| 摘要 |
A method and system for categorizing non-textual subject data (14), such as digitial images (20), content-based based data and meta-data (16) to determine outcomes of classification tasks. The meta-data (16) is indicative of the operational conditions of a recording device (12) during capturing of the content-based data. For example, the non-textual subject data (14) may be a digital image (20) captured by a digital camera (22), and the meta-data (16) may include automatic gain setting, film speed, shutter speed, aperture/lens index, focusing distance, date and time, and flash/no flashoperation. The subject image (14) is tagged with selected classifiers by subjecting the image to a series of classification tasks utilizing both content-based data and meta-data (16) to determine classifiers associated with the subject image (14). |
