Classification of normal and abnormal sperm from suspension of sprague dawley rat sperm
Loading...
Date
2009
Authors
Alias, Mohd Fauzi
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
As of now, the analysis of sperm such as counting and detection processes are
still operated manually. Even though the results obtained are of high quality, errors
still emerge. False detection in sperm analysis must be minimized as possible.
Therefore, the current study focuses on developing a Sprague Dawley rat sperm
classification system to assist the detection process by pathologist. The system has
the ability to classify the Sprague Dawley rat sperm into three classes namely
normal, hookless abnormal and banana shape abnormal based on the morphological
characteristics of the sperm’s head. The proposed system employs digital image
processing technique to classify sperm into normal and abnormal classes as well as
neural network to further classify sperm into normal, hookless abnormal and banana
shape abnormal. Several digital image processing techniques have been integrated
such as segmentation, hole filling and template matching. In segmentation process,
this research proposes two new segmentation algorithms called as Threshold
Doubled Value (TDV) and Modified Moving K-Mean (MMKM). These algorithms
have been proven to give better segmentation results as compared to the conventional
algorithms. This research also proposes a new implementation process for chain code
method to fill holes and noises which occur in segmented sperm’s head image. In the
sperm classification, template matching technique using cross correlation algorithm
successfully produces 99.79% of accuracy. However, the sperm classification using
the Hybrid Multilayered Perceptron (HMLP) network trained with Modified
Recursive Prediction Error (MRPE) algorithm achieved a higher accuracy by 100%.
The HMLP network further classifies the rat sperm into three classes with high
accuracy at 94.62%. This research also proposes three significant features of sperm
image to be used as input data to the HMLP network namely matching percentage,
opened degree and width of the bend.
Description
Master
Keywords
Biological Science , Normal sperm , Abnormal sperm , Rat sperm