<< Chapter < Page Chapter >> Page >

Image processing

Image Processing

Above is a picture documenting one of the best results. In most cases, processing managed to clear out debris, fill holes, and smooth without large errors. However, there were a few instances where debris was not cleared out properly or portions of the cell body were mistakenly deleted. Additionally, threshold detection could not always successfully separate out nuclei, especially in the cases of more granulated white blood cells such as eosinophils and basophils.

Thresholding failure

Cell Nucleus Comparison
Thresholding was unable to separate the cell and the nucleus in this basophil.

Cleaning failures

erode overlap
Parts of the cell were erroneously removed while clearing debris in the eosinophil on the left, whereas erosion could not separate the overlapping cells from the eosinophil on the right.

Get Jobilize Job Search Mobile App in your pocket Now!

Get it on Google Play Download on the App Store Now




Source:  OpenStax, Automatic white blood cell classification using svm and neural networks. OpenStax CNX. Dec 16, 2015 Download for free at http://legacy.cnx.org/content/col11924/1.5
Google Play and the Google Play logo are trademarks of Google Inc.

Notification Switch

Would you like to follow the 'Automatic white blood cell classification using svm and neural networks' conversation and receive update notifications?

Ask