Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/17726
Title: Towards an intelligent vision system for automatic cell microscopy
Authors: XIONG WEI
Keywords: Blood cells, area selection, object modeling, model-guided segmentation, infection detection/classification, local description
Issue Date: 6-Jan-2010
Source: XIONG WEI (2010-01-06). Towards an intelligent vision system for automatic cell microscopy. ScholarBank@NUS Repository.
Abstract: Cell enumeration and diagnosis using peripheral blood smears are routine tasks in many biological and pathological examinations using microscopy. To automate these tasks in the context of intelligent and high throughput screening, we firstly propose efficient algorithms and optimal features to quantify cell spatial distribution and clumping and select good working areas from whole slides. We then design an iterative optimization method to build unbiased probabilistic cell shape and appearance models. A learning method is also presented to model cell color distributions online. Both shape and color models are used to guide the segmentation and recognition of cell patterns from the selected areas. A new local descriptor and a new generative model using discrete circular samples are invented to represent regions and blob contexts and to detect, classify and retrieve pathological cell regions. Finally our methods have been applied in analyzing Giemsa-stained malaria-infected blood slides and achieved good performance in both speed and accuracy.
URI: http://scholarbank.nus.edu.sg/handle/10635/17726
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
01Chap.pdf489.62 kBAdobe PDF

OPEN

NoneView/Download
02Chap.pdf2 MBAdobe PDF

OPEN

NoneView/Download
03Chap.pdf674.11 kBAdobe PDF

OPEN

NoneView/Download
04Chap.pdf8.66 MBAdobe PDF

OPEN

NoneView/Download
05Chap.pdf4.18 MBAdobe PDF

OPEN

NoneView/Download
06Chap.pdf8.67 MBAdobe PDF

OPEN

NoneView/Download
07Chap.pdf425.28 kBAdobe PDF

OPEN

NoneView/Download

Page view(s)

358
checked on Dec 11, 2017

Download(s)

1,412
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.