MACHINE VISION

What is Machine Vision ?

• Machine vision can be defined as the acquisition of image of data,
followed by the processing and interpretation of these data by
computer for some useful application.
• Also called computer vision, since a digital computer is required to
process the image data is rapidly growing technology, with its
principal applications in industrial inspection.
• Vision systems are classified as being either 2D or 3D.
• Two- dimensional systems view the scene as a 2-D image.
• This is quite adequate for most industrial applications, since many
situations involve a 2-D scene.
• Examples include dimensional measuring and gaging, verifying the
presence of components, and checking for features on a flat (or
semiflat)
• Other applications require 3-D analysis of the scene, and 3-D vision
systems are required for this purpose.
• The operation of a machine vision system can be divided into the
1. 2.
following three functions:
Image Image
3.
acqui proce Inter
sition ssing pret
and and atio
digitiz analy
ation sis n
Basic functions of a machine vision system
1. Image acquisition and digitization
• Image acquisition and digitization is accomplished using a video
camera and a digitizing system to store the image data for subsequent
analysis.
• The camera is focused on the subject of interest, and an image is
obtained by dividing the viewing area into a matrix of discrete picture
elements (called pixels), in which each element has a value that is
proportional to the light intensity of that portion of the scene.
• The intensity value for each pixel is converted into its equivalent
digital value by an ADC (section 5.3)
• The operation of viewing a scene consisting of a simple object that
contrasts substantially with its background, and dividing the scene
into a corresponding matrix of picture elements, is depicted in figure
23.11.
• The figure illustrates the likely image obtained from the simplest type
of vision system, called a binary vision system.
• In binary vision, the light intensity of each pixel is ultimately reduced
to either of two values, white or black, depending on whether the
light intensity exceeds a given threshold level.
• A more sophisticated vision system is capable of distinguishing and
storing different shades of gray in the image. This is called a gray-
scale system.
• This type of system can determine not only an object’s outline and
area characteristics, but also its surface characteristics such as texture
and colour.
• Gray-scale vision systems typically use 4,6 or 8 bits of memory. Eight
bits corresponds to = 256 intensity levels, which is generally more
levels than the video camera can really distinguish and certainly more
than the human eye can discern.
• Each set of digitized pixel value is referred to as a frame. Each frame is
stored in a computer memory device called a frame buffer.
• The process of reading all the pixel values in a frame is performed
with a frequency of 30 times per second (typical in the United States,
25 times per second in European vision systems).
• Types of Cameras. Two types of cameras are used in machine vision
applications: vidicon cameras (the type used for television) and solid-
state cameras.
• Vidicon cameras operate by focusing the image onto a
photoconductive surface and scanning the surface with an electron
beam to obtain the relative pixel values.
• Different areas on the photoconductive surface have different voltage
levels corresponding to the light intensities striking the areas.
• The electron beam follows a well-defined scanning pattern, in effect
dividing the surface into a large number of horizontal lines, and
reading the lines from top-to-bottom.
• Each line is in turn divided into a series of points. The number of
points on each line, multiplied by the number of lines, gives the
dimensions of the pixel matrix shown in figure 23.11. During the
scanning process, the electron beam reads the voltage level of each
pixel.
• Solid-state cameras operate by focusing the image onto a 2-D array of
very small, finely spaced photosensitive elements. The photosensitive
elements from the matrix of pixels shown in figure 23.11. An electrical
charge is generated by each element according to the intensity of
light striking the element.
• The charge is accumulated in a storage device consisting of an array of
storage elements corresponding one-to-one with the photosensitive
picture elements. These charge values are read sequentially in the
data processing and analysis function of machine vision.
• Comparing the vidicon camera and solid-state camera, the latter
possesses several advantages in industrial applications. It is physically
smaller and more rugged,and the image produced is more stable.
• The vidicon camera suffers from distortion that occurs in the image of a
fast-moving object because of the time lapse associated with the
scanning electron beam as it reads the pixel levels on the
photoconductive surface.
• The relative advantages of the solid-state cameras have resulted in the
growing dominance of their use in machine vision systems. Types of solid-
state cameras include: (1) charge-coupled-device (CCD), (2) charge-
injected device (CID), and (3)charge –priming device (CPD). These types
are compared in [8].
• Typical square pixel arrays are 256 256,512 512, and 1024 1024
picture elements. Other arrays include 240 320,500 582 and 1035
1320 pixels (24).
• The resolution of the vision system is its ability to sense fine details
and features in the image.
• Resolution depends on the number of picture elements used ; the
more pixels designed into the vision system, the higher its resolution.
However, the cost of the camera increases as the number of pixels is
increased.
• Even more important, the time required to sequentially read the
picture elements and process the data increases as the number of
pixels grows. The following example illustrates the problem.
• Illumination. Another important aspect of machine vision is illumination.
The scene viewed by the vision camera must requires that special lighting
be installed for a machine vision application rather than rely on ambient
lighting in the facility.
• Five categories of lighting can be distinguished for machine vision
applications, as depicted in Figure 23 12: (a) front lighting, (b) back
lighting, (c) side lighting, (d) structured lighting, and (e) strobe lighting.
• These categories represent differences in the positions of the light source
relative to the camera as much as they do differences in lighting
technologies. The lighting technologies include incandescent lamps,
fluorescent lamps, sodium vapor lamps, and lasers.
• In front lighting, the light source is located on the same side of the
object as the camera. This produces a reflected light from the object
that allows inspection of surface features such as printing on a label and
surface patterns such as solder lines on a printed circuit board.
• In back lighting, the light source is placed behind the object being
viewed by the camera. This type of lighting can be used for binary vision
systems to inspect for part dimensions and to distinguish between
different part outlines.
• Side lighting causes irregularities in an otherwise plane smooth surface
to cast shadows that can be identified by the vision system. This can be
used to inspect for defects and flaws in the surface of an object.
• Structured lighting involves the projection of a special light pattern onto
the object to enhance certain geometric features. Probably the most
common structured light pattern is a planar sheet of highly focused light
directed against the surface of the object at a certain known angle, as in
Figure 23.12(d).
• The sheet of light forms a bright line where the beam intersects the
surface. In our sketch, the vision camera is positioned with its line of
plane of the part appear as deviations from a straight line.
• The distance of the deviation can be determined by optical
measurement, and the corresponding elevation differences can be
calculated using trigonometry.
• In strobe lighting, the scene is illuminated by a short pulse of high-
intensity light, which causes a moving object to appear stationary.
• The moving object might be a part moving past the vision camera on
a conveyor. The pulse of light can last 5-500 microseconds [8].
• This is sufficient time for the camera to capture the scene, although
the camera actuation must be synchronized with that of the strobe
light.
2. Image processing and analysis
• The second function in the operation of a machine vision system is
image processing and analysis. As indicated by Example 23.4, the
amount of data that must be processed is significant. The data for each
frame must be analyzed within the time required to complete one scan
(1/30 sec).
• A number of techniques have been developed for analyzing the image
data in a machine vision system. One category of techniques in image
processing and analysis is called segmentation.
• Segmentation techniques are intended to define and separate regions
of interest within the image. Two of the common segmentation
techniques are thresholding and edge detection.
• Thresholding involves the conversion of each pixel intensity level into
a binary value, representing either white or black. This is done by
comparing the intensity value of each pixel with a defined threshold
value.
• If the pixel value is greater than the threshold, it is given the binary
bit value of white, say 1; if less than the defined threshold, then it is
given the bit value of black, say 0.
• Reducing the image to binary form by means of thresholding usually
simplifies the subsequent problem of defining and identifying objects
in the image.
• Edge detection is concerned with determining the location of
boundaries between an object and its surroundings in an image.
• This is accomplished by identifying the contrast in light intensity that
exists between adjacent pixels at the borders of the object. A number
of software algorithms have been developed for following the border
around the object.
• Another set of techniques in image processing and analysis that
normally follows segmentation is feature extraction.
• Most machine vision systems characterize an object in the image by
means of the object’s features.
• Some of the features of an object include the object’s area, length,
width, perimeter, center of gravity, and aspect ratio.
• Feature extraction methods are designed to determine these features
based on the area and boundaries of the object (using thresholding,
edge detection, and other segmentation techniques).
• For example, the area of the object can be determined by counting
the number of white (or black) pixels that make up the object. Its
length can be found by measuring the distance (in terms of pixels)
between the two extreme opposite edges of the part.
3. Interpretation
• For any given application, the image must be interpreted based on
the extracted features.
• The interpretation function is usually concerned with recognizing the
object, a task termed object recognition or pattern recognition.
• The objective in these tasks is to identify the object in the image by
comparing it with predefined models or standard values.
• Two commonly used interpretation techniques are template matching
and feature weighting.
• Template matching is the name given to various methods that attempt
to compare one or more features of an image with the corresponding
features of a model or template stored in computer memory.
• The most basic template matching technique is one in which the image
is compared, pixel by pixel, with a corresponding computer model.
• Within certain statistical tolerances, the computer determines whether
the image matches the template. One of the technical difficulties with
this method is the problem of aligning the part in the same position
and orientation in front of the camera, to allow the comparison to be
made without complications in image processing.
• Feature weighting is a technique in which several features (e.g., area,
length, and perimeter) are combined into a single measure by
assigning a weight to each feature according to its relative importance
in identifying the object.
• The score of the object in the image is compared with the score of an
ideal object residing in computer memory to achieve proper
identification
Machine Vision Applications
• The reason for interpreting the image is to accomplish some practical
objective in an application.
• Machine vision applications in manufacturing divide into three
categories: (1) inspection, (2) identification, and (3) visual guidance
and control.
• Inspection. By far, quality control inspection is the biggest category.
Estimates are that inspection constitutes about 80% of machine vision
applications [22].
• Machine vision installations in industry perform a variety of
automated inspection tasks, most of which are either on-line/in-
process or on-line/post-process.
• The applications are almost always in mass production where the
time required to program and set up the vision system can be spread
over many thousands of units. Typical industrial inspection tasks
include the following:
• Dimensional measurement. These applications involve determining
the size of certain dimensional features of parts or products usually
moving at relatively high speeds on a moving conveyor. The machine
vision system must compare the features (dimensions) with the
corresponding features of a computer-stored model and determine
the size value.
• Dimensional gaging. This is similar to the preceding except that a
gaging function rather than a measurement is performed.
• -Verification of the presence of components in an assembled product.
Machine vision has proved to be an important element in flexible
automated assembly systems.

• -Verification of hole location and number of holes in a part.

Operationally, this task is similar to dimensional measurement and
verification of components.
• -Detection of surface flaws and defects. Flaws and defects on the
surface of a part or material often reveal themselves as a change in
reflected light. The vision system can identify the deviation from an
ideal model of the surface.

• -Detection of flaws in a printed label. The defect can be in the form

of a poorly located label or poorly printed text, numbering, or
graphics on the label.
• All of the preceding inspection applications can be accomplished using 2-D
vision systems.
• Certain applications require 3-D vision, such as scanning the contour of a
surface, inspecting cutting tools to check for breakage and wear, and
checking solder paste deposits on surface mount circuit boards.
• Three-dimensional systems are being used increasingly in the automotive
industry to inspect surface contours of parts such as body panels and
dashboards.
• Vision inspection can be accomplished at much higher speeds than the
traditional method of inspecting these components, which involves the use
of CMMs.
• Other Machine Vision Applications. Part identification applications
are those in which the vision system is used to recognize and perhaps
distinguish parts or other objects so that some action can be taken.
• The applications include part sorting, counting different types of parts
flowing past along a conveyor, and inventory monitoring. Part
identification can usually be accomplished by 2-D vision systems.
• Reading of 2-D bar codes and character recognition (Sections 12.3.3
and 12.3.4) represent additional identification applications performed
by 2-D vision systems.
• Visual guidance and control involves applications in which a vision
system is teamed with a robot or similar machine to control the
movement of the machine.
• Examples of these applications include seam tracking in continuous
arc welding, part positioning and/or reorientation, bin picking,
collision avoidance, machining operations, and assembly tasks. Most
of these applications require 3-D vision.
OTHER OPTICAL INSPECTION
METHODS
• Machine vision is a well-publicized technology, perhaps because it is
similar to one of the important human senses.
• Its potential for applications in industry is very high. However, there
are also other optical sensing techniques that are used for inspection.
Our discussion in this section surveys these technologies.
• The dividing line between machine vision and these techniques is
sometimes blurred (excuse the pun).
• The distinction is that machine vision tends to imitate the capabilities
of the human optical sensory system, which includes not only the
eyes but also the complex interpretive powers of the brain. The
reader will note that the techniques in this section have a much
simpler mode of operation.
• Scanning Laser Systems. The unique feature of a laser (laser stands
for light amplification by stimulated emission of radiation) is that it
uses a coherent beam of light that can be projected with minimum
diffusion. Because of this feature, lasers have been used in a number
of industrial processing and measuring applications. High-energy laser
beams.