Stories
Slash Boxes
Comments
typodupeerror delete not in

Book Reviews

Recent reviews from Slashdot readers:

Submitting a review for consideration is easy; please first read Slashdot's book review guidelines. Updated: 2008114 by samzenpus

Comments: 125 +-   HP Restores Creased Photos With Flatbed Scanners on Wednesday August 12, @01:04PM

Posted by timothy on Wednesday August 12, @01:04PM
from the but-can-they-restore-my-boorish-charm? dept.
graphics
software
hp
inputdev
technology
An anonymous reader writes "Scientists at HP have developed a technique to detect creases in photographs using standard, unmodified flatbed scanners. Once correctly scanned into a computer, software can determine where the photograph's defect is, and artificially correct it to remove any trace of a crease or fold. The result is a spotless JPEG scan from a creased photo, with absolutely no modified hardware and no technical know-how required on the part of the user." They're using multiple light sources to do this, in a way that reminds me of last year's description of 3D image creation using an ordinary digital camera.
story

Related Stories

This discussion has been archived. No new comments can be posted.
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
 Full
 Abbreviated
 Hidden
More
Loading... please wait.
  • Nice (Score:5, Funny)

    by thewils (463314) on Wednesday August 12, @01:07PM (#29041435) Journal

    A fold-less centerfold :)

  • Wait, wait (Score:5, Funny)

    by sottitron (923868) on Wednesday August 12, @01:07PM (#29041439)
    Won't this ruin my collection of photographs of creased paper?
  • !unmodified (Score:3, Interesting)

    by muyla (1429487) on Wednesday August 12, @01:09PM (#29041471)

    In the article it says that they use an unmodified scanner, but later on they claim to control the lights of the scanner individually... how is this not modifing the hardware?

    • Modification implies a hardware change. Using lights individually is simply a new way to use something. Does not imply a hardware change.

      • Re: (Score:2, Informative)

        Yeah, but I'm guessing there was no reason for the scanners to come with individual controls for each light before this technology

        • There's also no reason for them to include the switches for each light in hardware when they can do it in firmware.
        • Contrast control, avoiding light pollution in the sensors when scanning an undersized object, lamp longevity, improved support for scanning coarse film grain photographs, glare reduction on shiny objects...

          I could think of a few.

    • Re: (Score:3, Informative)

      From a different FA: [newscientist.com]

      Now Malzbender's team has achieved the same effect using an off-the-shelf flatbed scanner. They rely on the fact that modern scanners use two separate light bulbs. This feature was added to scanners to improve colour quality, but it also lets you capture the image from two different angles. Re-scanning the object after rotating it 90 degrees provides a total of four different angles, more than enough to deduce 3D information about the object - mathematically, you only need three.

      To fix

  • nothing worse than scanned centerfold porn. porn-wise, i mean. (:
  • Not really (Score:5, Insightful)

    by Radagast (2416) on Wednesday August 12, @01:14PM (#29041549) Homepage

    I was hoping they were using that 3D information to do something interesting to actually restore the image. They're not.

    They're basically using rudimentary 3D information that they can get out of the scanner to determine that a crease exists. They then remove it with a simple infill algorithm, which is as basic as it gets (although it often works ok), and which you can find in most image editing software. It's no coincidence that the example image they use has a crease going over mostly similarly colored and low-detail areas.

    So what they're doing is not an improvement to restoration, it's just an improvement to defect detection. Basically, it saves you having to tell the software where the defect to be fixed is, the fixing is the same quality as it's always been.

    • Re: (Score:3, Interesting)

      Could still save some people a lot of money. I did some consulting a while back for a company that, among other things, digitises archives. Libraries send them books and they scan them then manually open each file, draw a line along the curve of the page, and then let the machine deform the image to remove the curve along the line of the text. This step takes several times longer than the scanning phase to do well. If a machine can recognise the creases then they can get rid of the humans in this proces
      • Just use the Google method, of course there is the little problem of it being patented.

    • If the crease did not destroy image detail (a creased Polaroid instant picture often gets nondestructive creases) this could remove warping and glare problems.
    • So what they're doing is not an improvement to restoration, it's just an improvement to defect detection.

      That's still helpful, isn't it? It seems to me that part of the problem with any algorithm to automatically fix photos is that you have to make sure the software knows the difference between a defect and a detail. If it detects what it thinks is a crease or a scratch, but it's really part of the image, it might edit out something you don't want it to.

  • . . . found ONLY along the crease, then they can't interpolate what was there. Period. This is just an improved version of the various touch-up tools in Photoshop etc.
    • Strictly speaking that's true, although some really smart software could restore the original image with high probability, given that almost all real-world images contain certain predictable elements such as faces, grass, clouds, etc. If I give you a picture of the President's face with a little bit torn out, there are many other images where you can find most of the information that was almost certainly there. Now is it possible something novel was actually happening at that point on his face at the time?
  • by bugnuts (94678) on Wednesday August 12, @01:17PM (#29041597) Journal

    The rudimentary 3D info can be used for improving all sorts of scans.

    How about...

    - Flattening a scan of a book (by the spine)
    - Focusing an area that's raised (products like Focus magic [focusmagic.com] assume a section is all out of focus at the same level, whereas a map of the amount of lost focus is possible here).
    - Using the above, scanning non-flat items.
    - Scanning nearly-flat 3d surfaces.

    Add a lens that can vary focus (based on the light differential) and you'd have a good 3D scanner for one side of a mostly-flat item, and a flatbed scanner that wouldn't lose focus on slightly-raised papers.

  • by gurps_npc (621217) on Wednesday August 12, @01:23PM (#29041685)
    What we really need is a copy machine/scanner that can detect the valley formed by the spine of a book being copied and automatically correct for it. That would be worth it.
  • Applied Science Fiction was the first company to successfully market this as a 'dust and scratches' solution.

    Same idea, taken to a new level. Now, I hope HP's management is smart enough to get out of the way and bring this to market. It should definitely sell a few more scanners.

  • by Animats (122034) on Wednesday August 12, @01:29PM (#29041771) Homepage

    Multiple light sources offer some interesting options. A few years ago, someone modified a digital camera (I think a Canon PowerShot) to have four flash sources instead of the usual one. The camera would take four pictures in quick succession, one with each flash. This allowed better edge detection.

    It was useful for applications like taking a picture of complex, dirty machinery (as under a car hood) and locating the edges, even where everything was roughly the same shade. It also helped when photographing very shiny objects, where the reflection from the flash was a problem. With each reflection from each flash unit in a different place, all reflections could be removed.

    It was too specialized to become mainstream, though. That seems to be the fate of 3D from 2D systems. Good ones have been built [canoma.com], but most have been either discontinued or turned into very expensive products for specialized use.

    • Re: (Score:2, Interesting)

      There will soon be much less need for 3D from 2D hacks, because there's a new technology coming that produces 3D pictures directly: Time-of-flight cameras [wikipedia.org]. Today they are really expensive but they're going to become much cheaper very soon. This is what XBox's Project Natal is based on.

  • by vandelais (164490) on Wednesday August 12, @01:29PM (#29041773)

    since it will restore the upskirt I took of Carly Fiorina that I accidentally creased.

  • I don't have any creased photos that I need to restore, but I've got boxes of matte finish prints that are a pain to scan. I wonder if a similar technique couldn't be used to automatically remove the scanning artifacts (little regularly-spaced crescent moon shapes) from those.

  • Do you suppose HP will be nice consumer-friendly guys and update their PrecisionScan software for previous scanner models? Nope: they'll roll this feature into software that'll only work with new scanners they wanna sell you. So, even though it doesn't REQUIRE new hardware, you can bet they'll figure out how to restrict it so that you still have to buy new hardware in order to use it.

  • .. would like to patent the concept of removing the creases from a newspaper by ironing it under a dry towel.

  • Scientists invented the wheel too but I don't want to see it posted on Slashdot. Seriously, isn't this really old news? Removing creases in photos was one of the first things I remember everybody doing when scanners went mainstream sometime in the 80'.s
  • This does nothing to restore creased photographs. What it does is scan the photograph, manipulate the digital image obtained, so that you can print out the image onto another piece of paper. This is not restoring the photograph. The photograph still has a crease in it.

    As a practitioner of traditional photography, I'm annoyed to no end by people who talk as if the concepts of "photograph" and "image" were one and the same. Photographs are unique physical objects that have mass. Speaking as if photographs are
    • Re: (Score:3, Interesting)

      As a practitioner of traditional photography, I'm annoyed to no end by people who talk as if the concepts of "photograph" and "image" were one and the same. Photographs are unique physical objects that have mass. Speaking as if photographs are digital images is like speaking as if symphonies are .mp3 files.

      That's stupid. A traditional print is made from a negative or slide, so by your purist philosophy, restoring the print isn't actually restoring "the photograph." Digital images are photographs and vice versa. What matters is the image, not the medium it is presented on.

      Your idea of the photograph would be considered silly and outdated by the photographers of 50 years ago.

    • Re: (Score:3, Insightful)

      P.S:

      I probably shouldn't have used the term "purist philosophy" to describe your attitude towards photography in my previous post. Because it is neither pure or philosophy. A more apt description would be "nostalgic shortsightedness" or "ludditism."

      The word "photography" at its root, means painting, drawing or writing with light. And "light" is really the key theme, the other root of the word describing "capturing" the light more than anything else. A digital image displayed on a screen that is never printe

    • From the examples shown in the .PDF [hp.com] it seems that it is once again a case of a quick fix that only works on low-res and low detail photos, preferably in single color.

      And for it to work at all, you would need a 2-lamp scanner.
      Which are standard, but in high-quality print studios and other places that would do this kind of retouching by hand anyway in order to preserve or achieve better quality of the final product.

      • Re:Quite so... (Score:5, Insightful)

        by nine-times (778537) <nine.times@gmail.com> on Wednesday August 12, @01:50PM (#29042071) Homepage

        From the examples shown in the .PDF [hp.com] it seems that it is once again a case of a quick fix that only works on low-res and low detail photos, preferably in single color.

        That doesn't seem like a terribly bad thing to me. If you were a professional looking for extremely high-quality results, then yes, you're going to want to spend a lot of time screwing around with things manually on each photo. Even if it's a largely automatic procedure, you'll probably still want to tweak the parameters a little for each photo, including things like brightness, contrast, and hue.

        However, there's another real-world application for this sort of thing: someone like my grandmother scanning lots of old pictures that may have been folded, crumpled, or otherwise damaged. Even if it's not giving the highest quality results, if the results are at all better than not processing the photo, then it's probably fine. Without automatic quick fixes, people might either scan it and leave the damage, or decide not to scan it at all. Giving even barely passable results is an improvement.

      • Re: (Score:3, Informative)

        Which are standard, but in high-quality print studios and other places that would do this kind of retouching by hand anyway in order to preserve or achieve better quality of the final product.

        Actually, most images are restored using digital techniques these days, because it can achieve better results than doing it by hand. You'd only do it by hand if you were talking about something like a historical artifact or unique artwork.

    • Yeah, I was wondering about that too. Really, there is no good excuse to not be using PNG these days.

Kids, the seven basic food groups are GUM, PUFF PASTRY, PIZZA, PESTICIDES, ANTIBIOTICS, NUTRA-SWEET and MILK DUDS!!