Computer Vision for Green Plant Segmentation and Leaf Count

Abstract

Image-based plant phenotyping plays an important role in productive and sustainable agriculture. It is used to record the plant traits such as chlorophyll fluorescence, plant growth, yield, leaf area, width and height of plants frequently and accurately. Among these plant traits, plant growth is an important trait to be analyzed that directly depends on leaf area and leaf count. Taking benign conditions of quick advancement in computer vision and image processing algorithms, many methods have been developed in recent days to find the leaf area and leaf count accurately. In this chapter, the recent techniques in image-based plant phenotyping and their limitations are discussed. Also, this chapter discusses a new plant segmentation method based on wavelet and leaf count methods based on Circular Hough Transform and deep learning model, which overcomes the drawbacks of recent methods. These methods are experimented with Computer Vision Problems in Plant Phenotyping (CVPPP) benchmark datasets.