On July 18, 2013, the US Patent & Trademark Office published a patent application from Apple that generally relates to the field of image processing. More particularly, but not by way of limitation, it relates to techniques for determining an orientation of an image via the use of image processing techniques, such as face detection and optical character detection (OCD). In a nutshell, Apple's patent covers improved techniques for device display orientation that are in the works.
A Quick Overview of Apple's Invention
Apple states that in some scenarios, device positional sensor information may currently prove unreliable in determining the orientation of an iDevice with respect to a captured image. Consider the scenario where the image capture device is lying flat on a table top or other horizontal surface. The force of gravity would be pulling exclusively in the direction of the z-axis if the image capture device were lying on a flat horizontal surface. Thus, if a user rotated their iPhone while it was lying on the flat horizontal surface, image processing routines would be unable to discern whether the image was being held in portrait or landscape orientation via the accelerometer information. This is because the pull of gravity along the x- and y-axes would remain negligible so long as the device was lying flat, no matter how the device was rotated.
Apple's invention is about image orientation detection techniques that are designed to handle the processing of images captured by handheld personal electronic devices oriented in a wide range of positions.
More specifically, the techniques described in Apple's patent filing are for intelligent image orientation determination using image processing techniques such as face detection and optical character detection (OCD) in scenarios where image positional sensor data is unreliable for determining the device's orientation. Once image orientation has been determined, the appropriate image orientation metadata may be stored with the image.
The patent figures noted below cover the following: Patent FIG. 4 illustrates image orientation detection based on face detection data; FIG. 5A illustrates image orientation determination based on optical character detection data; and lastly, patent FIG. 5B illustrates various directional axes passing through the centroid of a text blob.
The techniques disclosed in Apple's patent application are applicable to any number of electronic devices with optical sensors and/or positional sensors, such as digital cameras, digital video cameras, mobile phones, personal data assistants (PDAs), portable music players, as well as laptop, desktop and tablet computer systems.
Apple credits Ralf Brunner as the sole inventor of this patent application which was originally filed in Q1 2012 under number 20130182139. To review the details of this invention, click here.
Patently Apple presents a detailed summary of patent applications with associated graphics for journalistic news purposes as each such patent application is revealed by the U.S. Patent & Trade Office. Readers are cautioned that the full text of any patent application should be read in its entirety for full and accurate details. Revelations found in patent applications shouldn't be interpreted as rumor or fast-tracked according to rumor timetables. About Comments: Patently Apple reserves the right to post, dismiss or edit comments.
New on Patent Bolt this Week