Friday, 29 September 2017

While privacy concerns have been a factor for years, it turns out that if you put a useful application in front of the MACHINE VISION’S algorithm —i.e., you make it fun — everyone’s happy. For example, a Russian music festival used a facial recognition algorithm to supply attendees with photos of themselves from the event, while a firm in Singapore is developing a transport ticketing system that uses voluntary facial recognition to charge commuters as they pass through fare gates.
It helps that consumers have face detection technology in the palm of their hands. Mobile applications such as FaceLock scan a user’s face in order to unlock apps on their smartphone or tablet. Furthermore, a recent patent filed by Apple suggests that the next generation iPhone will have “enhanced face detection using depth information.” Users also are relying on facial recognition for critical tasks such as mobile banking and commerce.
The projected growth of facial recognition and other biometrics usage reflects these trends. Facial recognition market size is estimated to rise from $3.3 billion in 2016 to $6.84 billion in 2021. Analysts attribute the growth to an expanding surveillance market, increasing government deployment, and other applications in identity management. The machine vision industry is starting to find ways to capitalize on the growth opportunities in facial recognition, whether it’s a camera calibrated to work in low light or a mobile app that helps police officers catch suspects. But the technology needs to overcome a few hiccups first.


Suspect Technologies, a startup in Cambridge, Massachusetts, has developed advanced facial recognition algorithms, but for two very different purposes within law enforcement. One use addresses the privacy considerations around body cameras worn by police officers. The most frequently cited goal of body worn video (BWV) is to improve law enforcement accountability and transparency. When someone files a Freedom of Information Act request to acquire one of these videos, law enforcement agencies must promptly comply. 
But they can’t do that without first blurring the identities of victims, minors, and innocent bystanders, which typically has been a slow, tedious process restricted to video specialists. Suspect Technologies’ automated video redaction (AVR) software, available on cameras manufactured by VIEVU, is optimized for the real-world conditions of BWV — most notably high movement and low lighting. The technology, which can track multiple objects simultaneously, features a simple interface that allows users to add or adjust redacted objects. AVR reduces the time it takes to redact video footage by tenfold over existing methods.
Unlike AVR which covers up identities, Suspect Technologies is rolling out a mobile facial recognition app to identify suspects. “As it stands now, there’s no simple way for law enforcement to tell if someone is a wanted criminal,” says Jacob Sniff, CEO and CTO of Suspect Technologies.
Compatible with iPhone and Android devices, the company’s cloud-based watchlist recognition software has been tested on 10 million faces. The algorithm takes advantage of better facial recognition accuracy, which increases tenfold every four years. “Our goal is to be 100% accurate on the order of 10,000 identities,” Sniff says.
Suspect Technologies will start by customizing the product for regional law enforcement agencies in midsized towns, which typically have about 100 wanted felons. The company also plans to introduce its software to schools and businesses for attendance-oriented applications. 
Machine Vision System


On the hardware side, the specifications of a facial recognition application are driving machine vision camera selection. “Monochrome cameras offer better sensitivity to light, so they are ideal in low-light conditions indoors and outdoors,” says Mike Fussell, product marketing manager of the integrated imaging division at FLIR SYSTEMS, Inc.(Wilsonville, Oregon). “If someone is strongly backlit or shadowed, cameras with the latest generation of high-performance CMOS sensors really shine in those difficult situations.”
For customers seeking better performance in low light, FLIR offers higher-end sensors that have high frame rates and global shutter. The entire pixel count reads out at the same time instantly, eliminating the distortion caused by the rolling shutter readout found on less expensive sensors, Fussell says. Rolling shutter cameras show distortion caused by the movement of the subject relative to the shutter movement, but they present a lower-cost alternative in low-light conditions.
Most cameras used in facial recognition are in the 3–5 MP range, according to Fussell. But in an application like a passport kiosk, where all of the variables are controlled, a lower-resolution camera is suitable. FLIR also offers stereo vision products that customers calibrate for optical tracking, which measures eye movement relative to the head. Some companies are taking the concept of facial recognition to the next level with gait analysis, the study of human motion. “In a building automation application, where you want to learn people’s habits, you could track their gait to turn lights on and off or have elevators waiting in advance for them,” Fussell says.


For all its potential, facial recognition technology must address fundamental challenges before an algorithm reaches a camera or mobile device. According to one study, face recognition systems are 5–10 percent less accurate when trying to identify African Americans compared to white subjects. What’s more, female subjects were more difficult to recognize than males, and younger subjects were more difficult to identify than adults. ”
As such, algorithm developers must focus more on the content and quality of the training data so that data sets are evenly distributed across demographics. Testing the face recognition system, a service currently offered by the National Institute of Standards and Technology (NIST), can improve accuracy. 
Once the algorithm reaches the camera, facial recognition’s accuracy is dependent upon the number and quality of photos in the comparison database. And even though most facial recognition technology Is automated, most systems require human examination to make the final match. Without specialized training, human reviewers make the wrong decision about a match half the time.
The machine vision industry, however, is no stranger to waiting for a technology to mature. Once facial recognition does that, camera makers and software vendors will be ready to supply the equipment and services for secure, accurate identity verification.



3 Raffles Place, #07-01 Bharat Building,Orchard RoadSingapore - 048617Tel: +65 63296431 Fax: +65 63296432 

Friday, 21 July 2017


In recent years, a miniaturization trend has been established in many areas of electronics. For example, ICs have become more and more integrated and circuit boards in the electrical industry have become smaller and more powerful. This has also made PCs, mobile phones and cameras more and more compact and powerful. This trend can also be observed in the world of vision technology.
A classic machine vision system consists of an industrial camera and a PC: Both were significantly larger a few years ago. But within a short time, smaller and smaller-sized PCs became possible, and in the meantime, the industry saw the introduction of single-board computers, i.e. computers that can be found on a single board. At the same time, the camera electronics became more compact and the cameras successively smaller. On the way to even higher integration, small cameras without housings are now offered, which can be easily integrated into compact systems.
Due to these two developments, the reduction in size of the PC and the camera, it is now possible to design highly compact camera vision systems for new applications. Such systems are called embedded (vision) systems.


An embedded vision system consists, for example, of a camera, a so-called board level camera, which is connected to a processing board. Processing boards take over the tasks of the PC from the classic machine vision setup. As processing boards are much cheaper than classic industrial PCs, vision systems can become smaller and also more cost-effective. The interfaces for embedded vision systems are primarily USB or BASLER BCON for LVDS.
Basler Camera Distributor in India
Embedded vision systems are used in a wide range of applications and devices, such as in medical technology, in vehicles, in industry and in consumer electronics. Embedded systems enable new products to be created and thereby create innovative possibilities in several areas.


As embedded systems, there are popular single-board computers (SBC), such as the Raspberry Pi®. The Raspberry Pi ® is a mini-computer with established interfaces and offers a similar range of features as a classic PC or laptop.
Embedded vision solutions can also be implemented with so-called system on modules (SoM) or computer on modules (CoM). These modules represent a computing unit. For the adaptation of the desired interfaces to the respective application, a so-called individual carrier board is needed. This is connected to the SoM via specific connectors and can be designed and manufactured relatively simply. The SoMs or CoMs (or the entire system) are cost-effective on the one hand since they are available off-the-shelf, while on the other hand they can also be individually customized through the carrier board.
For large manufactured quantities, individual processing boards are a good idea.
All modules, single-board computers, and SoMs, are based on a system on chip (SoC). This is a component on which the processor(s), controllers, memory modules, power management and other components are integrated on a single chip.
Due to these efficient components, the SoCs, embedded vision systems have only become available in such a small size and at a low cost as today.


Most of the above-mentioned single-board computers and SoMs do not include the x86 family processors common in standard PCs. Rather, the CPUs are often based on the ARM architecture.
The open-source Linux operating system is widely used as an operating system in the world of ARM processors. For Linux, there is a large number of open-source application programs, as well as numerous freely-available program libraries.
Increasingly, however, x86-based single-board computers are also spreading.
A consistently important criterion for the computer is the space available for the embedded system.
For the SW developer, the program development for an embedded system is different than for a standard PC. As a rule, the target system does not provide a suitable user interface which can also be used for programming. The SW developer must connect to the embedded system via an appropriate interface if available (e.g. network interface) or develop the SW on the standard PC and then transfer it to the target system.
When developing the SW, it should be noted that the HW concept of the embedded system is oriented to a specific application and thus differs significantly from the universally usable PC.
However, the boundary between embedded and desktop computer systems is sometimes difficult to define. Just think of the mobile phone, which on the one hand has many features of an embedded system (ARM-based, single-board construction), but on the other hand can cope with very different tasks and is therefore a universal computer.


In some cases, much depends on how the embedded vision system is designed. A single-board computer is often a good choice as this is a standard product. It is a small compact computer that is easy to use. This solution is also useful for developers who have had little to do with embedded vision.
On the other hand, however, the single-board computer is a system which contains unused components and thus generally does not allow the leanest system configuration. This solution is suitable for small to medium quantities. The leanest setup is obtained through a customized system. Here, however, higher integration effort is a factor. This solution is therefore suitable for large unit numbers.
The benefits of embedded vision systems at a glance:
  •  Lean system design
  •  Light weight
  •  Cost-effective, because there is no unnecessary hardware
  •  Lower manufacturing costs
  •  Lower energy consumption
  •  Small footprint


Embedded vision is the technology of choice for many applications. Accordingly, the design requirements are widely diversified. Depending on the specification, BASLER offers a variety of cameras with different sensors, resolutions and interfaces.
The two interface technologies that Basler offers for embedded vision systems in the portfolio are:
  •  USB3 Vision for easy integration and
  •  Basler BCON for LVDS for a lean system design
Both technologies work with the same Basler pylon SDK, making it easier to switch from one interface technology to the other.


USB 3.0 is the right interface for a simple plug and play camera connection and ideal for camera connections to single-board computers. The Basler pylon SDK gives you easy access to the camera within seconds (for example, images and settings), since USB 3.0 cameras are standard-compliant and GenICam compatible.
  •  Easy connection to single-board computers with USB 2.0 or USB 3.0 connection
  •  Field-tested solutions with Raspberry Pi®, NVIDIA Jetson TK1 and many other systems
  •  Profitable solutions for SoMs with associated base boards
  •  Stable data transfer with a bandwidth of up to 350 MB/s


BCON - Basler's proprietary LVDS-based interface allows a direct camera connection with processing boards and thus also to on-board logic modules such as FPGAs (field programmable gate arrays) or comparable components. This allows a lean system design to be achieved and you can benefit from a direct board-to-board connection and data transfer.
The interface is therefore ideal for connecting to a SoM on a carrier / adapter board or with an individually-developed processor unit.
If your system is FPGA-based, you can fully use its advantages with the BCON interface.
BCON is designed with a 28-pin ZIF connector for flat flex cables. It contains the 5V power supply together with the LVDS lanes for image data transfer and image triggering. You can configure the camera vialanes that work with the I²C standard.
BASLER'S PYLON SDK is tailored to work with the BCON for LVDS interface. Therefore, it is easy to change settings such as exposure control, gain, and image properties using your software code and pylons API. The image acquisition of the application must be implemented individually as it depends on the hardware used.
  •  Image processing directly on the camera. This results in the highest image quality, without compromising the very limited resources of the downstream processing board.
  •  Direct connection via LVDS-based image data exchange to FPGA
  •  With the pylon SDK the camera configuration is possible via standard I²C bus without further programming. The compatibility with the GenICam standard is given.
  •  The image data software protocol is openly and comprehensively documented
  •  Development kit with reference implementation available
  •  Flexible flat flex cable and small connector for applications with maximum space limitations
  •  Stable, reliable data transfer with a bandwidth of up to 252 MB/s


Although it is unusual for developers who have not had much to do with embedded vision to develop an embedded vision system, there are many possibilities for this. In particular, the switch from standard machine vision system to embedded vision system can be made easy. In addition to its embedded product portfolio, Basler offers many tools that simplify integration.
Find out how you can develop an embedded vision system and how easy it is to integrate a camera in our simpleshow video.


Embedded vision systems often have the task of classifying images captured by the camera: On a conveyor belt, for example, in round and square biscuits. In the past, software developers have spent a lot of time and energy developing intelligent algorithms that are designed to classify a biscuit based on its characteristics (features) in type A (round) or B (square). In this example, this may sound relatively simple, but the more complex the features of an object, the more difficult it becomes.
Algorithms of machine learning (e.g., Convolutional Neural Networks, CNNs), however, do not require any features as input. If the algorithm is presented with large numbers of images of round and square biscuits, together with the information which image represents which variety, the algorithm automatically learns how to distinguish the two types of biscuits. If the algorithm is shown a new, unknown image, it decides for one of the two varieties because of its "experience" of the images already seen. The algorithms are particularly fast on graphics processor units (GPUs) and FPGAs.



3 Raffles Place, #07-01 Bharat Building,Orchard RoadSingapore - 048617Tel: +65 63296431 Fax: +65 63296432 

Friday, 7 July 2017


Bayer Filter
  •  Nearly all color sensors follow the same principle (according to its inventor Dr.Bryce E. Bayer).

  •  The light sensitive cells or pixels on the sensor are only capable of distinguishing different levels of light. For this reason tiny color filters (red,green and blue) are placed in front of the pixel as part of the production process.

  •  In a subsequent step of image processing the filtered output values are combined to a “color pixel” again.

  •  To adapt closer to the perception of the human eye (which is much more green-sensitive than to other colors), twice as many green filters are used.
Burst Trigger Mode
  •  Generally a trigger event indicates the camera when to start recording, after a predefined amount of time (or when the memory is full) the recording stops.
  •  Depending on the application yet another trigger event tells the camera when to terminate the recording.
  •  In Burst Trigger Mode however the camera records as long and as often as the trigger is active (comparable to the triggering mechanism of a machine gun).
Mikrotron High Speed Camera in Singapore
CCD / CMOS comparison
  •  Abbreviations for the two main sensor technologies, describing the inner structure of the chip:

  •  „CMOS“: complementary metal-oxide semiconductor

  •  „CCD“: charge coupled device
A CCD-sensor provides a determined electrical charge per pixel, i.e. a certain amount of electrons according to the previous exposure.
These have to be captured pixel by pixel with a subsequent electronic circuit, converted into a voltage quantity and recalculated into a binary value.
This operation is rather time consuming. In addition the whole frame has to be grabbed, which requires comprehensive postprocessing.
CMOS sensors can be produced cheaper and offer the possibility of onboard preprocessing, the information of every pixel can be provided in a digitised mode.
  •  Thus the camera may be designed smaller and random acces to particular parts of the image (“ROI”, region of interest) is possible.

  •  Needing less external circuits results in reduced power consumtion of the camera, the stored frames can be read out much faster.
Dynamic Range Adjustment
  •  The human eye has a very extensive dynamic range, i.e. can evaluate very low lighting conditions (like candle- or starlight) as well as extreme light impressions (reflected sunlight on a water surface).

  •  This corresponds to a (logarhithmic) dynamic range of 90dB.That means, two objects with 1,000,000,000 times different quantity of light can both be seen clearly.

  •  Unlike this, a CMOS camera has a linear dynamic range of about 60dB which equals a ratio of 1:1000.

  •  If for instance a recording setup requires to identify dim component labels with large welding reflections, image details within the reflection area can not be seen.

  •  Cameras with Dynamic Range Adjustment enable the user to adjust the linear response in certain areas: overexposed objects become darker without loosing intensitiy on the dark ones.

  •  Thus minimal variations of luminosity can be detected, even in areas

  •  of intense reflective light.
Fixed Pattern Noise (FPN)
  •  Every single pixel or photodiode in a CMOS camera has a construction related tolerance.

  •  Even without any exposure to light the diodes generate slightly varying output values.

  •  To avoid a corruption of the image, a process similar to the white balance in digital photography compares a reference picture with a dark frame.

  •  This frame contains only the detected differences and is used to correct the subsequent images of the sensor.

  •  Only after this kind of postprocessing e.g. a plain white area is displayed homogenously white.
Gigabit Ethernet (GigE)
  •  This data transfer technology allows the transmission among various devices (server, printer, mass storage, cameras) within a network.

  •  While standard Ethernet is to slow for the transfer of comprehensive image data, Gigabit Ethernet (GigE) with a maximum transfer rate of 1000Mbit/s or 1 Gigabit per second ensures a dependable image transfer in machine vision cameras.
GigE Vision
  •  GigE Vision is a industrial standard, developed by the AIA (Automated Imaging Association) for high performance machine vision cameras, optimised for the transfer of large amounts of image data.

  •  GigE Vision bases on the network structure of Gigabit Ethernet and includes a hardware interface standard (Gigabit Ethernet) and communication protocolls as well as standardised communication- and controlmodi for cameras.

  •  The GigE Vision camera control is based on a command structure named GenICam.

  •  This establishes a common camera interface to enable communication with third party vision cameras without any customisation.
ImageBLITZ automatic trigger
  •  To capture an unpredictable or unmeasurable event for "inframe" triggering purpose, Mikrotron invented the ImageBLITZ operation mode.

  •  In most cases no further equipment or elaborate trigger sensing devices for camera control are needed, the picture itself is the trigger.

  •  Within certain limits the ImageBLITZ is adjusted to react only to the expected changes in a predefined area of the picture.
Multi Sequence Mode
  •  In this mode the available memory of the camera is divided into many individual sequences. Following each trigger event (e.g. keystroke or a light barrier is set off) a predefined number of frames is saved.

  •  In repeatedly occuring events the different variations can be compared and provide a valuable base for the analysis of malfunctions or technical processes.

  •  Even a previously determined amount of frames before and after the trigger event can be saved within every recorded sequence.
Sobel Filter
  •  In several machine vision applications as motion analysis, positioning or pattern matching it is essential to determine certain edges, outlines or coordinates.

  •  The Sobel filter uses an edge-detection algorithm to detect just those edges and produces a chain of pixels (just on/off) that resembles the edges.

  •  This process allows to cut down the data stream already in the FPGA-chip of the camera for more than 80%. Less data has to be transferred and processed, the transfer rate rises considerably.
Suspend to Memory Mode
  •  The operation of a camera is reduced to the preservation of recorded images.

  •  Due to resulting low power consumtion the charge of the storage battery lasts significantly longer.

  •  This mode is activated either automatically after recording or manually by pressing a button.

  •  Thus the recording memory can be preserved for 24 hours.



3 Raffles Place, #07-01 Bharat Building,
Orchard Road
Singapore - 048617
Tel: +65 63296431 
Fax: +65 63296432 

Tuesday, 14 February 2017

Vision System Inspects X-ray Dosimeter Badges – Helmholtz-Zentrum 

In Germany, the inspection of x-ray dosimeters worn by people who may be exposed to radiation is a governmental responsibility. Only a handful of institutions are qualified to perform such tasks. One of which, the Helmholtz-Zentrum (Munich, Germany) is responsible for the analysis of approximately 120,000 film badge dosimeters a month.

Previously these 120,000 film badges were evaluated manually. To speed this inspection and increase reliability, the Helmholtz-Zentrum has developed a machine-vision system to automatically inspect these films. The film from each dosimeter badge is first mounted on a plastic adhesive foil, which is wound into a coil. This coil is then mounted on the vision system so that each film element can be inspected automatically (see figure). To analyze each film, a DX4 285 FireWire camera from Kappa optronics (Gleichen, Germany) is mounted on a bellows stage above the film reel. 

Data from this camera is then transferred to a PC and processed using HALCON 9.0 from MVTec Software (Munich, Germany). Resulting high-dynamic-range images are then displayed using an ATIFire GL V3600 graphic board from AMD (Sunnyvale, CA, USA) on a FlexScan MX 190 S display from Eizo (Ishikawa, Japan). Before the optical density of the film is measured, its presence and orientation must be determined. As each film moves under the camera system’s field of view, this presence and orientation task is computed using HALCON’s shape-based matching algorithm.

Both the camera and a densitometer are used to measure the optical density of the film. The densitometer measures the brightness at each of seven points on the film in high precision and is used to calibrate the camera measurement for every film image. To increase the dynamic range of the gray-level image of the film, two images with different exposure times are computed and combined into a high-dynamic-range image. Because the background lighting is not homogenous, shading correction is performed to eliminate any lighting variation. Any lens vignetting and variations caused by pixel-to-pixel sensitivity variation is eliminated by flat-field correction. The optical density is converted into a photon dose using a linear algebraic function to calculate the x-ray dose to which the film was exposed.

Every film reading must be correlated with the unique specimen number associated with each badge. Since these numbers are deposited onto the film material, approximately 10,000 characters needed to be trained and saved to an OCR database using HALCON. After the film is identified, the system must also detect which type of dosimeter cassette has been used to house the film. Since each cassette uses a different x-ray filter, the shadow cast on the film can be either rectangular or round. Thus, a grayscale analysis of these shadows can be used to detect the differences between the different types of cassettes that were used to house the film. To pinpoint the specific causes of x-ray exposure, the system is also programmed to detect whether any potential exposure is caused by errors in film developing or x-ray contamination. If the imaging system detects contamination events, these are then reported manually.

To Know More About Machine Vision System in Singapore, Contact MVAsia Infomatrix Pte Ltd at +65 6329-6431 or Email us at


3 Raffles Place, #07-01 Bharat Building,
Orchard Road
Singapore - 048617
Tel: +65 63296431 
Fax: +65 63296432
Source -