Numerous classification mechanisms anticipate the class's instances to be carried out as the features' vectors, namely the points in a feature's space. It is oftentimes a chance to make an informative exemplification of an image's feature vector for classification problems in computer vision like utilizing global descriptors for the texture description or shape description. The proposed methodology is to classify the sperm image in mice that has been affected through plasma and this methodology consists of three stages. The points of interest could be elicited from sperm plasma images in the first stage by utilizing Adaptive and Generic Corner detector that depended on AGAST (Accelerated Segment Test). FREAK (descriptor of Fast Retina Key-points) was employed in the second stage for describing those points of interest and then computing the standard deviation for those points. KNN (K-Nearest Neighbors) was calculated in the third stage for plasma images classification depending on the STD (standard deviation) amount. The outcomes of the experimental work illustrated that; plasma produced by microwave holds minimum amount of STD than Plasma with high temperature.
Falih, Ekhlas and Mazhar, Alaa Noori
"Using FREAK descriptor to classify plasma influence in Mice sperm,"
Karbala International Journal of Modern Science: Vol. 6
, Article 6.
Available at: https://doi.org/10.33640/2405-609X.1352
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.