Detecting Orientation of Digital Images Using Face Detection Information

Abstract

A method of automatically establishing the correct orientation of an image using facial information. This method is based on the exploitation of the inherent property of image recognition algorithms in general and face detection in particular, where the recognition is based on criteria that is highly orientation sensitive. By applying a detection algorithm to images in various orientations, or alternatively by rotating the classifiers, and comparing the number of successful faces that are detected in each orientation, one may conclude as to the most likely correct orientation. Such method can be implemented as an automated method or a semi automatic method to guide users in viewing, capturing or printing of images.

What is claimed is: 
     
         1 . A method of enhancing a digital image using statistical classifier techniques, comprising:
 using a processor;   acquiring a first digital image;   detecting an object within the first digital image;   generating in-camera, capturing or otherwise obtaining in-camera a collection of further digital images including said object captured at different times than said first digital image;   tracking said object within said collection of further images;   applying a set of object detection classifiers to the first digital image and at least one image of the collection of further images;   determining that at least one of said further digital images has a greater probability of comprising a higher level of match to a desired image parameter than said first digital image; and   generating a re-composited first digital image including replacing said object within said first digital image with said object from said at least one further digital image captured respectively at said different times.   
     
     
         2 . The method of  claim 1 , further comprising cropping the first digital image including selecting an object region that includes said object within the first digital image and excludes one or more regions of the first digital image outside of said object region to obtain a cropped image including the object region. 
     
     
         3 . The method of  claim 1 , further comprising detecting a second object within the first digital image; and wherein said generating said re-composited first digital image further includes maintaining said same second object within said re-composited first digital image. 
     
     
         4 . The method of  claim 3 , wherein the tracking said object comprises tracking both the object and the second object respectively continuing to identify, in one or more subsequently captured digital images of the further digital images, the object and the second object as corresponding to the object and the second object captured within the first digital image at said different times. 
     
     
         5 . The method of  claim 1 , further comprising automatically adjusting focus position based upon detecting that the focus position of the object t has changed based on movement between two or more of the first and further digital images captured at said different times. 
     
     
         6 . The method of  claim 1 , wherein said collection of further images comprises relatively low resolution images compared with said first digital image. 
     
     
         7 . The method of  claim 1 , wherein said object comprises a face. 
     
     
         8 . One or more non-transitory computer readable storage devices having processor readable code embodied thereon, said processor readable code for programming one or more processors to perform a method of enhancing a digital image using statistical classifier techniques, wherein the method comprises:
 detecting an object within a first digital image;   generating in-camera, capturing or otherwise obtaining in-camera a collection of further digital images including said object captured at different times than said first digital image;   tracking said object within said collection of further images;   applying a set of object detection classifiers to the first digital image and at least one image of the collection of further images;   determining that at least one of said further digital images has a greater probability of comprising a higher level of match to a desired image parameter than said first digital image; and   generating a re-composited first digital image including replacing said object within said first digital image with said object from said at least one further digital image captured respectively at said different times.   
     
     
         9 . The one or more non-transitory computer readable storage devices of  claim 8 , wherein the method further comprises cropping the first digital image including selecting an object region that includes said object within the first digital image and excludes one or more regions of the first digital image outside of said object region to obtain a cropped image including the object region. 
     
     
         10 . The one or more non-transitory computer readable storage devices of  claim 8 , wherein the method further comprises detecting a second object within the first digital image; and wherein said generating said re-composited first digital image further includes maintaining said same second object within said re-composited first digital image. 
     
     
         11 . The one or more non-transitory computer readable storage devices of  claim 10 , wherein the tracking said object comprises tracking both the object and the second object respectively continuing to identify, in one or more subsequently captured digital images of the further digital images, the object and the second object as corresponding to the object and the second object captured within the first digital image at said different times. 
     
     
         12 . The one or more non-transitory computer readable storage devices of  claim 8 , wherein the method further comprises automatically adjusting focus position based upon detecting that the focus position of the object t has changed based on movement between two or more of the first and further digital images captured at said different times. 
     
     
         13 . The one or more non-transitory computer readable storage devices of  claim 8 , wherein said collection of further images comprises relatively low resolution images compared with said first digital image. 
     
     
         14 . The one or more non-transitory computer readable storage devices of  claim 8 , wherein said object comprises a face. 
     
     
         15 . A digital image acquisition device, comprising:
 one or more optics and a sensor for acquiring a digital image,   a processor, and   one or more processor readable storage devices having processor readable code embodied thereon for programming the processor to perform a method of enhancing a digital image using statistical classifier techniques, wherein the method comprises:
 acquiring a first digital image; 
 detecting an object within the first digital image; 
 generating in-camera, capturing or otherwise obtaining in-camera a collection of further digital images including said object captured at different times than said first digital image; 
 tracking said object within said collection of further images; 
 applying a set of object detection classifiers to the first digital image and at least one image of the collection of further images; 
 determining that at least one of said further digital images has a greater probability of comprising a higher level of match to a desired image parameter than said first digital image; and 
 generating a re-composited first digital image including replacing said object within said first digital image with said object from said at least one further digital image captured respectively at said different times. 
   
     
     
         16 . The digital image acquisition device of  claim 15 , wherein the method further comprises cropping the first digital image including selecting an object region that includes said object within the first digital image and excludes one or more regions of the first digital image outside of said object region to obtain a cropped image including the object region. 
     
     
         17 . The digital image acquisition device of  claim 15 , wherein the method further comprises detecting a second object within the first digital image; and wherein said generating said re-composited first digital image further includes maintaining said same second object within said re-composited first digital image. 
     
     
         18 . The digital image acquisition device of  claim 17 , wherein the tracking said object comprises tracking both the object and the second object respectively continuing to identify, in one or more subsequently captured digital images of the further digital images, the object and the second object as corresponding to the object and the second object captured within the first digital image at said different times. 
     
     
         19 . The digital image acquisition device of  claim 15 , wherein the method further comprises automatically adjusting focus position based upon detecting that the focus position of the object t has changed based on movement between two or more of the first and further digital images captured at said different times. 
     
     
         20 . The digital image acquisition device of  claim 15 , wherein said collection of further images comprises relatively low resolution images compared with said first digital image. 
     
     
         21 . The digital image acquisition device of  claim 15 , wherein said object comprises a face. 
     
     
         22 . The digital image acquisition device of  claim 15 , comprising a cell phone equipped with a digital camera.