Difference between revisions of "Team:Cambridge-JIC/MicroMaps"
KaterinaMN (Talk | contribs) |
KaterinaMN (Talk | contribs) |
||
Line 95: | Line 95: | ||
<div style="width: 100%; padding:0% 10%; margin: 30px 0px;color:#fff"> | <div style="width: 100%; padding:0% 10%; margin: 30px 0px;color:#fff"> | ||
<h3>Image Processing</h3> | <h3>Image Processing</h3> | ||
− | <!-- | + | <!-- |
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
− | + | ||
*** ask souradip!!! *** | *** ask souradip!!! *** | ||
blockly visual programming to assemble simple annotators and microscope commands into complex workflows to automate experiments | blockly visual programming to assemble simple annotators and microscope commands into complex workflows to automate experiments | ||
Line 108: | Line 101: | ||
<p>The purpose of microscopy is to extract some useful information about the specimen: screen for a particular phenotype, examine fluorescence, measure sizes, count cells, recognize distinctive features, eg. nuclei. Focusing on a specimen is just a small part of the art of microscopy. The actual scientific challenge is to interpret the image. Imagine a program that does this for you. This is what we had in mind when creating MicroMaps. To achieve this, we had to implement different types of image processing algorithms. Image recognition is still work in progress, but we believe that we have laid out the framework for a new, smarter, approach to digital microscopy.</p> | <p>The purpose of microscopy is to extract some useful information about the specimen: screen for a particular phenotype, examine fluorescence, measure sizes, count cells, recognize distinctive features, eg. nuclei. Focusing on a specimen is just a small part of the art of microscopy. The actual scientific challenge is to interpret the image. Imagine a program that does this for you. This is what we had in mind when creating MicroMaps. To achieve this, we had to implement different types of image processing algorithms. Image recognition is still work in progress, but we believe that we have laid out the framework for a new, smarter, approach to digital microscopy.</p> | ||
− | <p><b>The Method:</b> We tested our image processing software on some images of <i>Marchantia</i> gemma on a Petri dish with agar, This was intended to be a step towards our <a href="https://2015.igem.org/Team:Cambridge-JIC/Stretch_Goals" class="blue">Stretch Goal</a> - an automated screening desktop system. Two types of image processing algorithms were implemented:</p> | + | <p><b>The Method:</b> We tested our image processing software on some images of <i>Marchantia</i> gemma on a Petri dish with agar, This was intended to be a step towards our <a href="https://2015.igem.org/Team:Cambridge-JIC/Stretch_Goals" class="blue">Stretch Goal</a> - an automated screening desktop system. To write the software, the <a href="http://opencv.org/" class="blue">OpenCV</a> library was used. Two types of image processing algorithms were implemented:</p> |
<ul> | <ul> | ||
<li><p><b>Standard thresholding</b><br>This makes an image grey-scale and searches for the dark areas. We started off with a basic contrast increase to isolate the darker areas of the image, which we assume would correspond to samples. Rajiv then followed the steps in a paper by ……… which was supposed to yield much better sample isolation for samples which look faint, and are hard to distinguish from their background. This ended up detecting dents in the agar gel along with the samples. To resolve this issue we came up with the next idea...</p></li> | <li><p><b>Standard thresholding</b><br>This makes an image grey-scale and searches for the dark areas. We started off with a basic contrast increase to isolate the darker areas of the image, which we assume would correspond to samples. Rajiv then followed the steps in a paper by ……… which was supposed to yield much better sample isolation for samples which look faint, and are hard to distinguish from their background. This ended up detecting dents in the agar gel along with the samples. To resolve this issue we came up with the next idea...</p></li> |
Revision as of 14:57, 18 September 2015