•The present study addresses sources of error affecting the validity of mobile-based dietary assessments in a free-living setting.•A two-stage data modification process that included manual data cleaning and reanalyzing of prepackaged foods improved the accuracy of an image-assisted mobile nutrition app.•Stage 1 errors were commonly observed and associated with wrong food code selections, portion size estimates, misreporting, and missing condiments.•Stage 2 errors related to the mobile nutrition app were associated with prepackaged and restaurant/street foods that only provide limited micronutrient information.•Reanalyzing food codes with missing nutrients substantially improved the accuracy of micronutrient intake levels and enhanced correlations between the app and 24-h dietary recall.•Results highlight the importance of addressing errors in mobile-based dietary assessments and continually updating and expanding prepackaged food databases with full nutrient information. Display omitted Mobile nutrition applications (apps) provide a simple way for individuals to record their diet, but the validity and inherent errors need to be carefully evaluated. The aim of this study was to assess the validity and clarify the sources of measurement errors of image-assisted mobile nutrition apps. This was a cross-sectional study with 98 students recruited from School of Nutrition and Health Sciences, Taipei Medical University. A 3-d nutrient intake record by Formosa Food and Nutrient Recording App (FoodApp) was compared with a 24-h dietary recall (24-HDR). A two-stage data modification process, manual data cleaning, and reanalyzing of prepackaged foods were employed to address inherent errors. Nutrient intake levels obtained by the two methods were compared with the recommended daily intake (DRI), Taiwan. Paired t test, Spearman's correlation coefficients, and Bland–Altman plots were used to assess agreement between the FoodApp and 24-HDR. Manual data cleaning identified 166 food coding errors (12%; stage 1), and 426 food codes with missing micronutrients (32%) were reanalyzed (stage 2). Positive linear trends were observed for total energy and micronutrient intake (all Ptrend < 0.05) after the two stages of data modification, but not for dietary fat, carbohydrates, or vitamin D. There were no statistical differences in mean energy and macronutrient intake between the FoodApp and 24-HDR, and this agreement was confirmed by Bland–Altman plots. Spearman's correlation analyses showed strong to moderate correlations (r = 0.834 ∼ 0.386) between the two methods. Participants’ nutrient intake tended to be lower than the DRI, but no differences in proportions of adequacy/inadequacy for DRI values were observed between the two methods. Mitigating errors significantly improved the accuracy of the Formosa FoodApp, indicating its validity and reliability as a self-reporting mobile-based dietary assessment tool. Dietitians and health professionals should be mindful of potential errors associated with self-reporting nutrition apps, and manual data cleaning is vital to obtain reliable nutrient intake data.