Deep Neural Nets Can Now Recognize Your Face in Thermal Images

Neural Network – Connecting Mid-or-Far Infrared Image

Cross modal matching of the face between thermal and visible range is a desired capability especially during night time scrutiny as well as security applications. Owing to huge modality gap, thermal to visible recognition of the face seems to be one of the challenging face matching issue.

Recently Saquib Sarfraz and Rainer Stiefelhagen at Karlsruhe Institute of Technology in Germany has worked out for the first time, a way in connecting a mid-or far-infrared image of a face with a visible light counterpart, a trick they have achieved in teaching a neural network to do all the task. Corresponding to an infrared image of a face to its visible light counterpart is not an easy work, but which deep neural networks are beginning to surface.

The issue with infrared observed videos or infrared CCTV images is that it could be difficult in recognising individuals where the faces tend to look different in the infrared images. Matching of these images to their usual look could be an important uncertain experiment. The issue could be that the connection between the way one may tend to look in infrared and visible light could be very nonlinear. This could be very complicating for footage which could be taken in midand far-infrared that could use passive sensors detecting emitted light instead of the reflected range.

Visible Light Images- High Resolution/Infrared Images – Low Resolution

The way in which a face emits infrared light is completely different from the way it reflects it where the emissions differ as per the temperature of the air as well as that of the skin. This in turn is based on the activity level of the individual, like having a fever or not. Another issue which could make comparison difficult is that visible light images could have a high resolution while far infrared images could have a much lower resolution due to the nature of the camera from which the images have been taken.

Collectively, these factors could tend to make it difficult in matching an infrared face with its visible light corresponding image. With the recent developments in deep neural networks in overcoming all types of difficult issues, it gave rise to the idea to Sarfraz and Stiefelhagen. They speculated on training a network to recognize visible light faces by looking at infrared types. Two major factors have been pooled in, recently in making neural networks very powerful.

Better Understanding/Availability of Interpreted Datasets

Better understanding, being the first, on how to build and tweak the networks in the performance of their task which is a procedure leading to the development of the supposed deep neural nets which was something that Sarfraz and Stiefelhagen learnt from other work.The second is the availability of largely interpreted datasets which could be utilised in training these networks.

For instance accurate computerized face recognition has been possible due to the creation of massive banks of images wherein people’s faces have been remote as well as identified by observers because of crowdsourcing services like Amazon’s Mechanical Turk. These data sets seem to be much difficult to come by for infrared or visible light evaluations.

Nevertheless, Sarfrax and Stiefelhagenhandled this issue. It was created at the University of Notre Dame comprising of 4,585 images of 82 individuals which were taken either in visible light at a resolution of 1600 x 1200 pixels or in the far infrared at 312 x 239 pixels.The data is said to comprise of images of individuals, laughing, smiling together with neutral expressions taken in various sessions in order to capture the way their appearance seem to change from day to day and in two various lighting conditions.

Fast/Capable of Running in Real Time

Each image was then divided into sets of overlapping patches of 20 x 20 pixels in size in order to vividly increase the size of the database. Eventually Sarfraz and Stiefelhagen utilised the images of the first 41 individuals in training their neural net together with the images of the other 41 people for the purpose of testing. The outcome of it seemed to be interesting.

Sarfraz and Stiefelhagen have commented saying that `the presented approach improves the state-of-the art by more than 10 percent. It is said that the net can now match a thermal image to its noticeable counterpart in a mere 35 milliseconds. They further added that `this is very fast as well as capable of running in real time at ∼ 28 fps’. Though it is by no means flawless, at best its precision is over 80 percent when it has anextensivearray of visible images when compared against the thermal image.

The one-to-one contrast accuracy is only 55 percent. Improved accuracy could be possible with larger datasets together with much more powerful network, out of which, the creation of a data set that is higher by order of magnitude would be the more difficult of the two jobs.

However, it is not an issue to imagine this type of database to be created rather quickly provided the interested individuals could be the military, law enforcement agencies and government who tend to have deeper pockets with regards to security related technology.

One Camera is all This Self-Driving Car Needs

Self-Driving Vehicles with One Camera

Vision systems are now considered to be adequate in enabling a car to drive automatically with only a camera. Several self-driving vehicles, inclusive of Google’s prototypes are impressed with the sensors like the cameras; high accuracy GPS, ultrasound as well as the expensive laser ranging instruments called `lidar’.

These devices tend to support the cars in building a composite image of the world around for the purpose of safe driving, though some of the components like lidar tend to be quite costly. A demo portrayed how quickly some of the technology has been progressing.

A company – Magna which provides components to several huge carmakers has recently shown that it could make a car drive itself with the use of a single camera which is embedded in the windshield. Cost of the technology has not been disclosed by the company but the vehicle camera system would probably cost hundreds of dollars instead of thousands.

 This achievement has been possible due to the speedy progress in the software that comes from MobileEye, an Israeli company, which is good at interpreting a scene.

Software Recognized Traffic Signs

Lead control algorithm engineer at Magna, Nathaniel Johnson, organised a ride in a Cadillac with the installed technology in it and after pulling onto the I-94 north of Ypsilanti, Michigan, he pressed a button on the steering wheel in order to activate the system and then sat back enabling the car to take control.

Johnson explained that `it could drive itself in several situations and as the car followed the curve of the road, it used various image processing techniques’. Entertainment display on the dashboard of the car portrayed the video feed which was being processed by MobileEye’s software.

Besides this, the lane marked were emphasized in green while green boxes were drawn around each vehicle ahead with their numbers indicating their distance in feet. Moreover the software also recognized instantly, the traffic signs. He also clarified that the automated driving method could be organized to stick to whichever speed the sign indicated. He took the opportunity of taking the wheel for a few seconds then abandoned it, enabling the self-driving system to retake control.

Technology Linked with Other Sensors

The company had been testing the technology, in trails for the past several years in U.S., Germany, and U.K and recently in China. It is said that the technology would not be utilised this way by carmaker but would probably be linked with other sensor systems, though it portrays that automated driving abilities can be added quite cheaply to vehicles.

Johnson has informed that `for higher levels of autonomy, they would need more sensors, but this seems a good introductory level of autonomy. It is something people could afford and get into their cars’.Currently, automated driving systems like adaptive cruise control as well as hands-free parallel parking are only provided on high-end vehicles.

 Mercedes S-Class sedan that can automatically follow the car ahead in stop-and-go-traffic and can take the wheel to support swing over obstacles, comes at a cost of $94,400 in the U.S. and could cost as much as $222,000.If the technology should have an great impact on the consumers, the price of sensors as well as the related systems will need to come down considerably.

Chinese Carmaker is Testing Car-to-Car Communications

Chinese Testing Technology

One of the leading carmakers in China has been testing technology which could prevent accidents and reduce overcrowding by enabling vehicles and traffic signals with wireless communication. Though there is no standard for the technology that has surfaced in China so far, representative at the company state that it could introduce some sort of car-to-car communication by 2018 ahead of several U.S. automakers.

 A state owned car manufacturers, Changan; based in Chongquing, in central China has been testing vehicle-to-vehicle – V2V as well as vehicle-to-infrastructure – V2I technology at its U.S. R&D centre in Plymouth, Michigan. The company does not sell vehicles in the U.S. and has stated that it has no plans in entering the U.S. market.

However, testing car-to-car technology at its U.S. centre indicates that it envisages a future for it in its home country. The car-to-car technology has been promoted in the U.S. and Europe as cost effective way in helping vehicles to avoid crashes as well as to control traffic flow in an efficient manner.

Technology to Be Introduced in High-End Cadillac- 2017

Vehicles which are equipped with useful broadcast information inclusive of location, direction of travel, speed and computers on-board on each car could use that information in identifying an approaching crash and send a warning. Some of the companies are also making headway in custom communication systems to enable commercial vehicles to travel in highly efficient high-speed convoys.

The U.S. Department of Technology, after a successful test of the technology involving thousands of cars around Ann Arbour, Michigan, is expected to issue specifications for the technology somewhere later this year. The technology is said to be introduced in a high-end Cadillac towards 2017 and would eventually be delegated for new cars in the U.S.

The scenario is less clear in China wherein the government is studying vehicle-to-vehicle technology though has not yet provided any clues on when it could be implemented.

Will Take Time to Get Universal

A ride was organised around Ann Arbor in one of the Changan’s car which was a small SUV known as the CS35 and was fitted with vehicle-to-infrastructure technology. The SUV was fitted with a wireless transmitter as well as a receiver that was connected to an Android tablet attached to the dashboard. When another car which was equipped with the technology approached along a blind crossing, a warning flashed out. Another warning was also received as the car travelled around a sharp bend too quickly.

The challenge with car-to-car technology is that it would take some time to get universal. Though the Chinese car market tends to be the largest auto market in the world, per capita car ownership is still lower in China than in the U.S., Japan of Europe. China also tends to lag behind U.S., Europe and Japan with regards to the development of technology. A PhD student at Carnegie Mellon University, John Helveston, studying the adoptions of electric vehicles in China has stated that the foreign car developers which control the market in China favour selling older technology there. If domestic car makers tend to be interested in car-to-car systems, it would not be interesting if only five out of every 100 cars could communicate with each other’.

How to Unlock Your Samsung Galaxy S6 or S6 Edge

Did you know that there are some awesome hidden features on your Galaxy S6 or S6 Edge, that you can activate by navigating to system/csc/Features.xml and adding the corresponding line to the end of the file for each feature? It’s recommended that you do a backup before this process, and then you can safely enable: camera during call, continuous music while using camera, scheduled messaging option in your messaging app, and much more.

Your device has a lot of potential, but you need to know how to unlock it in order to benefit from it. And I do mean “unlock it” in its literal sense. Unlocking your Galaxy S6 or S6 Edge will allow you to get your favorite cell phone plan, no matter what carrier offers it; it will help you escape outrageous roaming fees when you travel outside the country, by using local SIMs; it will make you more money when you sell your device to upgrade to a newer model.

Those are your benefits for unlocking your Samsung Galaxy S6 or S6 Edge. Now let’s see what your options are for unlocking it:

•  Go to a local phone repair shop. The prices aren’t high, but the risk of damaging your phone is real because they use a piece of hardware to do so. And on top of that, you have to leave your phone with them - can you imagine staying a day without it? 
•  Go to your carrier. Network providers are obliged to unlock your phone, for free or a fee, but they don’t advertise this. The downside is that you’ll most likely have to wait for your contract to expire, in order to benefit from this. 
•  Go to an online unlocking platform or app. UnlockUnit.com and UnlockScope.com are good examples, because they have great reviews on ReviewCentre. Other people’s experience is a great indicator of the quality of the service. They help you buy the unique unlocking code attributed to your phone in the factory, from the comfort of you own home.

They both have a turnaround time of 1 to 6 hours for Samsung Galaxy S6 and S6 Edge devices, and a discount that’s running for a limited time on the site.

How to unlock your Galaxy S6 or S6 Edge safe, fast and secure

First of all, you’ll need to check and make sure that your device is locked. Then, for the unlocking process to go smoothly, you’ll need internet access, a second SIM card from a different network provider and, obviously, your locked smartphone

All good? Now head to the order page and quickly fill in the form with the country and network provider you bought it from, your 15 digit IMEI (which you can find out by calling *#06# or going to Settings > More > About device > Status), and your email address. At this point, this is all you have to do.

Then, you’ll be redirected to the payment page. You can pay for your unique unlock code through credit card, PayPal, Skrill, MoneyBookers or Bitcoin. Cool huh?

Once the payment is completed, your order has been successfully submitted and, at any moment, your code should arrive in your email inbox.

Then simply insert the SIM card from a different network provider, and your device will display the message “SIM Network Unlock PIN” or “Enter Unlock Code” and an empty box (see the image below). In that empty space you have to insert the unlocking code received.

Right after hitting the unlock button, your Samsung Galaxy S6 or S6 Edge will be permanently unlocked and, from now on, you can use it with any carrier in any country in the world.

If you prefer to do this through an app rather than on your computer, you can download the UnlockScope app from Play Store instantly. If you have any questions or would like to share your unlocking experience with us, please leave a comment in the section below.

Watch Out for These Serious Mac Attacks

Apple’s esteemed line of Mac devices are about to go through troubled times with the emergence of new age advanced bugs and glaring loopholes in Apple’s operating system. Security researchers had unearthed a new kind of vulnerability in the Mac devices, which allows the hackers install devious ad-wares like VSearch without even requiring the password. VSearch is a notorious malware, which infects the Mac devices with numerous pop-up ads and redirects the users to different search engine whenever they try to use Google.

VSearch bug reported earlier by vigilant security researcher

A German security researcher named Stefan Esser had made this bug public earlier this week. It should be noted that the generally accepted protocol is to inform Apple about the new bug discoveries not to disclose it to the public and cause a furor. Some of the hackers had already taken advantage of this bug found by the German researcher. They had actively used this newfound vulnerability to attack Macs devices as said by a security company named MalwareBytes in their blogpost.

How this bug works and how it can be neutralized?

This bug is designed to effectively take advantage of the Mac OS X 10.10 (Yosemite) features that determines which programs are allowed to make changes on the computer without the need of password. Yosemite makes a list of those programs and keeps it hidden in a file named Sudoers. However, this bug allows the malware to get listed in the Sudoers file which simply means that the malware gets the capability to install any in any part of the OS without users approval via password.

Esser had provided a fix to solve this malware issue. It should also be noted that next patch for the Yosemite will include the bug fix because even Apple about this vulnerability for a while.

Another deadly bug, which take over the control of Mac device

Another group of security researchers had found a more threatening bug, which has the ability to take permanent control of the Mac device. Users can effectively get rid of most vicious malwares by reinstalling the operating system but this new vulnerability in Mac devices turn the game away from the users. Using this particular vulnerability hacker can easily install the malware directly in the computer’s firmware, which is responsible for booting up the computer.

A team of researchers had developed this worm and named it Thunderstrike 2 which can easily take the advantage of this security flaw in Mac deices.

This worm can be installed on the computer just like any other malware where people happen to click on wrong links or fails to the ploy of phishing scam. Once installed this malware takes a nastier turn and keeps looking for the devices connected to Mac in order to load them with worm. Other users when uses the same infected Ethernet adapter happens to get their Mac devices infected too. This bug has not been fixed till now by the Apple.