Latest Updates from Tech world;

Sunday, 29 April 2018

How Facial Recognition Systems Work?

How Facial Recognition Systems Work ?Steps involved in facial re cognition process, Techniques for face acquisition,Applications of facial recognition,Face recognition with AI

In Facebook and other social media sites , you might have noticed that it has the ability to recognize people's faces. In group photos peoples’ faces are recognized and tagged. This is just one example of high-tech facial recognition software. Facial recognition is used in lot of areas like security systems, access control, identity verification etc. Modern smartphones uses facial recognition to secure your data from unauthorized access. Here is How Facial Recognition Systems Work.

How we recognize other people’s faces? ,Human faces have certain qualities you recognize. The spacing of eyes on a face, the position and width of a nose, the shape of a hairline and chin -- these are all things that you unconsciously use to recognize someone’s face. A computer uses same method to identify faces.

How face recognition algorithm works?

Like other “biometric” identification systems, facial recognition examines physical features of a person’s face in an attempt to uniquely distinguish one person from all the others. Other forms of biometric recognition include the very common fingerprint matching, retina scanning, iris scanning and voice recognition.
A facial recognition system measures the overall facial structure, including distances between eyes, nose, mouth, and jaw edges. Each human face has approximately 80 nodal points. Distance between these nodal points are measured and stored. These measurements are retained in a database and used as a comparison when a user stands before the camera.

Some of the features measured for facial recognition are:
  • Distance between the eyes 
  • Width of the nose 
  • Depth of the eye sockets 
  • The shape of the cheekbones 
  • The length of the jaw line 
These nodal points are measured creating a numerical code, called a faceprint, representing the face in the database.

Five steps involved in facial recognition process are
  • Capture - a physical or behavioral sample is captured by the system during enrollment 
  • Extraction - unique data is extracted from the sample and a template is created 
  • Normalization: Normally face image is captured at different angles and different distances gives different measurements. These values needed to be normalized before comparing with the stored template. 
  • Comparison - the template is then compared with a new sample 
  • Matching - the system then decides if the features extracted from the new sample are matching or not 

Techniques for face acquisition

Traditional:In this method landmarks, or features, from an image of the subject's face are extracted. For example, an algorithm may analyze the relative position, size, and/or shape of the eyes, nose, cheekbones, and jaw .These features are then used to search for other images with matching features.In this techniques facial recognition camera used is a normal camera.

3-Dimensional recognition:Three-dimensional face recognition technique uses 3D sensors to capture information about the shape of a face. This information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose, and chin. It can identify a face from a range of viewing angles.Three-dimensional data points from a face vastly improve the precision of face recognition.
Thermal Cameras:Input for facial recognition can also be captured with Infrared thermal cameras. In this cameras will only detect the shape of the head and it will ignore the subject accessories such as glasses, hats, or make up. It uses low-sensitive, low-resolution ferro-electric electrics sensors that are capable of acquire long wave thermal infrared (LWIR). Fusion of LWIR and regular visual cameras has greater results in outdoor probes.

Applications of facial recognition

Social Media :Social media platforms have adopted facial recognition capabilities to diversify their functionalities in order to attract a wider user base amidst stiff competition from different photo tagging.
Mobile Technologies  ,Face ID :Apple introduced Face ID on the flagship iPhone X as a biometric authentication successor to the Touch ID, a fingerprint based system. Face ID has a facial recognition sensor that consists of two parts: first module that projects more than 30,000 infrared dots onto the user's face, and a second module that reads the pattern. Infrared sensors are used to ensure the camera is scanning your actual face and not a photo or 3D model. The pattern is then compared with confirm a match with the phone owner's face already stored in the phone. Apple’s Face ID also depends on AI(Artificial Intelligence) programs to improve the accuracy. Many other phones like Vivo V9 also comes with built in facial recognition.
Free facial recognition apps and facial recognition software are available for download and and use in mobile phones and PCs. But they are of limited accuracy.

Facial recognition in Security services :Most useful application of facial recognition systems is in security systems. It can be used in large open spaces like airports, arenas and shopping malls.

Advantages of facial recognition over other biometric technologies.

Face recognition technology is the least intrusive and fastest biometric technology.

Limitations and drawbacks of Facial Recognition

Poor resolution images and poor lighting can reduce the accuracy of face-scanning results.
Different angles and facial expressions, even a simple smile, can pose challenges for face matching systems. 

Facial recognition loses accuracy when the person is wearing items like glasses, hats, scarves, or hair styles that cover part of the face. Makeup and facial hair can also pose issues for face detection programs..

Facial recognition algorithm using Artificial Intelligence

In modern facial recognition programs Artificial Intelligence and neural network algorithms are blended to get better results. Neural networks learn from examples and respond to inputs it’s own based on the knowledge it acquired through examples. Even if input images are of poor quality , artificial intelligence algorithm can distinguish and identify images accurately.

Friday, 20 April 2018

Huawei to launch first 5G smartphone by mid 2019

At its Global Analyst Summit 2018 in Shenzhen,China, Huawei detailed its plans to release its first 5G-enabled smartphone in the second half of 2019.

Huawei aims outsmart it's western counterparts in 5G roll out revealing plans to launch a handset next year packing the firm’s very own 5G modem.

Huawei recently revealed the Balong 5G01 chip in February at MWC 2018, in Barcelona. The company claims the model is capable of 2.3Gbps bandwidth.

This particular model is designed for mobile hotspots and self-driving cars. However, it is also working on modems exclusively for use in 5G smartphone.

Huawei’s 5G NR products have passed TÜV SÜD's (the European Union's certification authority) strict verification requirements after several rounds of rigorous testing and evaluation. As a leading information and communications technology (ICT) solutions provider, Huawei is now the first company to achieve a CE type examination certificate (TEC) for its 5G products.

If Tech rumors are correct, first 5G handset would be from Huawei mate series.

5G handset from other manufactures

Samsung signed a strategic agreement with Qualcomm that covered the “transition to 5G".This tells that Samsung is also keen on 5G hansets.Samsung had previously earmarked 2019 for its first 5G handsets. Qualcomm already has its own modem called the X50 for mobile devices recently managed to hit speeds of 4.51 gigabits per second.

Intel announced a partnership with Microsoft, Dell, HP, and Lenovo to create 5G-enabled laptops based on Intel's own modems.

5G handset challenges

  • Building a 5G smartphone is more challenging than 3G or 4G as these will include multi-modes (2G,3G,4G,4.9G, 5G SA/NSA).Packing multiple antennas and chipsets into a single device is tough and challenging.
  • 5G uses Millimeter wave bands (26, 28, 38, and 60 GHz)., which makes the RF integration and positioning more complicated.Designing boards  for RF is challenging.
  • 5G network data speed will be 1-10Gb. 5G phone needs 5x more processing power and 2.5x more power consumption.Currently available batteries are not a good choice for 5 handsets.

Tuesday, 17 April 2018

Amazing features of Vivo V9 AI camera

Unique features of Vivo V9 AI(Artificial Intelligence) enabled camera can enhance your selfies like never before

features of Viivo v9 AI camera
Vivo V9 AI Camera
Chinese phone makers Vivo launched their latest smartphone Vivo V9 with a almost bezel-free 6.3-inch display, 24MP front camera and 16MP+5MP dual camera setup on the rear. Vivo V9 primarily focuses on high quality selfies.

Vivo claims thats "The V9’s world-leading 24MP front camera turns your every selfie into a work of art. Experience greater brightness, color vibrancy, clarity and dynamic range, even in the dimmest light. Whenever you need it, your V9 is right there with you, capturing every moment with crystal-clear precision. Turn your selfies into masterpieces and shine in every photo."

Features of Vivo V9 AI camera

-Bokeh effect: The Bokeh feature lets you blur the background and highlight the foreground before or after taking the shot.The V9 uses two rear cameras – a 16MP main camera and a 5MP secondary camera* – and is supported by an AI Bokeh algorithm. This algorithm has been optimized based on machine learning of large amounts of data, so it can achieve amazing bokeh shots that rival DSLR camera results.
Bokeh effect
-Shoot and focus later:You can even shoot first and focus later, transforming every photo into an artistic masterpiece.

-AI Face Beauty:Vivo claims - with the help of its AI (artificial intelligence) it will be able to work out your age, sex, skin tone and texture by referring to a database of almost one million facial images from all over the world, it detects your gender, age, skin tone and texture, as well as the lighting environment, and uses this information to deliver astonishingly clear, beautiful selfies.
It can also learn your customized setting preferences and apply these settings automatically each time you take a photo. Think of it as your personal make-up artist, ready to make you look naturally perfect in every shot.

-AI Face Access:With the all-new AI Face Access technology, the V9 scans your facial features and unlocks instantaneously upon activation. It also identifies unauthorized access attempts by detecting light-reflected surfaces and subtle facial movements, helping prevent phone unlocking through use of photos or video.
Vivo V9 AI camera face access

-AR Stickers:Vivo V9 comes with pre installed Augmented Reality(AR) stickers.
AR Sticker features numerous stickers that you can use to decorate your selfies and show off your cute side. Set your style to super-sweet, funny or punk, and transform your look with just a single click. Get ready to be playful and enjoy some serious photo fun.
Vivo v9 AI camera VR stickers
-Time-Lapse Photography:Time-lapse photography is a cinematography technique whereby the frequency at which film frames are captured (aka the frame rate) is much lower that that which will be used to play the sequence back. When you replay this sequence at normal speed, time appears to be moving faster and lapsing

-AI Selfie Lighting:With every photograph, the V9’s algorithm transforms the original 2D photo into a 3D model in order to process the light authentically and artistically. It can allow you to choose from a range of light effects to create model-style pictures. Get ready to transform any environment into your own professional photo studio.

-Group Panorama Selfie:The Vivo V9 also comes with the group selfies that allows you to shoot panoramic pictures from the front-facing camera. The feature requires you to move around the phone to get in as many as people in the frame as you’d like.

Other scene mode that are available with Vivo V9 AI camera:Ultra HD,PPT,Professional,Slow,,Camera Filter,Live,Bokeh,HDR,AI Face Beauty,Panorama,4K video, Palm capture,Gender detection,LED Flash,

Sunday, 15 April 2018

IBM creates ‘world’s smallest computer’ that’s smaller than a grain of salt

Recently during IBM Think 2018, the company's flagship conference, IBM unveiled what it claims is the world's smallest computer.The finished computer is smaller than a grain of salt.First of all let me tell you this tiny device is not for PC or smartphone.It has got some specific applications.
Left: 64 motherboards with two tiny computers in the top-left corner. Right: The tiny computer, mounted to a motherboard, atop a pile of salt. IBM
How much computing power tiny chip is embedded with?
It has the same computing power as Intel’s X86 chip from the 90s.It contains around million transistors.You may be wondering what we are going to do with such a small computing power.There comes the blockchain.

Architecture of IBM's world's smallest computer

IBM’s new computer, contains up to 1 million transistors, along with a small amount of static random access memory(RAM), a light-emitting diode (LED) and photo-detector that allow it to communicate, and an integrated photovoltaic(Solar cell) cell for power.
System architecture of IBM's tiny computer
How much it would cost?
IBM claims that it is “small enough and cheap enough to be put anywhere—and everywhere.”
The computer will cost less than 0.10$ to manufacture.On mass production it will reduce further.

Applications and uses of IBM's tiny computer

According to the company, the device will be a data source for anti-fraud blockchain applications.
Block chain is nothing but distributed decentralized database/Ledger that is nearly impossible to tamper.Blockchain became popular with bitcoin and cryptocurrencies. Specifically, this computer will be a data source for blockchain applications. It's intended to help track the shipment of goods and detect theft, fraud, and non-compliance.It can also do basic AI tasks, such as sorting the data it's given.

"Within the next five years, cryptographic anchors — such as ink dots or tiny computers smaller than a grain of salt — will be embedded in everyday objects and devices. They’ll be used in tandem with blockchain’s distributed ledger technology to ensure an object’s authenticity from its point of origin to when it reaches the hands of the customer. These technologies pave the way for new solutions that tackle food safety, authenticity of manufactured components, genetically modified products, identification of counterfeit objects and provenance of luxury goods".says IBM head of research Arvind Krishna.

Official release
It's not clear yet when this thing will be released — IBM researchers are currently testing its first prototype.
Join Our Newsletter