摘要:
A digital image acquisition system having no photographic film, such as a digital camera, has a flash unit for providing illumination during image capture and a red-eye filter for detecting a region within a captured image indicative of a red-eye phenomenon, the detection being based upon a comparison of the captured image and a reference image of nominally the same scene taken without flash. In the embodiment the reference image is a preview image of lower pixel resolution than the captured image, the filter matching the pixel resolutions of the captured and reference images by up-sampling the preview image and/or sub-sampling the captured image. The filter also aligns at least portions of the captured image and reference image prior to comparison to allow for, e.g. movement in the subject.
摘要:
A method of detecting and correcting an eye defect within an acquired digital image comprising a multiplicity of pixels indicative of color and forming various shapes within the image is disclosed. A probable size distribution of eye regions, if any, in the image is determined using image meta-data and human anthropometric data, the meta-data including information describing conditions under which the image was acquired. A candidate eye region in the image is detected and whether it falls within the size distribution is determined. In respect of a candidate eye region falling within the size distribution, the anthropometric data is used to search for the presence of at least one of a second eye, lips, nostrils and surrounding face. If the search is successful, a probability that the candidate eye defect region is an actual eye region is increased. The candidate eye region is confirmed as an actual eye region if the probability is above a certain threshold. If the confirmed eye region has a color representative of a red-eye defect, the red-eye defect is corrected.