Waterfowl biologists estimate seed production in moist-soil wetlands to calculate duck-energy days (DEDs) and evaluate management techniques. Previously developed models that predict plant seed yield using morphological measurements are tedious and time consuming. We developed simple linear regression models that indirectly and directly related seed-head area to seed production for 7 common moist-soil plants using portable and desktop scanners and a dot grid, and compared time spent processing samples and predictive ability among models. To construct models, we randomly collected approximately 60 plants/species at the Tennessee National Wildlife Refuge, USA, during September 2005 and 2006, threshed and dried seed from seed heads, and related dry mass to seed-head area. All models explained substantial variation in seed mass (R² ≥ 0.87) and had high predictive ability (R²_predicted ≥ 0.84). Processing time of seed heads averaged 22 and 3 times longer for the dot grid and portable scanner, respectively, than for the desktop scanner. We recommend use of desktop scanners for accurate and rapid estimation of moist-soil plant seed production. Seed predictions per plant from our models can be used to estimate total seed production and DEDs in moist-soil wetlands.