Joint dictionary generation method for image processing, interlace-based high dynamic range imaging apparatus using joint dictionaries and image processing method of the same

The joint dictionary generation method of claim wherein the first data comprises image patches sampled from a first image frame which was captured, and the second data comprises image patches sampled from a second image frame generated by adding interlace artifacts or noise to the first image frame.

An HDR (High Dynamic Range) imaging apparatus comprising:

• a reconstructing circuit configured to remove interlace artifacts and noise from a high-exposure RGB frame and a low-exposure RGB frame, using joint dictionaries generated through joint dictionary learning on training data sets each containing a plurality of bases, wherein the plurality of bases of one training data set correspond one-to-one to those of the other training data set, but the corresponding bases have different values;
• and
• an HDR generation circuit configured to generate an HDR image frame by combining the high-exposure RGB frame and the low-exposure RGB frame from which interlace artifacts and noise were removed by the reconstructing circuit.

An HDR image processing method comprising:

• removing interlace artifacts and noise from a high-exposure RGB frame and a low-exposure RGB frame, by using joint dictionaries generated through joint dictionary learning on training data sets each containing a plurality of bases, wherein the plurality of bases of one training data set correspond one-to-one to those of the other training data set, but the corresponding bases have different values;
• and
• generating an HDR image frame by combining the high-exposure RGB frame and the low-exposure RGB frame from which interlace artifacts and noise are removed.