期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2015
卷号：6
期号：3
页码：3014-3016
出版社：TechScience Publications
摘要：Extraction of features can be viewed as a preprocessing step which eliminates distracting inconsistency from a dataset, so that downstream classifiers or regression estimators perform better and hence various applications can be implemented from it. The area where feature extraction ends and classification, or regression, begins is necessarily gloomy: an ultimate feature extractor would simply map the data to its class labels, for the categorization task. These features can be used for image matching or recognition techniques or learning in supervised algorithms. Here in this paper all methods that are implemented for the extraction of features is converse about and a relative investigation is exposed in the paper so that by analyzing the various limitations of the algorithms in the future a more modified and effective feature extraction based technique is implemented.
