CELL COUNTING - PowerPoint PPT Presentation

About This Presentation
Title:

CELL COUNTING

Description:

CELL COUNTING USING IMAGE PROCESSING B. HEMAKUMAR Dept. of Electronics and Instrumentation SHANMUGA ARTS SCIENCE TECHNOLOGY AND RESEARCH ACADEMY (SASTRA) Deemed ... – PowerPoint PPT presentation

Number of Views:134
Avg rating:3.0/5.0
Slides: 22
Provided by: Balacha
Learn more at: https://www.oocities.org
Category:

less

Transcript and Presenter's Notes

Title: CELL COUNTING


1
BLOOD
CELL COUNTING USING IMAGE
PROCESSING
2
B. HEMAKUMAR Dept. of Electronics and
Instrumentation SHANMUGA ARTS SCIENCE TECHNOLOGY
AND RESEARCH ACADEMY (SASTRA) Deemed
University TANJORE, SOUTH INDIA
3
INTRODUCTION
  • NEED FOR BLOOD CELL COUNTING
  • CONVENTIONAL METHODS AND THEIR DEMERITS
  • METHOD PROPOSED
  • MERITS OF USING IMAGE PROCESSING

4
SAMPLE
BLOOD
STEP 1
VIDEO M COMP. INT
STEP 2
RGB TO GRAY SCALE
STEP 3
EDGE DETECTION
STEP 4
STEP 5
CELL COUNT
5
SYSTEM SETUP
6
STEP
  • BLOOD SAMPLE COLLECTION
  • CHEMICAL MIXING
  • GIVEN TO MICROSCOPE

7
STEP
  • CAPTURING THE IMAGE
  • CAMERA CONTROL UNIT
  • CCD TYPE VIDEO CAMERA
  • COMPACT, LIGHT WEIGHT, BETTER SENSITIVITY,
    HIGHER RESOLUTION

8
  • CCD TYPE HEAT NOISE SUPPRESSED BY
    INTEGRATED COOLING SYSTEMS
  • SCSI INTERFACE A/D
  • PARALLEL INTERFACE STANDARD
    (PC/MAC/UNIX)
  • IMAGE GRIPPER CARD
  • PC - MATLAB V6.5

9
STEP
RGB TO GRAY
Y gives the grayscale image Y 0.299R
0.587G 0.114B
10
STEP
EDGE DETECTION EDGE ABRUPT GRAY LEVEL
CHANGE METHODS 1. GRADIENT OPERATOR PAIR OF
MASKS MEASURES GRADIENT ALONG TWO ORTHOGONAL
DIRECTIONS. MAGNITUDE PHASE OF GRADIENTS
11
MAGNITUDE gt THRESHOLD EDGE PHASE EDGE
DIRECTION TWO THRESHOLDS - STRONG AND WEAK
EDGES SOBEL, PREWITT, ROBERT CANNY
12
2. LAPLACIAN WIDE GRAY LEVEL CHANGE MORE
SENSITIVE TO NOISE ZERO CROSSING
PROPERTY POPULAR LAPLACIAN GUASSIAN
OPERATOR h(m,n)c1-(m2m2)/s2 exp
(-((m2n2)/2s2))) OUTPUT OF EDGE DETECTION
BINARY IMAGE

13
STEP
  • CELL COUNT
  • Linear flow of reading from starting of
    ROW/COLUMN and increment
  • If p(x-1, y-1), p(x-1, y), p(x, y-1) and
    p(x1, y- 1) are ZERO, then increment COUNT

14
RESULTS...
15
(No Transcript)
16
FRONT END TOOL USING GUIDE
17
Edge Detection Method No. of Cells
Counted Sobel 288 Prewitt 286
Canny 689 Roberts 229 Laplacian
471
300
MANUAL COUNT
18
CONCLUSION
Sobel and Prewitt
matches with min. error
with manual counting
19
REFERENCES
  •  
  • 1. C. Harris and M. Stephens, A combined
    corner and edge detector, Proc.4th Alvey
    Vision Conference, pp. 189-192,1988
  • X. Xie, R. Sudhakar and H. Zhuang, Corner
    detection by a cost minimization approach,
    Pattern Recognition, Vol. 26, No. 8, pp.
    1235- 1243, 1993
  • 3. Gernot Hoffmann Tutorial on Luminance
    Models for the Grayscale conversion

20
REFERENCES contd..
4. R.Gonzalez and R. Woods, Digital Image
Processing, 1st edition, Addison-Wesley,1992. 5.
W. Pratt, Digital Image Processing, John
Wiley Sons, 1978.
21
Thank you for your attention...
Write a Comment
User Comments (0)
About PowerShow.com