Microsoft Technology Licensing, LLC

Steve J White

Denis Demandolx

Karthik G Anbalagan

Tomasz S M Kasperkiewicz

Douglas Alan Ricard

Sergei S Shinkevich

A system and method are provided for correcting an image captured by a digital image capturing device. The method includes calculating a log of a desired correction value based on sample point and a target value for that point and calculating an approximation to the log of illumination based on an input pixel intensity. The method additionally includes calculating any target pixel intensity value based on the log of the correction value and the approximation to the log of illumination. Image correction tools correct the image to correspond to the target pixel intensity value. The technique may be used to correct the gain of any image and for example, may correct exposure or color balance deficiencies. The technique provides excellent results regardless of the image capturing device.

System and method for automated correction of digital images

A method is provided for correcting undesired eye color in a digital image. Color information from the digital image is used to identify an orthogonal color channel. The orthogonal color channel is a channel corresponding to a color that is orthogonal to the undesired color. Information from the orthogonal color channel is used to perform channel mixing. The channel mixing is selectively applied to the original digital image using a masking effect to retain certain portions of the original image and replace certain portions of the original image with the channel-mixed image. This method achieves natural-looking black pupils and preserves specular reflections to conceal the fact that the digital image has been corrected.

Correcting eye color in a digital image

A unified method for processing Raw and pre-processed digital images is provided. The method may include receiving digital image data and determining if the data is Raw or pre-processed. If the digital image data is Raw, the method may further include receiving modifications to the Raw image data, applying a sensor profile and an output profile to the data to create output-ready digital image data, and outputting the output-ready digital image data. If, on the other hand, the digital image data is pre-processed, the method may further include receiving a sensor profile that has been applied to the pre-processed image data (or a proxy therefore), converting the pre-processed image data to linear image data using the sensor profile, receiving modifications to the linear image data, applying the sensor profile and an output profile to the data to create output-ready digital image data, and outputting the output-ready digital image data.

Growing community of inventors

Seattle, WA, United States of America

Steve J White