Estimating Acrylamide and 5-Hydroxymethylfurfural Levels in Crackers Using Computer Vision: Effects on Consumer...

Area of Science:

• Food Science
• Analytical Chemistry
• Computer Vision

Background:

• Baking crackers generates neo-formed contaminants (NFCs) like acrylamide (AA) and 5-hydroxymethylfurfural (HMF) via non-enzymatic browning.
• Conventional methods for quantifying NFCs are time-consuming, labor-intensive, and require specialized expertise.

Purpose of the Study:

• To develop and validate computer vision (CV) models for rapid prediction of AA and HMF in crackers.
• To assess the efficiency of CV in estimating NFCs compared to traditional analytical techniques.

Main Methods:

• Digital image analysis using CV models was employed to analyze cracker surface characteristics.
• Five baking temperatures (160-200 °C) and times (15-35 min) were tested.
• CV predictions were cross-validated against conventional analytical measurements for AA and HMF.

Main Results:

• CV models achieved an average error of 3.10% for AA and 3.28% for HMF, demonstrating high accuracy.
• The study successfully correlated cracker baking conditions with NFC levels.
• Consumer preference studies indicated a preference for samples baked at 180 °C for 25 min, which had the lowest AA and HMF.

Conclusions:

• Computer vision is an effective and rapid tool for estimating AA and HMF in crackers.
• CV can aid in optimizing baking processes to minimize NFC formation while meeting consumer preferences.
• This approach offers a promising alternative for quality control in the food industry.