23-03-2011, 09:45 AM
[attachment=10787]
Fundamental Steps in Computer Vision
Today:
Pre-processing
• Segmentation
• Point Processing
What is point processing?
• Grey level mapping
• Histograms
• Segmentation using thresholding
• ImageJ
• SW to do Image Processing and Analysis
• Free: http://rsb.info.nih.gov/ij/
• Stabile (Java)
• Extremely easy to learn and use
• Comes with a C-like programming language, but we’ll only use the menus
• Show…
What is point processing?
• Only one pixel in the input has an effect on the output
• For example:
– Changing the brightness, thresholding, histogram stretching
Point processing
• Grey level enhancement
– Process one pixel at a time independent of all other pixels
– For example used to correct Brightness and Contrast (remote control)
Brightness
• The brightness is the intensity
• Change brightness:
– To each pixel is added the value b
– f(x,y) is the input image
– g(x,y) is the (enhanced) output image
• If b>0 => brighter image
• If b<0 => less bright image
Contrast
• The contrast describes the level of details we can see
• Change contrast:
• Each pixel is multiplied by a
– f(x,y) is the input image
– g(x,y) is the (enhanced) output image
• If a>1 => more contrast
• If a<1 => less contrast
Combining brightness and contrast
• Both:
• A straight line
• Greylevel mapping
• X-Axis: Input Value
• Y-Axis: Output Value
• This plot: Identity
– Output equals Input: a=1 and b=0
• Apply to each pixel!
• To save time the greylevel
mapping can be written as a
Lookup-Table:
Histogram
• How to set the greylevel mapping
Histogram Types
Histogram processing
Improving contrast
• Humans cannot tell the difference between greylevel values too close to each other
• So: spread out the greylevel values
• This is called histogram stretching
Histogram stretching
• Something really different…
Segmentation
• Until now: Image processing (manipulation)
• Image analysis: segmentation
• The task:
– Information versus noise
– Foreground (object) versus background
Segmentation
• Use greylevel mapping and the histogram
• When two peaks (modes) of a histogram correspond to object and noise (Show: AuPbSn40, bridge)
• Find a THRESHOLD value, T, that separates the two peaks. This process is called THRESHOLDING
• Algorithm:
– If f(x,y) > T then g(x,y) = 1, else g(x,y) = 0
– ( or reverse )
• Result: a binary image where
object pixels = 1 and noise = 0
• (Show: AuPbSn40, bridge, 2Dgel, blobs)
Segmentation
• Often, obtaining a bi-modal histogram is the ”sole” purpose of the image acquisition:
– Lighting
– Setup
– Camera
– Lens
Segmentation
• How to define the Theshold?
– If we have a good setup => the Threshold is static!
– Find it during training
• But the histogram is NEVER static!!
What to remember
• Point processing
– Pixel-wise operations
– Greylevel mapping
• Setting brightness and contrast
– Histogram processing
– Segmentation: Thresholding. Bimodal histogram
Fundamental Steps in Computer Vision
Today:
Pre-processing
• Segmentation
• Point Processing
What is point processing?
• Grey level mapping
• Histograms
• Segmentation using thresholding
• ImageJ
• SW to do Image Processing and Analysis
• Free: http://rsb.info.nih.gov/ij/
• Stabile (Java)
• Extremely easy to learn and use
• Comes with a C-like programming language, but we’ll only use the menus
• Show…
What is point processing?
• Only one pixel in the input has an effect on the output
• For example:
– Changing the brightness, thresholding, histogram stretching
Point processing
• Grey level enhancement
– Process one pixel at a time independent of all other pixels
– For example used to correct Brightness and Contrast (remote control)
Brightness
• The brightness is the intensity
• Change brightness:
– To each pixel is added the value b
– f(x,y) is the input image
– g(x,y) is the (enhanced) output image
• If b>0 => brighter image
• If b<0 => less bright image
Contrast
• The contrast describes the level of details we can see
• Change contrast:
• Each pixel is multiplied by a
– f(x,y) is the input image
– g(x,y) is the (enhanced) output image
• If a>1 => more contrast
• If a<1 => less contrast
Combining brightness and contrast
• Both:
• A straight line
• Greylevel mapping
• X-Axis: Input Value
• Y-Axis: Output Value
• This plot: Identity
– Output equals Input: a=1 and b=0
• Apply to each pixel!
• To save time the greylevel
mapping can be written as a
Lookup-Table:
Histogram
• How to set the greylevel mapping
Histogram Types
Histogram processing
Improving contrast
• Humans cannot tell the difference between greylevel values too close to each other
• So: spread out the greylevel values
• This is called histogram stretching
Histogram stretching
• Something really different…
Segmentation
• Until now: Image processing (manipulation)
• Image analysis: segmentation
• The task:
– Information versus noise
– Foreground (object) versus background
Segmentation
• Use greylevel mapping and the histogram
• When two peaks (modes) of a histogram correspond to object and noise (Show: AuPbSn40, bridge)
• Find a THRESHOLD value, T, that separates the two peaks. This process is called THRESHOLDING
• Algorithm:
– If f(x,y) > T then g(x,y) = 1, else g(x,y) = 0
– ( or reverse )
• Result: a binary image where
object pixels = 1 and noise = 0
• (Show: AuPbSn40, bridge, 2Dgel, blobs)
Segmentation
• Often, obtaining a bi-modal histogram is the ”sole” purpose of the image acquisition:
– Lighting
– Setup
– Camera
– Lens
Segmentation
• How to define the Theshold?
– If we have a good setup => the Threshold is static!
– Find it during training
• But the histogram is NEVER static!!
What to remember
• Point processing
– Pixel-wise operations
– Greylevel mapping
• Setting brightness and contrast
– Histogram processing
– Segmentation: Thresholding. Bimodal histogram