RESUMO
INTRODUCTION: This study aimed to investigate whether the facial soft tissue changes of individuals who had undergone surgically assisted rapid maxillary expansion (SARME) would be detected by three different well-known facial biometric recognition applications. METHODS: To calculate similarity scores, the pre- and postsurgical photographs of 22 patients who had undergone SARME treatment were examined using three prominent cloud computing-based facial recognition application programming interfaces (APIs): AWS Rekognition (Amazon Web Services, Seattle, WA, USA), Microsoft Azure Cognitive (Microsoft, Redmond, WA, USA), and Face++ (Megvii, Beijing, China). The pre- and post-SARME photographs of the patients (relaxed, smiling, profile, and semiprofile) were used to calculate similarity scores using the APIs. Friedman's two-way analysis of variance and the Wilcoxon signed-rank test were used to compare the similarity scores obtained from the photographs of the different aspects of the face before and after surgery using the different programs. The relationship between measurements on lateral and posteroanterior cephalograms and the similarity scores was evaluated using the Spearman rank correlation. RESULTS: The similarity scores were found to be lower with the Face++ program. When looking at the photo types, it was observed that the similarity scores were higher in the smiling photos. A statistically significant difference in the similarity scores (Pâ¯< 0.05) was found between the relaxed and smiling photographs using the different programs. The correlation between the cephalometric and posteroanterior measurements and the similarity scores was not significant (Pâ¯> 0.05). CONCLUSION: SARME treatment caused a significant change in the similarity scores calculated with the help of three different facial recognition programs. The highest similarity scores were found in the smiling photographs, whereas the lowest scores were found in the profile photographs.
RESUMO
INTRODUCTION: This study aimed to investigate whether the postoperative change in patients after orthognathic surgery, whose facial aesthetics was affected, led to detectable differences using Microsoft Azure, Amazon Web Services Rekognition, and Face++, which were commercially available face recognition systems. METHODS: Photographs of 35 patients after orthognathic surgery were analyzed using 3 well-known cloud computing-based facial recognition application programming interfaces to compute similarity scores between preoperative and postoperative photographs. The preoperative, relaxed, smiling, profile, and semiprofile photographs of the patients were compared separately to validate the relevant application programming interfaces. Patient characteristics and type of surgery were recorded for statistical analysis. Kruskal-Wallis rank sum tests were performed to analyze the relationship between patient characteristics and similarity scores. Multiple-comparison Wilcoxon rank sum tests were performed on the statistically significant characteristics. RESULTS: The similarity scores in the Face++ program were lower than those in the Microsoft Azure and Amazon Web Services Rekognition. In addition, the similarity scores were higher in smiling photographs. A statistically significant difference was found in similarity scores between relaxed and smiling photographs according to different programs (P <0.05). For all 3 facial recognition programs, comparable similarity scores were found in all photographs taken before and after surgery across sex, type of surgery, and type of surgical approach. The type of surgery and surgical approach, sex, and amount of surgical movement did not significantly affect similarity scores in any facial recognition programs (P >0.05). CONCLUSIONS: The similarity scores between the photographs before and after orthognathic surgery were high, suggesting that the software algorithms might value measurements on the basis of upper-face landmarks more than lower-face measurements.