1 / 16

A Simple Method for Detecting Protein Spots in 2D-GE Images Using Image Contrast

A Simple Method for Detecting Protein Spots in 2D-GE Images Using Image Contrast. Authors: Meng-Hsiun Tsai Shu-Fen Chiou Min-Shiang Hwang Speaker: Shu-Fen Chiou. Outline. Introduction Related Work Our Proposed Method Experimental Results Conclusions.

gibson
Download Presentation

A Simple Method for Detecting Protein Spots in 2D-GE Images Using Image Contrast

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. A Simple Method for Detecting Protein Spots in 2D-GEImages Using Image Contrast Authors: Meng-Hsiun Tsai Shu-Fen Chiou Min-Shiang Hwang Speaker: Shu-Fen Chiou

  2. Outline • Introduction • Related Work • Our Proposed Method • Experimental Results • Conclusions

  3. Introduction(1/2) Two-dimensional gel electrophoresis image

  4. Introduction(2/2) Pixel value y x

  5. Related Work (1/2) • Image features of images • Tamura et al. proposed six features of texture images: • Coarseness • Contrast • Directionality • Linelikeness • Regularity • Roughness

  6. Related Work (2/2) • Image contrast • Every pixel in the image has its own contrast, and we can determine this by comparing them with the neighboring pixels. The contrast is defined as • σis the pixel values' standard error, and u4 is fourth moment of the image.

  7. Our Proposed Method • Our method uses the following steps: • 1. Computing the contrast. • 2. Detection.

  8. Our Proposed Method • Step 1. Computing the contrast Step 1: Compute average: Step 2: Compute standard error σ: Step 3: Compute fourth moment u4: Step 4: Compute Fcon: 2D-GEl image

  9. Our Proposed Method • Step 1. Computing the contrast Step 5: Determine the maximum and minimum contrasts ith row and jth column Step 6: Normalization Step 7: Define the threshold t

  10. 567 • 4 0 • 321 A Our Proposed Method • Step 2. Detect the protein spot • If • 0 • 7 1 • 2 • 5 3 • 4 Chain code direction is clockwise from 0, 1, … to 7

  11. Our Proposed Method • Detecting protein spots

  12. Experimental Results • Original images g3 g1 g2

  13. g3 g2 g1 Experimental Results • Contrast images

  14. Experimental Results • Cytoplasmic protein extracting from corynebacterium glutamicum. 1606 2008

  15. Conclusions • We propose a simple method to detect protein spots in 2D-GE images based on the image's chromatic features. We use contrast to separate the protein spots and background. • We compare contrast among pixels with a threshold. If their contrast is greater than threshold, they are candidate pixels. • Finally we locate every candidate pixel among its eight neighbors and use these groupings of pixels to locate protein spots.

  16. Thank You

More Related