Sriramemarose.blogspot.in
COUNTING NUMBER OF FRUITS USING WATERSHEDING
Problem statement:
 Fruits distributed closely will be considered as a single blob in normal thresholding,
therefore counting is impossible with thresholding
Sample image: Input image
Object boundaries and regional mamima superimposed on orginal image after watershed
Output image with counted fruits
Sriramemarose.blogspot.in
Steps used:
 Filter the image to eliminate noise
 Create an edge emphasizing filter kernel(say ‘a’) after converting the image to grayscale
 Create a transpose of the filter kernel(say ‘b’)
 Obtain two images with one filtered with a and other filtered with b
 Calculate the gradient magnitude of the two images
 Perform morphological operations and reconstruct the image on the original image
 Convert the resultant to binary image and estimate the distance transform
 Perform watershedding and segment the watershed boundary lines
 Obtain the regional minima of the gradient magnitude by morphological reconstruction of
the boundary lines and regional maxima of the original image
 Find the number of fruits from the boundaries of the new image
Other examples:
 Counting number of cells in medical imaging
 Connected objects segmentation
Sriramemarose.blogspot.in
LIQUID LEVEL IN BEVERAGE BOTTLES
Problem statement:
 Overfill and Underfill identification
 Quantity estimation
Sample image:
Processed image:
Steps involved:
 Perform color segmentation based on sample`s threshold
 Smoothen the segmented image with suitable filter
 Apply morphological operators to remove remaining components other than sample
 Calculate the pixels contributing to the sample
 Calibrate the pixels in terms quantity(volume)
 Label the calibrated quantity value to its corresponding sample
Applications:
 Pharmaceutical Industries
 Beverage Industries
 Batch processing
Sriramemarose.blogspot.in
Nuts and Bolts
Problem statement:
 Distinguish between nut and bolt
 Count number of nuts and bolts
Sample image Processed image
Steps involved:
 Adjust the contrast after converting to grayscale image
 Obtain the binary image with suitable threshold level
 Filter the noises with suitable filters
 Apply morphological operators to enhance the features
 Detect the nuts using hough circle transform with appropriate sensing radius and
sensitivity
 Subtract the detected nuts from the image, which leaves only with the bolts
 Detect the number of bolts using binary labeling
Applications:
 Automotive Industries
 Manufacturing Industries
 Industrial Automation
Sriramemarose.blogspot.in
PENCIL LENGTH IDENTIFICATION
Problem statement:
 To identify objects (pencil) length to ensure manufacturing defects
Sample image:
Test image Pencil length Pencil and lead length
Steps involved:
 Obtain a Boolean image with suitable threshold value
 Apply filters to remove noises
 Perform morphological operation to enhance the detection, without altering the object
dimension
 Segmented the object from background and label the object blob
 Find the region properties of the object blob
 Measure the pixels and calibrate in real world units
Applications:
 Manufacturing industries
 Factory Automation
 Quality control
Sriramemarose.blogspot.in
RICE GRAIN INSPECTION
Problem statement:
 To identify broken grains
 To segment good quality grains
Sample image:
Input image
Steps involved:
 Eliminate the uneven illumination using morphological tophat operation
 Adjust the image contrast
 Obtain the binary image with suitable threshold value
 Find the connected components in the image to locate each grain, use filter if needed
 Find the region properties of the grains
 Traverse through every connected component (pixel index list) and check its
corresponding properties
 If a grain does not satisfy the standard quality (based on its property value), subtract that
particular component(grain) from the pixel index list
Applications:
 Food processing Industries
 Quality control
Sriramemarose.blogspot.in
BLISTER INSPECTION
Problem statement: To identify the missing in the tablet strips( Blisters)
Sample images:
Good sample Processed image
Sample with defect Processed image
Steps involved:
 Convert to grayscale image and adjust the contrast
 Obtain the binary image with suitable threshold value
 Eliminate the noise with appropriate filters
 Perform morphological operations to segment tablet and tablet strip
 Apply hough transform to find the tablets
 Based on the detection, mark the blister as defected or good.
Applications:
 Pharmaceutical Industries
 Manufacturing industries
Sriramemarose.blogspot.in
NUTS SORTING
Problem statement:
 To measure the diameter of the nuts
 To sort them based on their size
Sample image:
Processed image:
Nut with minimum diameter Detected nuts
Steps involved:
 Convert to grayscale image and adjust the contrast
 Obtain the binary image with suitable threshold value
 Eliminate the noise with appropriate filters
 Perform morphological operations to enhance the features
 Use hough circle transform to detect the nuts since it has circular feature
 Detect the required nuts radius using mathematical operators
 Segment the detected nuts
Applications:
 Manufacturing Industries
 Industrial Automation
 Quality control
Sriramemarose.blogspot.in

Machine Vision applications development in MatLab

  • 1.
    Sriramemarose.blogspot.in COUNTING NUMBER OFFRUITS USING WATERSHEDING Problem statement:  Fruits distributed closely will be considered as a single blob in normal thresholding, therefore counting is impossible with thresholding Sample image: Input image Object boundaries and regional mamima superimposed on orginal image after watershed Output image with counted fruits
  • 2.
    Sriramemarose.blogspot.in Steps used:  Filterthe image to eliminate noise  Create an edge emphasizing filter kernel(say ‘a’) after converting the image to grayscale  Create a transpose of the filter kernel(say ‘b’)  Obtain two images with one filtered with a and other filtered with b  Calculate the gradient magnitude of the two images  Perform morphological operations and reconstruct the image on the original image  Convert the resultant to binary image and estimate the distance transform  Perform watershedding and segment the watershed boundary lines  Obtain the regional minima of the gradient magnitude by morphological reconstruction of the boundary lines and regional maxima of the original image  Find the number of fruits from the boundaries of the new image Other examples:  Counting number of cells in medical imaging  Connected objects segmentation
  • 3.
    Sriramemarose.blogspot.in LIQUID LEVEL INBEVERAGE BOTTLES Problem statement:  Overfill and Underfill identification  Quantity estimation Sample image: Processed image: Steps involved:  Perform color segmentation based on sample`s threshold  Smoothen the segmented image with suitable filter  Apply morphological operators to remove remaining components other than sample  Calculate the pixels contributing to the sample  Calibrate the pixels in terms quantity(volume)  Label the calibrated quantity value to its corresponding sample Applications:  Pharmaceutical Industries  Beverage Industries  Batch processing
  • 4.
    Sriramemarose.blogspot.in Nuts and Bolts Problemstatement:  Distinguish between nut and bolt  Count number of nuts and bolts Sample image Processed image Steps involved:  Adjust the contrast after converting to grayscale image  Obtain the binary image with suitable threshold level  Filter the noises with suitable filters  Apply morphological operators to enhance the features  Detect the nuts using hough circle transform with appropriate sensing radius and sensitivity  Subtract the detected nuts from the image, which leaves only with the bolts  Detect the number of bolts using binary labeling Applications:  Automotive Industries  Manufacturing Industries  Industrial Automation
  • 5.
    Sriramemarose.blogspot.in PENCIL LENGTH IDENTIFICATION Problemstatement:  To identify objects (pencil) length to ensure manufacturing defects Sample image: Test image Pencil length Pencil and lead length Steps involved:  Obtain a Boolean image with suitable threshold value  Apply filters to remove noises  Perform morphological operation to enhance the detection, without altering the object dimension  Segmented the object from background and label the object blob  Find the region properties of the object blob  Measure the pixels and calibrate in real world units Applications:  Manufacturing industries  Factory Automation  Quality control
  • 6.
    Sriramemarose.blogspot.in RICE GRAIN INSPECTION Problemstatement:  To identify broken grains  To segment good quality grains Sample image: Input image Steps involved:  Eliminate the uneven illumination using morphological tophat operation  Adjust the image contrast  Obtain the binary image with suitable threshold value  Find the connected components in the image to locate each grain, use filter if needed  Find the region properties of the grains  Traverse through every connected component (pixel index list) and check its corresponding properties  If a grain does not satisfy the standard quality (based on its property value), subtract that particular component(grain) from the pixel index list Applications:  Food processing Industries  Quality control
  • 7.
    Sriramemarose.blogspot.in BLISTER INSPECTION Problem statement:To identify the missing in the tablet strips( Blisters) Sample images: Good sample Processed image Sample with defect Processed image Steps involved:  Convert to grayscale image and adjust the contrast  Obtain the binary image with suitable threshold value  Eliminate the noise with appropriate filters  Perform morphological operations to segment tablet and tablet strip  Apply hough transform to find the tablets  Based on the detection, mark the blister as defected or good. Applications:  Pharmaceutical Industries  Manufacturing industries
  • 8.
    Sriramemarose.blogspot.in NUTS SORTING Problem statement: To measure the diameter of the nuts  To sort them based on their size Sample image: Processed image: Nut with minimum diameter Detected nuts Steps involved:  Convert to grayscale image and adjust the contrast  Obtain the binary image with suitable threshold value  Eliminate the noise with appropriate filters  Perform morphological operations to enhance the features  Use hough circle transform to detect the nuts since it has circular feature  Detect the required nuts radius using mathematical operators  Segment the detected nuts Applications:  Manufacturing Industries  Industrial Automation  Quality control
  • 9.