| Resumen |
In the biological area, the short reproductive cycle in rodents is useful because it allows analyzing electrophysiological properties, behaviors, or drugs effects, through the changes observed during this period. This cycle is composed of 4 stages, in which the classification is determined by vaginal cytology. Although automatic approaches have been used for the recognition of these stages, they are computationally expensive and require a great number of images for adequate performance. In this work, we study the effect of contrast enhancement on the images classification of the reproductive cycle named estrous cycle. We use a dataset of 344 images and four classical contrast enhancement methods. We extract texture features and use four classifiers to evaluate the impact of the contrast enhancement methods. From the results, we find that the contrast enhancement methods that do not emphasize strongly some regions in the images show higher classification results than those yes do it. Furthermore, features extracted manually overcome the classification rate concerning the features extracted automatically with a standard convolutional neural network. |
