Sign in with
Sign up | Sign in

IBM Files Patent to Resize Images Without Artifacts

By - Source: USPTO | B 24 comments

IBM claims to have found a method to increase or decrease the size of digital images better than it is possible today with traditional techniques such as nearest neighbor, bilinear or bicubic resizing.

Even the most sophisticated image editing software does not provide perfect solutions to increase or decrease digital image sizes. Making images smaller results in loss of detail as pixels are eliminated; and an increase, which requires the addition of detail, relies on predictive methods that are rather crude today. With the nearest neighbor interpolation, the software simply adds pixels of the same color, which preserves detail, but impacts smooth shapes.

Bicubic resizing delivers much smoother lines, but quickly drifts into blurring and ugly artifacts. Much more elaborate methods, such as fractal analysis, require enormous computing resources that are generally not practical in consumer applications. In order to address these and other problems, the present invention provides a method and system for resizing a digital image.

According to IBM, there is another image analysis method that can deliver better results than current resizing techniques. The idea is to stretch or shrinks the image along the horizontal and vertical dimensions using two separately calculated scaling vectors, resulting in a scaling matrix.

IBM says that the technique delivers greater accuracy and quality than current methods as missing pixels are not just created from their neighboring pixels or interpolated, but predicted using spatial and frequency transformation of complete rows and complete columns that does not create jaggedness, artifacts or any other aliasing.

The patent did not mention any products this technology will be used in, but hopefully it won't be long before we see it.

Discuss
Display all 24 comments.
This thread is closed for comments
Top Comments
  • 15 Hide
    shin0bi272 , April 27, 2012 3:36 PM
    I wonder if they got this idea from CSI. They seem to be able to pick up a reflection off of someone's eyeball from a camera phone 3 blocks away and just click a couple of buttons and get your license plate #. So Life imitating art I guess.
  • 12 Hide
    freggo , April 27, 2012 3:46 PM
    shin0bi272I wonder if they got this idea from CSI. They seem to be able to pick up a reflection off of someone's eyeball from a camera phone 3 blocks away and just click a couple of buttons and get your license plate #. So Life imitating art I guess.



    As much as I like the CSI/NCIS type shows (having worked in a LAB many years ago myself) but their frequent use of the image 'enhancement' from crappy security footage is getting a bit old.
    It's like the airplane scenes where an engine sputters and the plane immediately goes into a screaming nose dive; which, as a pilot myself, I can assure you is NOT what happens :-).


  • 11 Hide
    Parsian , April 27, 2012 4:00 PM
    freggoAs much as I like the CSI/NCIS type shows (having worked in a LAB many years ago myself) but their frequent use of the image 'enhancement' from crappy security footage is getting a bit old.It's like the airplane scenes where an engine sputters and the plane immediately goes into a screaming nose dive; which, as a pilot myself, I can assure you is NOT what happens :-).


    lol they extremely over estimate the gravity thats why the plane goes down like a delta function
Other Comments
  • 8 Hide
    lahawzel , April 27, 2012 3:36 PM
    "Much more elaborate methods, such as fractal analysis, require enormous computing resources that are generally not practical in consumer applications."

    Isn't this exactly what Perfect Resize does? I have it as a Photoshop plugin and I am able to upscale images to many times their original size and maintain sharp edges with no artifacting. It's pretty fast, too.

    That being said, props to IBM for continuing to actually innovate and push for technological advancement in this day and age. Unlike a certain company that wastes resources patenting ultra-wide touchpads.
  • 15 Hide
    shin0bi272 , April 27, 2012 3:36 PM
    I wonder if they got this idea from CSI. They seem to be able to pick up a reflection off of someone's eyeball from a camera phone 3 blocks away and just click a couple of buttons and get your license plate #. So Life imitating art I guess.
  • 3 Hide
    freggo , April 27, 2012 3:42 PM
    Could there be a Photoshop plugin in the future?
    I'd have a use for this for a number of daily tasks if it
    indeed works better than current resizing methods.
  • 2 Hide
    Parsian , April 27, 2012 3:43 PM
    there is so much one can learn from noise that why noise is so interesting, you can pull a lot of hidden information from noise.
  • 8 Hide
    lahawzel , April 27, 2012 3:44 PM
    shin0bi272I wonder if they got this idea from CSI. They seem to be able to pick up a reflection off of someone's eyeball from a camera phone 3 blocks away and just click a couple of buttons and get your license plate #. So Life imitating art I guess.


    Image upscaling algorithms, no matter how good they get, cannot produce information that is not in the original material. If the entire license plate is only 30-ish pixels in area in the photograph you are processing, it's going to upscale to unintelligible mixes of color, no way around it.

    It's the same with image upscaling; it'll give you a bigger version of the original image, but details not visible in the original image won't be shown in the resultant picture. The SCP-191 testing log from the SCP Foundation, despite being a humor site, explains succinctly why things like Zoom & Enchance, Uncrop, and Rotate Camera don't work.
  • 12 Hide
    freggo , April 27, 2012 3:46 PM
    shin0bi272I wonder if they got this idea from CSI. They seem to be able to pick up a reflection off of someone's eyeball from a camera phone 3 blocks away and just click a couple of buttons and get your license plate #. So Life imitating art I guess.



    As much as I like the CSI/NCIS type shows (having worked in a LAB many years ago myself) but their frequent use of the image 'enhancement' from crappy security footage is getting a bit old.
    It's like the airplane scenes where an engine sputters and the plane immediately goes into a screaming nose dive; which, as a pilot myself, I can assure you is NOT what happens :-).


  • 11 Hide
    Parsian , April 27, 2012 4:00 PM
    freggoAs much as I like the CSI/NCIS type shows (having worked in a LAB many years ago myself) but their frequent use of the image 'enhancement' from crappy security footage is getting a bit old.It's like the airplane scenes where an engine sputters and the plane immediately goes into a screaming nose dive; which, as a pilot myself, I can assure you is NOT what happens :-).


    lol they extremely over estimate the gravity thats why the plane goes down like a delta function
  • 2 Hide
    lamorpa , April 27, 2012 4:25 PM
    LaHawzelImage upscaling algorithms, no matter how good they get, cannot produce information that is not in the original material...

    Humor upscaling algorithms, no matter how good they get, cannot produce comprehension that is not in the original viewer...
  • 6 Hide
    Anonymous , April 27, 2012 4:47 PM
    CSI should file the patent first. HAHAHA.
  • 0 Hide
    serendipiti , April 27, 2012 4:54 PM
    wonder if they are using some kind of fractal compression and decompression to the desired image size. Since fractal compression is somehow lossy (being the good part that you know the amount of loss) seems ironic that an aproximation is the more acurate way (like series in maths?)
  • 2 Hide
    jamie_1318 , April 27, 2012 5:01 PM
    lamorpaHumor upscaling algorithms, no matter how good they get, cannot produce comprehension that is not in the original viewer...


    I think this comment applies to you more than the person you are quoting. He is absolutely correct that you can't get information out that doesn't go in.

    Basically what that means is that there are hard real limits on how much any image can be enhanced, and information that did not make it into the image sensor cannot be extrapolated accurately.

    Is better image enlargement a good thing: of course it is. But most people vastly overestimate the amount of quality you can extrapolate from a picture. Once you work with the kind of pictures most people would want to use this on you will agree with me. Even humans have a really difficult time re-sampling some of this stuff and the obvious problem of artifacts getting enlarged will still exist.

    EDIT, went back and read my quotation. Totally misread that.
  • 0 Hide
    lamorpa , April 27, 2012 5:15 PM
    jamie_1318I think this comment applies to you more than the person you are quoting. He is absolutely correct that you can't get information out that doesn't go in...

    Um, LaHawzel was replying to shin0bi272's comment. LaHawzel was making a serious 'correction' to shin0bi272's joke comment, so I parodied it. Having to explain this means the missing-the-humor applies double to you. :-D
  • 4 Hide
    tntom , April 27, 2012 5:30 PM
    Forget Photoshop! This would be great in 3D graphic textures with Tesselation.
  • 1 Hide
    Anonymous , April 27, 2012 6:49 PM
    Bad article title.....

    You mean "IBM Files Patent to Resize Images With Less Artifacts"

    Producing a perfect scaled up image is impossible. You can predict information that is not there, but you can not ever be certain you've done it perfectly.

    Ill give you an example. Say you have 10 pixels of data in a real sample and an image created from that sample, say a photograph contains 1 pixel for every 10. In the real image you have 9 pixels of perfect blue with a 1 pixel wide red line going through the center of it. The image will have 1 pixel of slightly purple blue.

    No matter what you do with 1 pixel of slightly blue you will NEVER get that red line back. Because you can never be certain if the original image had 1 pixel of red and 9 pixels of blue, or maybe it had 10 pixels of slightly purple blue, or maybe it had 5 pixels of slightly less purple blue and 5 pixels of slightly more purple blue, etc. All of those will combine into the same single color pixel in your source.

    In this example there can be hundreds of millions of possible combinations of original data, all you can do is pick one, and assume its one pixel of slightly purple blue and scale it up....
  • -3 Hide
    koga73 , April 27, 2012 6:50 PM
    not sure how this would work if you scaled the image different amounts in the x and y then your resulting image wouldn't be the same aspect ratio.
  • 5 Hide
    lamorpa , April 27, 2012 7:05 PM
    koga73not sure how this would work if you scaled the image different amounts in the x and y then your resulting image wouldn't be the same aspect ratio.

    Oh yeah. I guess they missed that after years of research. It's not like you misunderstood what was being stated or anything. Back to the drawing board for IBM.
  • 3 Hide
    rumandcoke , April 27, 2012 11:02 PM
    patent invalid due to their choice of language.

    without artifacts - there is no such thing
    what is being described is a better upscaling.

    i suppose since patents don't actually require products to be produced they can use this patent to troll other companies who advertise artifact free upscaling.
  • 0 Hide
    Pherule , April 28, 2012 3:31 PM
    IBM, another patent troll.
  • 0 Hide
    freggo , April 28, 2012 9:37 PM
    jamie_1318...He is absolutely correct that you can't get information out that doesn't go in.Basically what that means is that there are hard real limits on how much any image can be enhanced, and information that did not make it into the image sensor cannot be extrapolated accurately...


    There is one bit of fine print to this that should be included.
    There is a lot of 'information' in an image that is not visually available to the human eye.
    For example; many photos of night skies look like a black picture with a few blinking starts, but if you run them thru Photoshop with an HDR filter and more things become visible.

    What I am trying to say is that you can not 'recover' information that is simply not there, but you can make visible information that -due to it's nature- is not visible to the human eye in it's raw format.

    Still, Abby Sciuto performs a few miracles in her lab; and all in a time frame that has little to do with reality :-)

  • 2 Hide
    bit_user , April 28, 2012 11:42 PM
    > nearest neighbor, bilinear or bicubic resizing

    LOL.

    Anyone who's taken a signal processing class or read a little about it knows that sinc is the theoritically ideal way to resample a band-limited signal.

    In the real world, a Lanczos-windowed sinc tends to work best on digital images.

    Most image scaling filters are separable, meaning they can be implemented as two 1D filters. This dramatically reduces the amount of computation needed, especially for large kernels.

    None of this is even remotely new. More details about IBM's patent would be needed to see what, if anything, is novel.
Display more comments