As one of the most important elements of a control loop, control valves are essential assets to the plant because they ensure the high quality of products, as well as the safety of personnel and equipment (Abbasi et al. in J Hydrol, 597:125717, 2021). Unfortunately, control valves tend to suffer from many issues, and stiction is one of the long-standing faults that results in oscillations in important process variables which are highly undesirable. In the present work, unthresholded recurrence plots and texture analysis previously developed for mining industry (Kok et al. in IFAC-PapersOnLine 52:36-41, 2019) is applied to diagnose stiction in process control loops. Texture features are extracted from distance matrices derived from typical control-loop OP-PV data generated from a valve stiction model. A neural network model is then trained based on the extracted features. The optimised classification model is then applied in industrial control loops to identify the presence of stiction. The results from 78 benchmark industrial loops with varying faulty issues show a comparable performance with the recent methods reported in the literature. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.