Principal Component Analysis in Image Classification: A review

Principal component analysis (PCA) is considered as an important technique for dimension reduction of the data in various artificial intelligence/machine learning applications. One of the most important application is computer vision or image classification. Owing to the benefits and importance of PCA in image classification it is used not only for reducing dimensions, but also used to find important/dominant features hidden inside the data set having high dimensions. That makes PCA as one of the best techniques that helps in image classification yielding highly accurate results. This paper reviews some of the recent studies of application using PCA in image classification. The article covers different datasets having different properties and information of images. Moreover, the paper contributed in listing details of evaluation matrices, datasets, objectives, and possible improvements to increase the accuracy with reduced computational time of included articles.