Plantago lanceolate is important for animal feed as it improves the nutritional value of forages. Aucubin, acteosids and catalpol are important compunds present in this plant but their determination is time consuming, costly and needs chemicals. In the present study we develop a method based on FT-NIR spectroscopy to determine aucubin, acteosides and catalpol from dry powders of plantago lanceolate. FT-NIR spectra were processed in PLS- and deep learning methods and the accuracies of models have been calculated and compared. Aucubine, acteosides and catalpol contents have been predicted with a root mean square error of 0.56, 0.25 and 0.18%, respectively by using PLS method. Deep learning did not allowed to improve the accuracies but allowed obtaining similar accuracies. FT-NIR based method showed interesting results and is promising to develop a fully usable method for selection programs of plantain with high level contents of biomolecules.