Paper Info
Title
Texture and moments-based classification of the acrosome integrity of boar spermatozoa images.
Abstract
The automated assessment of the sperm quality is an important challenge in the veterinary field. In this paper, we explore how to describe the acrosomes of boar spermatozoa using image analysis so that they can be automatically categorized as intact or damaged. Our proposal aims at characterizing the acrosomes by means of texture features. The texture is described using first order statistics and features derived from the co-occurrence matrix of the image, both computed from the original image and from the coefficients yielded by the Discrete Wavelet Transform. Texture descriptors are evaluated and compared with moments-based descriptors in terms of the classification accuracy they provide. Experimental results with a Multilayer Perceptron and the k-Nearest Neighbours classifiers show that texture descriptors outperform moment-based descriptors, reaching an accuracy of 94.93%, which makes this approach very attractive for the veterinarian community.
Year
DOI
Venue
2012
10.1016/j.cmpb.2012.01.004
Computer Methods and Programs in Biomedicine
Keywords
Field
DocType
texture descriptors,acrosome integrity,automated assessment,multilayer perceptron,boar spermatozoa image,discrete wavelet transform,moments-based classification,original image,image analysis,texture feature,moments-based descriptors,moment-based descriptors,classification accuracy,neural networks
Computer vision,Acrosome,Matrix (mathematics),First order,Computer science,Multilayer perceptron,Artificial intelligence,Discrete wavelet transform,Artificial neural network
Journal
Volume
Issue
ISSN
108
2
1872-7565
Citations 
PageRank 
References 
13
0.78
24
Authors
4
Name
Order
Citations
PageRank
Enrique Alegre113921.84
Víctor González-Castro29010.70
Rocío Alaiz-Rodríguez323613.16
María Teresa García-Ordás4374.45