1 / 21

CELL COUNTING USING IMAGE PROCESSING

BLOOD. CELL COUNTING USING IMAGE PROCESSING. B. HEMAKUMAR Dept. of Electronics and Instrumentation SHANMUGA ARTS SCIENCE TECHNOLOGY AND RESEARCH ACADEMY (SASTRA) Deemed University TANJORE, SOUTH INDIA. INTRODUCTION. NEED FOR BLOOD CELL COUNTING

badu
Download Presentation

CELL COUNTING USING IMAGE PROCESSING

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  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 STEP 1 BLOOD STEP 2 VIDEO M + COMP. INT STEP 3 RGB TO GRAY SCALE STEP 4 EDGE DETECTION 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’ = 0.299*R + 0.587*G + 0.114*B

  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 > 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)=c[1-(m2+m2)/σ2] exp (-((m2+n2)/2σ2))) 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(x+1, y- 1) are ZERO, then increment COUNT

  14. RESULTS...

  15. FRONT END TOOL USING GUIDE

  16. Edge Detection Method No. of Cells Counted Sobel 288 Prewitt 286 Canny 689 Roberts 229 Laplacian 471 300 MANUAL COUNT :

  17. CONCLUSION Sobel and Prewitt matches with min. error with manual counting

  18. 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”

  19. 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.

  20. Thank you for your attention...

More Related