Xylem vessels play a pivotal role in plant adaptation to drought stress. In this paper, we propose a novel framework that associates automatic segmentation of xylem vessels with its morphological features as a quantitative proxy to predict drought stress response (DSR). We develop an image processing pipeline that comprises of low level processing which enables high-throughput detection of xylem vessels. With no prior information about its size and location, the proposed detection methodology gives an accuracy of 98%. The labelled data for DSR are either not available or are subjectively developed, which is a low-throughput and error prone task. We resolve this problem by employing simplex volume maximization (SiVM) algorithm. The convex representations obtained from SiVM for each xylem in microscopic images based on its shape factors are aggregated to get an automated scoring of the whole plant. Bhattacharya distance is then employed to obtain the divergence of these responses w.r.t. the control group. The proposed framework successfully captures the phenotypic difference between MTU-1010 (drought susceptible rice cultivar) and Sahbhagi Dhan (drought tolerant rice cultivar). © 2017 MVA Organization All Rights Reserved.