Researchers at the University of Tokyo have developed a computerized, sensor-based “magic mirror” that analyzes muscular activity and shows real-time computer-generated images of how hard the user’s muscles are being worked while exercising.

The magic mirror, developed under the leadership of professor Yoshihiko Nakamura of the Information and Robot Technology Research Initiative (IRT), was unveiled at the University of Tokyo last Friday. In a demonstration for the media, the system’s display monitor showed a real-time computer-generated image of a male model’s musculo-skeletal system while he performed a series of physical exercises.

The system, which is currently capable of monitoring the activity of 30% of the body’s roughly 300 skeletal muscle pairs, consists of 16 electromyographs (instruments that record the electrical waves associated with muscle activity) attached to the user’s body, 10 motion-capture cameras, and a pair of floor sensors to measure the force exerted on the legs.

On the monitor, each muscle is shown in a different color depending on how much it is being used at a particular moment. Active muscles are shown in red, while inactive muscles are shown in yellow.

(Muscle images can also be overlaid on the video image of the user’s body.)

The magic mirror system uses newly developed software that is reportedly 10 times faster than previous technology, allowing the system to operate in real-time, even when the user is moving rapidly.

The researchers, who are already working on a more compact version that incorporates the cameras directly into the display, envision the system being used in homes, gyms and hospitals. In addition to helping people get into shape, the system might also help doctors more effectively treat conditions that affect the muscles.

[Sources: Robot Watch, Yomiuri, Nikkei]

Researchers from Japan’s ATR Computational Neuroscience Laboratories have developed new brain analysis technology that can reconstruct the images inside a person’s mind and display them on a computer monitor, it was announced on December 11. According to the researchers, further development of the technology may soon make it possible to view other people’s dreams while they sleep.

The scientists were able to reconstruct various images viewed by a person by analyzing changes in their cerebral blood flow. Using a functional magnetic resonance imaging (fMRI) machine, the researchers first mapped the blood flow changes that occurred in the cerebral visual cortex as subjects viewed various images held in front of their eyes. Subjects were shown 400 random 10 x 10 pixel black-and-white images for a period of 12 seconds each. While the fMRI machine monitored the changes in brain activity, a computer crunched the data and learned to associate the various changes in brain activity with the different image designs.

Then, when the test subjects were shown a completely new set of images, such as the letters N-E-U-R-O-N, the system was able to reconstruct and display what the test subjects were viewing based solely on their brain activity.

For now, the system is only able to reproduce simple black-and-white images. But Dr. Kang Cheng, a researcher from the RIKEN Brain Science Institute, suggests that improving the measurement accuracy will make it possible to reproduce images in color.

“These results are a breakthrough in terms of understanding brain activity,” says Dr. Cheng. “In as little as 10 years, advances in this field of research may make it possible to read a person’s thoughts with some degree of accuracy.”

The researchers suggest a future version of this technology could be applied in the fields of art and design — particularly if it becomes possible to quickly and accurately access images existing inside an artist’s head. The technology might also lead to new treatments for conditions such as psychiatric disorders involving hallucinations, by providing doctors a direct window into the mind of the patient.

ATR chief researcher Yukiyasu Kamitani says, “This technology can also be applied to senses other than vision. In the future, it may also become possible to read feelings and complicated emotional states.”

The research results appear in the December 11 issue of US science journal Neuron.

[Source: Chunichi]

Do these fellows look old enough to smoke? Yes indeed, say Japan’s cigarette vending machines that use face-recognition technology to determine the age of the purchaser.

Just two weeks after a major sports paper reported that magazine photos could be used to fool vending machine age-verification cameras, an even more surprising flaw has come to light. The portraits of Hideyo Noguchi and Yukichi Fukuzawa printed on the 1,000-yen and 10,000-yen bills can be used to trick the high-tech machines, according to a new report on the Sankei Shimbun website.

On July 1 — the day that Japan’s cigarette vending machine age-verification system was rolled out nationwide — Sankei reporters in Tokyo went out in search of machines equipped with age-verification cameras. They found that these machines treated them as adults and allowed them to purchase cigarettes when they showed the portrait of Yukichi Fukuzawa (the renaissance man and Keio University founder who appears on the 10,000-yen note) to the vending machine’s camera-embedded mirror. The machines also reportedly sold cigarettes to the portrait of Hideyo Noguchi (the notable bacteriologist who discoveredcontributed to the understanding of syphilis), which appears on the 1,000-yen note.

Once the machines approved the sale, the reporters then used the same money to pay for the purchase, making this all-in-one technique even more convenient than the recently discovered magazine photo trick.

Ironically, news of this latest discovery comes just days after the Finance Ministry officially approved the use of face-recognition technology to determine the age of vending machine users.

Sankei contacted the Finance Ministry’s Tobacco and Salt Industries Office about the flaw they found. A surprised official responded by saying, “This is the first we’ve heard of it. It’s a big problem if it’s true.”

The official said he would immediately notify Fujitaka, the vending machine manufacturer who developed the age-verification camera system. Fujitaka is reportedly in the process of upgrading its face-recognition technology so that it can more effectively distinguish photographs from real people.

Of Japan’s more than 500,000 cigarette vending machines, around 4,800 (less than 1%) are equipped with age-verification cameras. The rest are outfitted with readers that check Taspo age-verification cards, which are available to anyone of legal age who applies (though they have yet to become widespread). The vending machines that use age-verification cameras allow people to purchase cigarettes without a Taspo card, as long as they look older than 20 years of age.

[Source: Sankei Shimbun]

Related: Magazine photos fool age-verification cameras

With the full-scale rollout of Japan’s cigarette vending machine age-verification system just around the corner, a Sankei Sports news reporter has confirmed the existence of a minor flaw: magazine photos can be used to fool the age-verification cameras on some machines.

When the reporter went to check out the new age-verifying machines after they were introduced in the Osaka area in June, he soon discovered that the machines equipped with face-recognition cameras would let him buy cigarettes when he held up a 15-centimeter (6-in) wide magazine photo of a man who looked to be in his 50s.

The reporter also went to Kobe, where different face recognition hardware is being used. There, he bought cigarettes using an 8-centimeter (3-in) wide magazine photo of a female celebrity in her 30s. He also reportedly tried to use a 3-centimeter (1-in) wide photo, but the machines rejected it.

As part of the age-verification system, most of Japan’s 570,000 cigarette vending machines are being outfitted with RFID readers that check the purchaser’s Taspo age-verification card. Smokers without a Taspo card can now either buy their cigarettes in person over the counter or use one of 4,000 special machines equipped with face-recognition systems (these machines do not require Taspo cards). More face-recognition machines are on the way, according to vending machine manufacturer Fujitaka, who developed the face-recognition hardware.

The face-recognition machines rely on cameras that scan the purchaser’s face for wrinkles, sagging skin and other signs of age. Facial characteristics are compared with a database of more than 100,000 people, and if the purchaser is thought to be well over 20 years old (the legal age), the sale is approved. If the purchaser looks too young, they are asked to prove their age by inserting a driver’s license. According to Fujitaka, the machines are 90% accurate.

Fujitaka admits that people may, on occasion, be able to fool the age-verification cameras with photographs — but only for the time being. The company is now working on a more advanced system that will make sure each face belongs to a real human, but they are unable to say when these new machines will be put into place.

[Source: Sanspo]

Researchers at the University of Tokyo have developed a smart video goggle system that records everything the wearer looks at, recognizes and assigns names to objects that appear in the video, and creates an easily searchable database of the recorded footage. Designed to function as a high-tech memory aid, these “Cyber Goggles” promise to make the act of losing your keys a thing of the past, according to head researcher professor Tatsuya Harada.

Cyber Goggles are equipped with a compact camera that feeds video to a computer worn on the user’s back. The computer records the footage and relies on ultrahigh-speed image recognition processing software to analyze, name and file the objects that appear in the video. Later, when the user types in a keyword to search for a particular item, the corresponding video plays on a tiny LCD screen attached to the right-side lens, helping the user remember the location of the item in question.

In a demonstration at the University of Tokyo last week, 60 everyday items — including a potted begonia, CD, hammer and cellphone — were programmed into the Cyber Goggle memory. As the demonstrator walked around the room viewing and recording the various objects, the names of the items appeared on the goggle screen. The demonstrator was then able to do a search for the various items and retrieve the corresponding video.

In addition to functioning as a memory aid for the elderly, Cyber Goggles have a number of other potential uses, says professor Harada. For example, the image recognition processing technology can be used to sift through enormous amounts of video in search of specific images. It might also help in the development of robots with human-like abilities, he says.

[Sources: Asahi, Sankei]

The Japan Aerospace Exploration Agency (JAXA) and public broadcaster NHK have released a scaled-down online version of their much anticipated high-definition video of the Earth rising over the lunar horizon. The video was taken on November 7 by the HDTV camera aboard the KAGUYA (SELENE) lunar explorer orbiting the moon at an altitude of 100 kilometers (62 miles). The first part of the video shows the Earth rising up from the horizon near the moon’s north pole, and the second part shows the Earth setting near the moon’s south pole. The original high-definition footage, which NHK plans to broadcast soon, is the world’s first high-definition video of Earth taken from the moon (380,000 kilometers/ 236,000 miles from Earth). Obviously, the edited YouTube version you see here (as well as the original online version at JAXA) is not in HD format, but it is a nice teaser for what is coming to HDTV viewers in Japan.

[Source: JAXA]

=========================

See also:

- Earthrise video
- HDTV footage of Earth

=========================

JAXA has posted an online version of the video, which is divided into two parts. The first part was shot on west side of the Ocean of Storms as the explorer moved from south to north, and the second part was shot from a location north of the Ocean of Storms (Oceanus Procellarum) as the explorer moved toward the north pole. The footage was taken on October 31.

Here are a few stills from the video…

(Enlarge)

This still was taken from the first part of the video, which was shot on the west side of the Ocean of Storms as KAGUYA moved from south to north. The dark area on the right side of the screen is the “ocean,” and the bright area on the left is called the “highland.”

(Enlarge)

This still, which also shows the west side of the Ocean of Storms, was taken from the end of the first part of the video. The Repsold crater, which measures 107 kilometers (66 miles) across, is visible in the center of the image, near the bottom.

(Enlarge)

This still, taken from the second part of video, shows an area north of the Ocean of Storms, near the north pole. At this high latitude, the low-angle sunlight casts long shadows in the craters.

The online video does not include the much-anticipated shot of the earth rising over the lunar horizon, but perhaps NHK is saving it for when they broadcast the footage in its full, high-definition glory.

[Source: JAXA press release]

Using a high-definition camera NHK developed specifically for use in space, the video was taken at a distance of 110,000 kilometers (68,000 miles) from Earth, making it the most distant HDTV footage of the planet ever taken. Previous HDTV video from the Space Shuttle and International Space Station was taken from a distance of 340 kilometers (210 miles).

More HDTV space footage — including a money-shot of the Earth rising over the lunar horizon — is expected this month as Kaguya continues its journey toward the moon. Viewers with HDTV-compatible television sets will get to experience the full quality of the high-definition video whenever NHK decides to air it.

[Link: JAXA]

Built around Omron’s previous face recognition technology, the new “OKAO Vision Real-time Smile Measurement Technology” is designed to automatically identify faces in digital images and assign each corresponding smile a score of 0% to 100%. The system works by automatically fitting a 3D face model onto the subject’s face and analyzing a number of key points, such as the degree to which the eyes and mouth are open, the shape of wrinkles at the edges of the eyes and mouth, and changes in the position of facial features. The entire process, from the time an image is input until the time the smile score is output, takes 0.044 second (for a 3.2 GHz Pentium 4 processor).

OKAO Vision can analyze multiple faces simultaneously as long as they are at least 60 pixels wide and facing the camera (tilted less than 30 degrees to either side and less than 15 degrees up or down), and the software does not require faces to be registered beforehand. OKAO Vision, which Omron says is more than 90% accurate, was developed by studying the facial expressions of 15,000 individuals ranging from infants to the elderly, from a variety of countries.

The 46-KB, Windows 2000/XP-compatible program can easily be incorporated into a variety of devices, say the developers, who hope to see it put to use in digital cameras designed to capture the perfect smile, or in robots that can recognize when humans are happy. Masato Kawade, OKAO project leader, says he hopes the technology “can contribute to the development of an ideal society where machines operate in harmony with human emotions.”

Omron plans to release the new OKAO Vision system later this year, making it the latest addition to a line of face recognition technology that boasts features such as the ability to determine a subject’s age, gender and line of sight. In the future, the company plans to shift the focus away from shiny, happy people and develop technology that can read faces for anger and sadness.

[Sources: Kyoto Shimbun, RBB Today]

Motion Portrait is a killer little piece of digital animation technology that easily transforms an ordinary digital photograph of a face into a living 3D animation that can blink and move its eyes, turn its gaze to follow the movement of the mouse cursor, express a range of emotions, sneeze and more — all in a matter of seconds. In addition to being fast and easy to use, Motion Portrait is much lighter than conventional 3D animation engines, making it ideal for use in cellphones, handheld games and other portable devices.

Originally developed at the Sony Kihara Research Center two years ago, Motion Portrait now belongs to Motion Portrait Inc., which was founded this July after the research center closed its doors last year. As the company continues to develop Motion Portrait, it is on the lookout for new ways to put the technology to use.

While the technical details are being kept secret, the company says Motion Portrait works by automatically recognizing the eyes, nose, mouth and other facial features in ordinary digital photographs to create an instant three-dimensional map of the head. The data is then run through Motion Portrait’s Expression Engine to create a range of facial expressions. Here are a few examples of Motion Portrait at work: 1, 2, 3.

In addition to photographs of human faces, Motion Portrait can also breathe life into pictures of pets, with a little manual input. Check out this fun yet sinister-looking dog (pictured above). Grrrr!

The technology can also be used to create anime from illustrations, and it is already being used in a PSP game — the Promise of Suzumiya Haruhi (Suzumiya Haruhi No Yakusoku) by Bandai Namco Games — due out in early August. With the ability to create a wide range of facial animations from a single image, Motion Portrait promises to reduce game development costs and improve quality. In addition, when used in conjunction with the company’s voice recognition technology, Motion Portrait automatically syncs the animated lips with voice data to create realistic-looking talking mouths. Here are two anime examples: 1, 2.

The company also sees potential uses for Motion Portrait in advertising and in creating avatars used on social networking sites. Further, as a simulation tool, beauty salons can use Motion Portrait to show customers how they might look with different hairstyles and makeup, and eyeglass shops can use it to help customers choose their next pair of eyeglasses.

No word yet on when Motion Portrait will be made available to the general user.

[Source: Motion Portrait via IT Media]

Finger vein money relies on Hitachi’s finger vein authentication technology, which verifies a person’s identity by reading the pattern of blood vessels in his or her fingers. These blood vessel patterns are unique to each individual, much like fingerprints or retinas, only they are hidden securely under the skin, making them all the more difficult to counterfeit. Hitachi’s finger vein authentication technology is already being used to verify user identities for ATMs, door access control systems and computer log-in systems in Japan and elsewhere.

In the finger vein money system, consumers first register their finger vein pattern data with the credit card company. The data is then entered into a database along with the individual’s credit account information. Later, when shoppers want to pay for something, they simply go to the cash register and place their finger in a vein reader, which uses infrared LEDs and a special camera to capture a detailed image of their vein structure. The image is converted into a readable format and sent to the database, where it is checked against the records on file. When the system verifies the identity of the shopper, the purchase is charged to the individual’s credit account.

Hitachi’s three-month field test, which is set to begin in September, involves 200 Hitachi employees volunteering to use finger vein money at the company cafeteria and shops in the Hitachi System Plaza Building located in Shin-Kawasaki. If all goes well, Hitachi — who is conducting the test with the cooperation of major credit card company JCB — plans to expand the trial system to all of its company buildings.

As a cardless payment system that promises the ultimate in convenience and security, finger vein money could help contribute to the disappearance of credit cards and all the anxieties associated with their loss and theft. When that day comes, we may only need to worry about losing our fingers.

[Source: Nikkei Net]

Built around NEC’s NeoFace biometric face recognition system, as well as NEC’s electronic passport technology, the system is designed to boost the speed and efficiency of Hong Kong Immigration Department operations by allowing residents with microchipped national ID cards to remain in their vehicles while automated cameras verify their identities. Hong Kong residents aged 11 or over are required by law to carry a national ID card (HKID), and the recently issued “smart” IDs are embedded with chips that contain biometric and personal data.

The system works by first reading a vehicle’s license plate as it approaches a border gate. Because each vehicle in Hong Kong is registered to an individual driver, a simple automated database check determines who the driver should be. Next, the cameras scan the face of the driver and a database search is performed. If there is a match, the immigration process is completed and the gate opens, allowing the vehicle to pass through.

For now, NEC’s setup only works with truck drivers, but coming improvements promise the ability to identify up to 8 passengers per vehicle. The cameras have been installed at 8 of the 40 border gates on a new road connecting Hong Kong and Shenzhen, with all 40 gates expected to be upgraded by August.

NEC eventually hopes to develop a face recognition system so quick and accurate that it would eliminate the need for fingerprinting.

[Sources: Softbank Business + IT, NEC press release]

According to the Russian Tass news agency, a reindeer herder stumbled upon the 130 cm (4 ft 3 in) tall, 50 kg (110 lbs) frozen mammoth in May in an area of permafrost in northwestern Siberia, near the Yuribey River on the Yamal Peninsula, which extends into the Kara Sea. The mammoth, whose trunk and eyes remain intact and which still has some fur on its body, was shown to an international panel of experts that convened on July 5 in the town of Salekhard, near the discovery site.

Preparations are now being made to ship the baby mammoth to Jikei University School of Medicine, where researchers will use advanced computed tomography (CT) scanners to obtain three-dimensional images of its internal organs. “This is the first opportunity for anyone to perform an analysis on a complete mammoth body,” says Jikei University professor Naoki Suzuki, “and it should provide a more complete picture of its anatomy and how it lived.”

[Source: Yomiuri]