Digital Image Processing

Prof.H.T.Patil CCOEW, PUNE

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

What is a Digital Image?

A digital image is a representation of a twodimensional image as a finite set of digital values, called picture elements or pixels

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

What is a Digital Image?

Pixel values typically represent gray levels, colours, heights, opacities etc Remember digitization implies that a digital image is an approximation of a real scene
1 pixel

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

What is a Digital Image?

Common image formats include:
1 sample per point (B&W or Grayscale) 3 samples per point (Red, Green, and Blue){RGB} 4 samples per point (Red, Green, Blue, and Alpha){RGBA} (ex: PNG)

5/17/2012 Prof.H.T.Patil, CCOEW,PUNE For BE(2008) DIP course, we will focus on grey-scale images

What is a Digital Image?

Raster formats(Bitmaps)
JPEG/JFIF (Joint Photographic Experts Group) /(JPEG File Interchange Format) JPEG 2000 Exif (Exchangeable image file format)(image information) TIFF (Tagged Image File Format)(printing business)(CMYK) RAW PNG (Portable Network Graphics) GIF (Graphics Interchange Format) BMP PPM, PGM, PBM, (portable pixmap,graymap,bitmap) WEBP

Vector formats
CGM (Computer Graphics Metafile) Gerber Format (RS-274X) (PCB Software) SVG (Scalable Vector Graphics)

Stereo formats
PNS (PNG stereo) JPS (JPEG stereo)
5/17/2012 Prof.H.T.Patil, CCOEW,PUNE 5

What is Digital Image Processing?

Digital image processing focuses on two major tasks
Improvement of pictorial information for human interpretation Processing of image data for storage, transmission and representation for autonomous machine perception

Some argument about where image processing ends and fields such as image analysis and computer vision start
5/17/2012 Prof.H.T.Patil, CCOEW,PUNE 6

What is Digital Image Processing?

The continuum from image processing to computer vision can be broken up into low, mid and high level processes
Low Level Process Input: Image Output: Image Examples: Noise removal, image sharpening Mid Level Process Input: Image Output: Attributes Examples: Object recognition, segmentation High Level Process Input: Attributes Output: Understanding Examples: Scene understanding, autonomous navigation

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

DIP Applications
The use of digital image processing techniques has exploded and they are now used for all kinds of tasks in all kinds of areas
Image enhancement/restoration Artistic effects Medical visualisation Industrial inspection Law enforcement Human computer interfaces
5/17/2012 Prof.H.T.Patil, CCOEW,PUNE 8

Examples: Image Enhancement

One of the most common uses of DIP techniques: improve quality, remove noise etc.

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

Examples: The Hubble Telescope

Launched in 1990 the Hubble telescope can take images of very distant objects However, an incorrect mirror made many of Hubbles image Image techniques were used to fix this images

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

10

Examples: Artistic Effects

Artistic effects are used to make images more visually appealing, to add special effects and to make composite images

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

11

Examples: Medicine
Take slice from MRI scan of canine heart, and find boundaries between types of tissue
Image with gray levels representing tissue density Use a suitable filter to highlight edges

5/17/2012 Original

Prof.H.T.Patil, CCOEW,PUNE Edge Detection Image MRI Image of a Dog Heart

12

Examples: GIS
Geographic Information Systems
Digital image processing techniques are used extensively to manipulate satellite imagery Terrain classification Meteorology

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

13

Examples: GIS
Night-Time Lights of the World data set
Global inventory of human settlement Not hard to imagine the kind of analysis that might be done using this data

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

14

Examples: Industrial Inspection

Human operators are expensive, slow and unreliable Make machines do the job instead Industrial vision systems are used in all kinds of industries
5/17/2012 Prof.H.T.Patil, CCOEW,PUNE 15

Examples: PCB Inspection

Printed Circuit Board (PCB) inspection
Machine inspection is used to determine that all components are present and that all solder joints are acceptable Both conventional imaging and x-ray imaging are used

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

16

Examples: Law Enforcement

Image processing techniques are used extensively by law enforcers
Number plate recognition for speed cameras/automated toll systems Fingerprint recognition Enhancement of CCTV images
5/17/2012 Prof.H.T.Patil, CCOEW,PUNE 17

Examples: HCI
Try to make human computer interfaces more natural
Face recognition Gesture recognition

These tasks can be extremely difficult

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

18

Key Stages in Digital Image Processing

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain
Colour Image Processing
5/17/2012

Representation & Description

Image Compression
19

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Image Aquisition

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
20

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Image Enhancement

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
21

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Image Restoration

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
22

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Morphological Processing

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
23

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Segmentation

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
24

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Object Recognition

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
25

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Representation & Description

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
26

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Image Compression

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
27

Prof.H.T.Patil, CCOEW,PUNE

Key Stages in Digital Image Processing: Colour Image Processing

Image Restoration Morphological Processing

Image Enhancement

Segmentation

Image Acquisition

Object Recognition

Problem Domain Colour Image Processing

5/17/2012

Representation & Description

Image Compression
28

Prof.H.T.Patil, CCOEW,PUNE

Components of Digital Image Processing System

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

29

Components of Digital Image Processing System

image capture A/D conversion short term storage signal processing

image transfer

networking

archiving

image processing

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

30

What is digitizer?
Digitizer is used to convert any analog source of input, such as the lines in a picture, to a series of binary code in a computer. So it is a kind of input devices.

Examples of digitizer

Modem

Graphics Tablet

Examples of digitizer
scanner Digitizer pointer camera

Video digitizer

Function of digitizer
Change analog signal/image to digital signal/image for processing and computer display .
analog signal Modem digital signal

Internet

Function of digitizer
Change analog signal in the picture to digital signal for computer

analog signal

digital signal

scanner

How a digital camera works

Photo subject

Reflected light enters via lens

Image focuses onto beam splitter

CCD or CMOS sense each color

Storage to RAM

Processed image stored to long term memory

What breaks down the info into digital data?

A sensor converts the light into electrical charges Digital Cameras/Digitizers use CCDs (Charged Couple Devices) or CMOS (Complementary Metal Oxide Semiconductor)
Both convert light into electrons Value is read of each cell in the image

Whats the real difference CCD/CMOS

Because each pixel on a CMOS CCD sensors create highsensor has several transistors quality, low-noise images. located next to it, the light CMOS sensors are generally sensitivity of a CMOS chip is more susceptible to noise. lower. Many of the photons hit the transistors instead of the photodiode. CCD sensors have been CMOS sensors traditionally consume little power. CCDs, on the other hand, use a process that consumes lots of power. CCDs consume as much as 100 times more power than an equivalent CMOS sensor.

mass produced for a longer period of time, so they are more mature. They tend to have higher quality pixels, and more of them.

What else is important in a Digital Cameras/Digitizers?

Resolution:
The amount of detail that the camera can capture and it is measured in pixels. The more pixels a camera has, the more detail it can capture and the most of the pictures can be without becoming blurry or "grainy."

What else is important in a Digital Cameras/Digitizers?

Resolution: The resolution of an image tells you how small and densely packed the pixels are. It tells you how many pixels you have per inch.

18 ppi

36 ppi

72 ppi

150 ppi

Common Resolutions
256x256 - Found on very cheap cameras, this resolution is so low that the picture quality is almost always unacceptable. This is 65,000 total pixels. 640x480 - This is the low end on most "real" cameras. This resolution is ideal for emailing pictures or posting pictures on a Web site. 1216x912 - This is a "megapixel" image size -- 1,109,000 total pixels -- good for printing pictures. 1600x1200 - With almost 2 million total pixels, this is "high resolution." You can print a 4x5 inch print taken at this resolution with the same quality that you would get from a photo lab.

2240x1680 - Found on 4 megapixel cameras -- the current standard -- this allows even larger printed photos, with good quality for prints up to 16x20 inches.
4064x2704 - A top-of-the-line digital camera with 11.1 megapixels takes pictures at this resolution. At this setting, you can create 13.5x9 inch prints with no loss of picture quality.

How do Digital Cameras/Digitizers capture color?

Photosets are blind Photosets only keep track of the total intensity of light that strikes the surface To get full color of an image, most sensors use filtering to look at the light in its three primary colors All three colors get recorded and combined to create the full spectrum

 Beam splitter directs light to different sensors and each sensor only responds to one of the primary colors Rotate all three colors (red, green , blue) get rotated in front of a single sensor; 3 separate images get recorded Color filter array most economical and practical method used to permanently place a filter over each photosite. Sensor gets broken up into r,g, b pixels Bayer filter pattern Most common and alternates a row of red and green filters with a row of blue and green filters. [pixels are not evenly divided (as many green as there are blue and red combined)
Why?
Human eye is not a sensitive to all three colors Necessary to include all of green so as to create an image that the eye will perceive a true color

How do Digital Cameras/Digitizers capture color?

 types of scanners, like X-ray scanners, gamma ray scanner, RF scanners, biological scanners ,

5/17/2012

Prof.H.T.Patil, CCOEW,PUNE

50