Department of Electrical, Systems and Automatic Engineerings, University of León, 24071 León, Spain.
Comput Methods Programs Biomed. 2012 Nov;108(2):873-81. doi: 10.1016/j.cmpb.2012.01.004. Epub 2012 Feb 29.
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.
猪精子顶体的自动评估是兽医领域的一个重要挑战。在本文中，我们探讨了如何使用图像分析来描述猪精子的顶体，以便可以将其自动分类为完整或受损。我们的建议旨在通过纹理特征来描述顶体。纹理使用一阶统计和从图像的共生矩阵导出的特征来描述，这些特征都是从原始图像和离散小波变换的系数中计算得出的。我们评估了纹理描述符，并将其与基于矩的描述符进行了比较，以比较它们提供的分类准确性。使用多层感知器和 k-最近邻分类器的实验结果表明，纹理描述符优于基于矩的描述符，准确率达到 94.93%，这使得这种方法对兽医界非常有吸引力。
