MACHINE VISION

1
MACHINE VISION

• By Sean Ricks OCT 08, 07

2
What is Machine Vision?

• Machine Vision is the application of computer
  vision to industry and manufacturing.
• Machine vision is the capturing of an image (a
  snapshot in time), the conversion of the image to
  digital information, and the application of
  processing algorithms to extract useful
  information about the image for the purposes of
  pattern recognition, part inspection, or part
  positioning and orientation.Ed Red

3
Typical Requirements

• One or more digital or analog camera
  (black-and-white or color) with suitable optics
  for acquiring images
• Camera interface for digitizing images (widely
  known as a "frame grabber")
• A processor (often a PC or embedded processor,
  such as a DSP)
• (In some cases, all of the above are combined
  within a single device, called a smart camera).
• Input/Output hardware or communication links
• Lenses to focus the desired field of view onto
  the image sensor.
• Suitable, often very specialized, light sources
  (LED illuminators, fluorescent or halogen lamps
  etc.)
• A program to process images and detect relevant
  features.
• A synchronizing sensor for part detection (often
  an optical or magnetic sensor) to trigger image
  acquisition and processing.
• Some form of actuators used to sort or reject
  defective parts.

4
Current State
5
Major Vendors of Machine Vision

• Sony
• Basler
• Stemmer Imaging
• Lumenera
• Aegis
• Scorpion
• E2v
• Keyence
• Soliton
• Cognex
• many many more

6
Important Rules

• Segmentation Define and separate regions of
  interest
• Thresholding Convert each pixel into binary (B
  or W) value by comparing bit intensities
• Edge detection Locate boundaries between
  objects
• Feature extraction Determine features based on
  area and boundary characteristics of image
• Pattern recognition Identify objects in midst
  of other objects by comparing to predefined
  models or standard values (of area, etc.)

Image taken from www.solitontech.com
7
Specifications

• Image Sensor
• of Total Pixels
• Lens Type
• Angle of View
• Minimum Object Distance
• Minimum Illumination
• Inspection Rate
• Focusing System
• Data Format
• Video Output

• Operating Temperature
• Power Consumption
• Dimensions
• Mass
• AE Control
• Camera Control Interface

8
Cost

• Program example Vision Builder AI and PCI-1410,
  High Performance,4-channel, mono
• Dev Kit - Vision Builder AI Development Kit
• Cables and Mounts
• Camera
• Lighting - LED ring light with constant current
  source

• 2000.00
• 1000.00
• 300.00 - 600.00
• 1200.00 5000.00
• 1000.00
• TOTAL 5500.00 - 9600.00

Data courtesy of national instruments www.ni.com
9
Example

• A video camera has a 640 x 480 pixel matrix
  (VGA). Each pixel must be converted from an
  analog signal to the corresponding digital signal
  by an ADC. The analog-to-digital conversion takes
  0.1 microsecond (0.1 x 10-6 sec) to complete,
  including the time to move between pixels. How
  long will it take to collect the image data for
  one frame, and is this time compatible with
  processing at the rate of 30 frames per second?

10
Example

• A video camera has a 640 x 480 pixel matrix
  (VGA). Each pixel must be converted from an
  analog signal to the corresponding digital signal
  by an ADC. The analog-to-digital conversion takes
  0.1 microsecond (0.1 x 10-6 sec) to complete,
  including the time to move between pixels. How
  long will it take to collect the image data for
  one frame, and is this time compatible with
  processing at the rate of 30 frames per second?
• There are 640 x 480 307,200 pixels to be
  scanned and converted. The total time to
  complete the analog-to-digital conversion process
  is
• (307,200 pixels)(0.1 x 10-6 sec) 0.0307 sec
• At a processing rate of 30 frames per second,
  the processing time for each frame is 0.0333 sec,
  which is longer than the 0.0307 sec required to
  perform the 307,200 analog-to-digital
  conversions.

11
Applications

• Color Camera Machine Vision Application
• http//www.solitontech.com/videos.htm
• Dimensional measurement
• Object verification
• Proper position/orientation
• Flaws and defects
• Counting
• Guidance and control (offsets, tracking)
• Inspection of pre-manufactured objects (e.g.
  quality control, failure investigation)
• Visual stock control and management systems
  (counting, barcode reading, store interfaces for
  digital systems)
• Control of Automated Guided Vehicles (AGVs)

12
Cutting Edge

• Machine Vision being used to do difficult tasks.
• Combining the camera to the P.C.
• Infrared Machine Vision for surveillance

13
Cutting Edge Infrared Surveillance
Technical Paper taken from http//www.machinevisi
ononline.org/public/articles/articlesdetails.cfm?i
d3318
14
Summary

• Machine Vision is found in many different aspects
  of automation
• Machine Vision components have many different
  specifications for your needs
• You need to take into consideration cost of
  components
• Machine vision is a growing technology being
  expanded to use not only in the commercial
  sector, but is being prepped for use in the
  private sector

15
Sources

• http//bssc.sel.sony.com/BroadcastandBusiness/Disp
  layModel?m10005p2sp18id87846navidseeing_i
  s_believing_with_sonys_new_ultra_high_5_mega______
  ___
• http//bssc.sel.sony.com/BroadcastandBusiness/mark
  ets/10005/docs/irvs_SHAFI_6.5.07.pdf
• http//www.solitontech.com/
• Demant C., Streicher-Abel B. and Waszkewitz P.
  (1999). Industrial Image Processing Visual
  Quality Control in Manufacturing.
  Springer-Verlag.
• http//www.machinevisiononline.org

16
Questions?