Nova Baeza, PNavia-Ramirez, M. FLobos-Ortiz, MAlvial Ahumada, FRiveros, AOrellana-Donoso, MathiasMoya, M. PEstrada-Hernandez, A. CAngarita-Arevalo, L. ACasanova-Martinez, DPiagkou, MTriantafyllou, GValenzuela Fuenzalida, J. JSanchis-Gimeno, JLoaiza-Giraldo, J. PKonschake, MGranite, G2026-06-302026-06-302026Current problems in surgery, N° 79 (2026) pp. 1-361535-6337https://hdl.handle.net/20.500.12254/7652The study develops computer vision (CV) models to rapidly predict acrylamide (AA) and 5-hydroxymethylfurfural (HMF) levels in crackers, comparing CV estimates with conventional analytical methods. Five baking temperatures (160–200°C) and times (15–35 min) were tested, showing CV accuracy with average errors of 3.10% for AA and 3.28% for HMF. Consumer preference tests (CATA) revealed that crackers baked at 180°C for 25 min, with the lowest AA and HMF levels, were most accepted.enAcceso abierto5-HydroxymethylfurfuralAcrylamideComputer VisionArticlehttps://orcid.org/0000-0002-1781-062Xhttps://doi.org/10.1016/j.cpsurg.2026.102027