SlideShare a Scribd company logo
1 of 9
HW01 Eye Detection
Abhishek Bhandwaldar
Algorithm
• Step 1 : skin Detection
• Step 2: Eye Localization
• Step 3: Removing Low intensity regions
• Step 4: Eye detection
Skin Detection
• Used YCbCr color space
for skin detection.
• Condition to be
satisfied for Skin
detection:
• Cb>=77 & Cb<=127 &
Cr>=133 & Cr<=173
Eye Localization
• Assumptions:
• Image has only 1 face
and that it covers more
than 60% of image.
• Crop 60% from top and
then 40% from bottom.
Removing Low intensity regions.
• Take sum along column.
• Take threshold as
percentage of
maximum intensity of
all columns
(max(sum(img)))
• Set all pixel less than
threshold to value 255.
Low intensity
column
High intensity
column
Result
Eye detection
• Invert the image and
calculate intensity
graph.
• Calculate intensity
graph along Column
and Row.
• Points of maximum
intensity are eyes.
Column intensity
Row intensity
Failure
• The algorithm will fail if
skin detection
algorithm will fail.
• The intensity graph
generated will give us
not so clear and
separate maximum
values.
• Hence our algorithm
will fail. Failed Intensity graph
Thank you

More Related Content

Similar to Extracred

Gesture Recognition?
Gesture Recognition?Gesture Recognition?
Gesture Recognition?
Dayo Choul
 
30thSep2014
30thSep201430thSep2014
30thSep2014
Mia liu
 
Exploring Methods to Improve Edge Detection with Canny Algorithm
Exploring Methods to Improve Edge Detection with Canny AlgorithmExploring Methods to Improve Edge Detection with Canny Algorithm
Exploring Methods to Improve Edge Detection with Canny Algorithm
Prasad Thakur
 

Similar to Extracred (20)

face detection
face detectionface detection
face detection
 
Friday seminar presentation
Friday seminar presentationFriday seminar presentation
Friday seminar presentation
 
Computer Graphics: Visible surface detection methods
Computer Graphics: Visible surface detection methodsComputer Graphics: Visible surface detection methods
Computer Graphics: Visible surface detection methods
 
Gesture Recognition?
Gesture Recognition?Gesture Recognition?
Gesture Recognition?
 
PPT s06-machine vision-s2
PPT s06-machine vision-s2PPT s06-machine vision-s2
PPT s06-machine vision-s2
 
30thSep2014
30thSep201430thSep2014
30thSep2014
 
Spatial filtering
Spatial filteringSpatial filtering
Spatial filtering
 
OpenCV presentation series- part 4
OpenCV presentation series- part 4OpenCV presentation series- part 4
OpenCV presentation series- part 4
 
Handwritten mathematical symbol recognition
Handwritten mathematical symbol recognitionHandwritten mathematical symbol recognition
Handwritten mathematical symbol recognition
 
Mvs adas
Mvs adasMvs adas
Mvs adas
 
Final_Facial_Emotion_Detection_ppt.pdf
Final_Facial_Emotion_Detection_ppt.pdfFinal_Facial_Emotion_Detection_ppt.pdf
Final_Facial_Emotion_Detection_ppt.pdf
 
05 contours seg_matching
05 contours seg_matching05 contours seg_matching
05 contours seg_matching
 
Parking space detect
Parking space detectParking space detect
Parking space detect
 
Edge Drawing - An Heuristic Approach to Robust Real-Time Edge Detection
Edge Drawing - An Heuristic Approach to Robust Real-Time Edge DetectionEdge Drawing - An Heuristic Approach to Robust Real-Time Edge Detection
Edge Drawing - An Heuristic Approach to Robust Real-Time Edge Detection
 
Face detection system design seminar
Face detection system design seminarFace detection system design seminar
Face detection system design seminar
 
Clipping
ClippingClipping
Clipping
 
Image processing
Image processingImage processing
Image processing
 
IMAGE PROCESSING
IMAGE PROCESSINGIMAGE PROCESSING
IMAGE PROCESSING
 
Exploring Methods to Improve Edge Detection with Canny Algorithm
Exploring Methods to Improve Edge Detection with Canny AlgorithmExploring Methods to Improve Edge Detection with Canny Algorithm
Exploring Methods to Improve Edge Detection with Canny Algorithm
 
09 cie552 image_featuresi
09 cie552 image_featuresi09 cie552 image_featuresi
09 cie552 image_featuresi
 

Extracred

  • 2. Algorithm • Step 1 : skin Detection • Step 2: Eye Localization • Step 3: Removing Low intensity regions • Step 4: Eye detection
  • 3. Skin Detection • Used YCbCr color space for skin detection. • Condition to be satisfied for Skin detection: • Cb>=77 & Cb<=127 & Cr>=133 & Cr<=173
  • 4. Eye Localization • Assumptions: • Image has only 1 face and that it covers more than 60% of image. • Crop 60% from top and then 40% from bottom.
  • 5. Removing Low intensity regions. • Take sum along column. • Take threshold as percentage of maximum intensity of all columns (max(sum(img))) • Set all pixel less than threshold to value 255. Low intensity column High intensity column
  • 7. Eye detection • Invert the image and calculate intensity graph. • Calculate intensity graph along Column and Row. • Points of maximum intensity are eyes. Column intensity Row intensity
  • 8. Failure • The algorithm will fail if skin detection algorithm will fail. • The intensity graph generated will give us not so clear and separate maximum values. • Hence our algorithm will fail. Failed Intensity graph