Plant stress phenotyping is a useful tool to facilitate targeted interventions and optimize management practices of plants growing in stressful conditions. However, various technical challenges still need to be overcome, though, and there is a clear need for investigating functional traits that can be used as a proxy for stress prediction, especially for abiotic stresses. This experimental work leveraged machine learning classification models to detect salt stress in two populations of a non-model species, combining image-based approaches (i.e. both manual and automated) and minimal morpho-physiological/biochemical analyses. A small set of specific features, combining malondialdehyde content with other non-destructive image-derived traits, such as Chroma Difference and Chroma Ratio indices, was able to distinguish non-stressed from stressed plants (2-class model; precision: 0.91) as well as stress intensity (3-class model; precision: 0.84). This flexible approach can be adapted to different plant developmental stages and leaf shape/morphology. In the future, the robustness and reliability of the models should be tested in other species and other abiotic stresses, such as drought.