Aim and objective: This study was conducted to evaluate the accuracy of a light-induced fluorescence intraoral camera vs the visual–tactile assessment method according to the modified International caries detection and assessment system-II (ICDAS-II) criteria clinically in the detection of initial occlusal caries. Materials and methods: Occlusal surfaces of 260 molar and premolar teeth from 52 adult participants were examined by two calibrated observers, using two diagnostic methods. Teeth were initially assessed visually according to the criteria of the ICDAS-II, and then by fluorescence camera (Soprolife®). Inter- and intraobserver agreements were measured using Cohen's kappa test. Correlation between methods was calculated using Wilcoxon signed-rank test, and effect size for comparison between the two modalities. The sensitivity, specificity, predictive values, diagnostic accuracy, likelihood ratios (LRs), area under the receiver operating characteristic (ROC) curve (AUC), and 95% confidence interval (95% CI) of the AUC for caries detection by Soprolife® were evaluated. Results: A significant positive correlation was found between the ICDAS-II and camera measurements (p-value <0.001, effect size = 0.572). The sensitivity of Soprolife® was 94.2%, specificity 84.2%, positive predictive value 87.1%, negative predictive value 92.8%, positive LR 6%, negative LR 0.07%, and the diagnostic accuracy 89.5%. AUC was 0.909 with 95% CI (0.863–0.955). There was a perfect intraobserver agreement (kappa = 1.00) for both testing modalities. There was moderate interobserver agreement (kappa = 0.520) with regards to ICDAS, while for Soprolife®, there was substantial interobserver agreement (kappa = 0.798). Conclusion: Soprolife® can be used as a valid and reliable assessment tool for occlusal caries detection. Clinical significance: Light-induced fluorescence intraoral camera is an efficient tool in the detection of initial occlusal caries.