Here’s
another Microsoft internal newsletter about some pretty cool techniques from Microsoft
Research that have been integrated into Microsoft’s new Digital Image software.
IMHO, there’s just no decent imaging software. I was a huge Jasc Software
Paint Shop Pro 6 fan. That’s version 6, mind you. It was a fantastic
editor. It had powerful techniques ala Photoshop with a simple and elegant interface.
Later versions became far to complex with a schizophrenic move towards supporting
both vectors and rasters and layers in one confusion interface littered with toolbars
and toolboxes.
Photoshop
is too advanced for the average user, Paint is joke. The original Microsoft
Digital Image Suite was a train-wreck called “Picture-It” that had the
unfortunate habit of crashing by disappearing. You know these special crashes…no
Doctor Watson, just -poof-, gone.
The
new Adobe PhotoAlbum suite has some pretty impressive organizational skills, most
associating event and subject tags around the time the photo was taken. But,
will Microsoft get it right this time with a little help from Microsoft Research?
Side
Note: It would be nice
if Microsoft would decide what App or Applet should be used to view JPEGS. I’m
writing this post on a fairly fresh Tablet PC, and I’m presented with this menu
when right-clicking a JPEG:
Ok,
so I can open it in the “Windows Picture and Fax Viewer” – hm, I
open pictures a LOT more than Faxes. I’ve also got Paint. Hm, then
IE. Also the Microsoft Office Picture Manager which is a GREAT tool, but: 1.
it is relegated to the never used “Office Tools” program group, and 2.
it doesn’t associate itself with graphic files until you run it once…but
you have to discover it before you can run it! Seems since Microsoft is so gung-ho
on Digital Photography, that someone should organize a Unified Front within the org
and work this out.
-Scott
History is being
written in a new way. It is being written by people through the big and the small
events in their lives. We write history through personal Web sites, discussion boards,
and the legacy of photos, taken
at moments that are important to us.
Researchers at
Microsoft have been working on a wide range of technologies that will help people
write their personal histories through digital photography. To tell any history, it's
best to start at the beginning, and move forward.
In the beginning,
you buy a digital camera, take a quick look at the manual, throw it to the side, and
start pushing buttons. Digital photography has made it possible to take an almost
endless number of photos. Some of these photos are good; some get deleted before anyone
else sees them. Many of them are almost good, with a little tweaking they'd be just
fine.
Adjustable
Light
A common problem with digital photography is lighting. Photos turn out either too
light or too dark. Since digital cameras allow us to take lots of shots without running
out of film, we're willing to throw away a lot of the bad shots. But if you want to
take a great picture, it might be nice to be able to control the lighting without
purchasing professional lighting equipment.
One of the research
projects at Microsoft Research is called Continuous Flash. This technology allows
you to take the same picture with flash and without flash and later adjust the balance
between light and dark. It's better than contrast filters in photo editing tools,
because it considers the reflection characteristics of each object in your picture.
"You can't
compensate for having one area underexposed and one area overexposed," said Hugues
Hoppe, one of the project researchers. "If an
area is underexposed, you can't really get the detail back by increasing brightness,
because it wasn't captured in the first place. By having two different images which
both have useful information, you can merge them together."
Image
Stacks
A similar technology that combines the best of multiple photographs is a project called
Image Stacks. Image Stacks aligns multiple images of the same subject, allowing the
user to pick and chose the best pieces from each photograph. Researchers Michael
Cohen, Steven
Drucker and Alex
Colburn thought this would come in handy for special
events, when you want to get a picture of the entire group that's suitable for framing.
Taking group photographs
is difficult, because capturing a single image in which everyone looks good is almost
impossible. What usually happens is that in one shot, someone has their eyes closed,
but someone else has got the most adorable smile. Check the next shot, everyone has
their eyes open, but one person is picking a poppy seed out of their teeth. The third
shot, both previous people are behaving, but grandma is yawning, tired of waiting
through multiple shots. Which shot do you pick? With Image Stacks, you can easily
cut and paste to present everyone's best face. The images are automatically registered
into a single composite image.
Print
to Digital
Print photos are still around. They're around in shoeboxes. They're shoved under the
bed and in the back of closets. Some of us have so many print photos we don't know
what to do with them. Neatnik types tediously scan all of their print photos one-by-one,
converting them to digital form. But most of us don't want to go to all this trouble.
Cormac
Herley, a researcher in the Communications, Collaboration
and Signal Processing (CCSP) group,
has developed a way to allow people to scan multiple photos at one time. You can put
as many photos as will fit on your scanner, and the software will recognize each photo
separately. It can 'read' the edges of the photos, even if they're crowded together
or tilted. When it converts them to digital photos, it will correct for orientation
and position. It's a quick way to get the family memories out of the shoebox and onto
your hard drive.
"It's a harder
problem than it looks like on the surface. Many scanner makers have tried, but it
hasn't worked before," said Herley. "But this really works, it's not just
a demo."
Take
Out the Red
The Media Computing group at Microsoft Research Asia has developed several cool image
editing techniques to help you fix some common problems with any photograph. One of
the worst that comes to mind is the glowing red eyes that result from the flash hitting
the pupil in just the wrong way. Unless you're way into the vampire look, this just
isn't right. The red eye fix, which currently ships in Digital Image Suite and
Windows XP
Media Center Edition, is one of the best photo retouch features around. All you do
is move the 'target' over the red eye, click, and the red is out.
The same group
has also developed a quick and effective way to fix the brightness and contrast in
a picture. Even if you took a picture that is too dark, you can use the Levels Auto-Fix
feature in Digital Image Pro to lighten up your picture.
Organize
the Digital Shoebox
The Media
Computing group has also made it easy to organize your
digital photos using image recognition algorithms. Some people do the same thing they
did with the shoebox, and scatter pictures all over their hard drive. Then they can't
find the one picture they want to use for their holiday card. The group's algorithms
can distinguish between indoor and outdoor shots, shots with people in them and shots
without, and city and non-city scenes. Combined with other technologies, such as keyword
annotation, it makes it a breeze to find any photo in your collection.
John
Platt, a researcher in the CCSP group has developed
another way to manage your photos online. His image clustering algorithm helps users
find their photos by one of the most prominent markers: events. The software is effective
because it doesn't look only at timestamps, which could be misled by a faulty camera
clock. Instead, the software looks at photograph order plus color to find pictures
taken during one particular event.
"We only compare
colors locally in time," said Platt. "So if you have a pumpkin in one shot,
and a few months later you wear an orange shirt, later, when you're searching for
the day you visited the pumpkin patch, it won't show photographs from when you were
wearing the orange shirt."
His algorithm underlies
several other technologies designed to help people find their digital photos, including
the Microsoft Research Media Browser. The Media Browser, developed by researchers
in the Next
Media group, takes advantage of the photo recognition
research from the Media Computing group, and Platt's algorithms to build a unique
visual experience that helps you search for and identify your photos. And it looks
darn cool as it works. The interface is an impressive, futuristic presentation of
photos that rearrange themselves before your eyes, sliding into place in a typical
2D presentation or a 3D stack.
"The idea
behind this is annotation of large collections of photos," said Steven Drucker,
the lead researcher on the project. "We know that if you put annotations on photos,
that it's much easier to retrieve them. But we also know that it's tedious and difficult
to do. We use the advanced techniques that are available, such as face detection and
image clustering, to make it easier for you to interact with your photos. We also
use a game graphics card for higher visual quality."
Fill
It In
Smart Erase is a photo editing tool found in Digital Image Pro and invented by researcher Patrick
Perez in
Cambridge
. The feature allows users to remove objects from a picture. This can come in handy
in case you want to remove your ex from the family reunion picture, or you before
you lost the 30 pounds.
The algorithm looks
at areas of the image to see which patch of texture can be "stolen" to fill
in the holes left behind when the unwanted object in the image is removed.
To fill in the
hole, Smart Erase does some reasoning about texture. It views the pixels outside the
object as potential replacement material. The program has some strategies for knowing
exactly where to look to get this material. "The algorithm constantly reviews
what pieces it's got and makes comparisons very quickly to come up with the right
fit," said Andrew
Blake, Senior Researcher in
Cambridge
.
Blend
It
Another photo editing feature from the
Cambridge
lab, a tool code-named Blender, appeared in Digital Image Pro this year as the "Blending
Brush." Blender is a seamless cloning tool that can take the wrinkles out of
your face, insert a new object into a scene, and combine parts of one scene with another
- all without the usual difficulties and distortions that most photo editing techniques
present.
If an object inserted
into a new background has complex outlines, standard cloning may not work because
of the incompatibility of color and intensity between the background and the new object.
And even the best, most careful cutting and pasting often yields poor results because
the outlines are fuzzy or jagged. Blender 'blends' pieces of the inserted object and
the background together to form a seamless whole.
Cut
It Out
Cutting out an image and putting it somewhere else has always held a lot of fascination
for photo aficionados. Blake and his team are developing a new algorithm they call
GrabCut, that's a 'no-brainer' way to do this important task. Instead of having to
carefully trace the outlines of the object you want to cut out, all you have to do
is draw a rectangle around the object. The algorithm selects the object and eliminates
the old background. You can then paste the cut-out object onto a different background.
Cartoon
Wizard
Doesn't everyone want to star in their own anime or Disney cartoon?
Though Microsoft
Asia researchers can't get you a Disney contract, they can turn your digital photograph
into a cartoon. Their technology, developed in cooperation with MPD Japan, is called
the Cartoon Wizard. It is currently offered in the Japanese version of Office 2003.
Westerners will have to wait, as the Cartoon Wizard is only trained to work with Asian
faces.
Their system is
based on statistical learning techniques. The algorithm automatically generates a
cartoon from an image using face detection and alignment, and training data generated
by studying how a human artist renders a human image into a caricature. The resulting
cartoons can be used in e-cards or personalized emoticons for chat programs.
Tell
a Photostory
Now that you've stepped through the process of improving and organizing your digital
photos, perhaps you'd like to share them. Microsoft Research has developed several
ways to do this, in small and large ways.
When
researcher Dave Vronay was working on PhotoStory, he wanted to recreate the feeling
of a family sitting around an old-fashioned photo album and telling the stories connected
to the pictures.
"A picture
is not just a description of what is there," he said. "For instance, if
you have a picture of a hotel, and you showed it to a friend, you probably wouldn't
just say, 'and that's the hotel we stayed at.' You might instead launch into a story
about the waiter with purple hair who served you duck soup at the hotel restaurant,
even though you didn't have a picture of him. The photo would be a reminder of the
stories that surrounded that photo."
With Photostory,
you can add images, music, and background narration to tell the stories behind the
pictures and send it to the people you'd love to have sitting on the couch next to
you while you share your memories.
Share
Your Photos with Friends
The Social
Computing group is experimenting with an online blog
and photo sharing application code-named Wallop, a project designed to help people
to connect with those close to them — families and friends, and friends of friends.
The group considers
Wallop a "social networking" application that provides a way for small,
closely connected groups of people to share personal information and photographs online.
The beta testers can send photos to their Wallop interface through email or instant
messages to easily update their blog interface.
Share
Your Photos with the World
The World Wide Media Exchange (WWMX) offers users from around the world the chance
to upload and share their photos with millions. It provides MapPoint maps and TerraServer
maps so that you can view your photos by location as well as time.
One of the advantages
to this interface is the ability to communicate with people across the world. If you're
planning a trip to
London
, for instance, maybe some nice tourist who has gone before you has posted their pictures
of a trip around the city, complete with shots of their favorite tea stops. Then other
tourists or locals can jump in and write annotations on the photographs, such as,
"don't eat here, the crumpets aren't up to the usual standards."
Some of the contributors
to the WWMX have
contributed to history by adding photos of 'news' events, such as fires in
Southern California
and search and rescue operations.
A Visual
Journey
David
Salesin, a senior researcher in the Document Processing
and Understanding group, has inspired many digital projects at Microsoft Research.
He is also on the faculty at the
University
of
Washington
. Salesin recently became actively involved in a large digital photography project.
A very large project. He contributed original digital photographs from his trip to
Bhutan
to the world's largest published book, a visual journey across the last unspoiled
Himalayan kingdom on the planet.
The project was
funded by several sources, including the Bill & Melinda Gates Foundation and the iCampus
program at Microsoft Research. "Mike's project
seemed like an interesting, original take on how we might be able to use technology
for education," said Salesin. He helped convince the iCampus funding committee
to support the project.