified salient features, a saliency map of the image is computed. The saliency map includes a saliency value for each of at least a portion of the plurality of pixels. In this example pixels above a threshold saliency value are processed with an optical character recognition engine.

主权项

1. A computer-implemented method, comprising
under control of one or more computer system configured with executable instructions,
obtaining image data from a camera of a portable computing device;determining at least one feature point of the image data using a feature point detection algorithm;applying a saliency function to the at least one feature point to determine at least one corresponding saliency value for at least a portion of the image data, wherein the saliency function is a feature point density function programmed to calculate a number of feature points per area, areas with a higher density of feature points having a higher saliency value relative to areas with a lower density of feature points;generating a saliency map of the image data based at least in part on the at least one corresponding saliency value;determining at least one region of the saliency map in which the at least one corresponding saliency value meets or exceeds a saliency threshold value; andselecting the at least one region of the saliency map to be analyzed using a visual recognition component.