Plants exert a vital influence on the survival of life on Earth by producing oxygen and supplying the necessities for food, medicine, and a variety of industrial applications. Given an enormous array of different plant species, each with its own unique features such as form and texture, manually identifying them for diverse applications becomes challenging. Consequently, the use of artificial intelligence-driven feature extraction techniques becomes critical in order to speed the process. Feature extraction involves identifying and capturing specific characteristics from leaf images. This paper aims to offer a comprehensive overview of the related work done by the researchers in the previous years. For feature extraction, Histogram of Oriented Gradients (HOG), Local Binary Pattern (LBP), and Grey Level Co-Occurrence Matrix (GLCM) are preferably employed, followed by classification using neural networks, and so on. HOG excels at extracting details concerning the distribution of edge directions or intensity gradients within an image. LBP performs well in describing local patterns of pixel intensities, making it useful for work involving texture. Different techniques are used depending on the specifications. The foremost objective of our work is on investigation on various feature extraction techniques that can be utilized.