Historically, practitioners relied on an engineered feature extraction pipeline, usually containing multiple stages of processing combined with simple machine learning techniques. (nextcanada.com)
The goal of this activity is to illustrate the key AI concept of feature extraction — conversion of data in the original format (for example, an image) into a series of quantitative or qualitative features that can be used to distinguish different objects in the original data. (teachermagazine.com.au)
«Using automated feature extraction is standard for face recognition and emotion recognition,» says Raia Hadsell, a machine vision engineer at Google DeepMind. (newscientist.com)