J. Stuart, Anita Stephen, Karen Aul, Michael D. Bumbach, Shari Huffman, Brooke Russo, Benjamin Lok
{"title":"开发增强现实滤镜,显示不同肤色的视觉线索","authors":"J. Stuart, Anita Stephen, Karen Aul, Michael D. Bumbach, Shari Huffman, Brooke Russo, Benjamin Lok","doi":"10.3389/frvir.2024.1363193","DOIUrl":null,"url":null,"abstract":"Introduction: Variations in skin tone can significantly alter the appearance of symptoms such as rashes or bruises. Unfortunately, previous works utilizing Augmented Reality (AR) in simulating visual symptoms have often failed to consider this critical aspect, potentially leading to inadequate training and education. This study seeks to address this gap by integrating generative artificial intelligence (AI) into the AR filter design process.Methods: We conducted a 2 × 5 within-subjects study with second-year nursing students (N = 117) from the University of Florida. The study manipulated two factors: symptom generation style and skin tone. Symptom generation style was manipulated using a filter based on a real symptom image or a filter based on a computer-generated symptom image. Skin tone variations were created by applying AR filters to computer-generated images of faces with five skin tones ranging from light to dark. To control for factors like lighting or 3D tracking, 101 pre-generated images were created for each condition, representing a range of filter transparency levels (0–100). Participants used visual analog scales on a computer screen to adjust the symptom transparency in the images until they observed image changes and distinct symptom patterns. Participants also rated the realism of each condition and provided feedback on how the symptom style and skin tone impacted their perceptions.Results: Students rated the symptoms displayed by the computer-generated AR filters as marginally more realistic than those displayed by the real image AR filters. However, students identified symptoms earlier with the real-image filters. Additionally, SET-M and Theory of Planned Behavior questions indicate that the activity increased students’ feelings of confidence and self-efficacy. Finally, we found that similar to the real world, where symptoms on dark skin tones are identified at later stages of development, students identified symptoms at later stages as skin tone darkened regardless of cue type.Conclusion: This work implemented a novel approach to develop AR filters that display time-based visual cues on diverse skin tones. Additionally, this work provides evidence-based recommendations on how and when generative AI-based AR filters can be effectively used in healthcare education.","PeriodicalId":502489,"journal":{"name":"Frontiers in Virtual Reality","volume":"7 10","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Developing augmented reality filters to display visual cues on diverse skin tones\",\"authors\":\"J. Stuart, Anita Stephen, Karen Aul, Michael D. Bumbach, Shari Huffman, Brooke Russo, Benjamin Lok\",\"doi\":\"10.3389/frvir.2024.1363193\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Introduction: Variations in skin tone can significantly alter the appearance of symptoms such as rashes or bruises. Unfortunately, previous works utilizing Augmented Reality (AR) in simulating visual symptoms have often failed to consider this critical aspect, potentially leading to inadequate training and education. This study seeks to address this gap by integrating generative artificial intelligence (AI) into the AR filter design process.Methods: We conducted a 2 × 5 within-subjects study with second-year nursing students (N = 117) from the University of Florida. The study manipulated two factors: symptom generation style and skin tone. Symptom generation style was manipulated using a filter based on a real symptom image or a filter based on a computer-generated symptom image. Skin tone variations were created by applying AR filters to computer-generated images of faces with five skin tones ranging from light to dark. To control for factors like lighting or 3D tracking, 101 pre-generated images were created for each condition, representing a range of filter transparency levels (0–100). Participants used visual analog scales on a computer screen to adjust the symptom transparency in the images until they observed image changes and distinct symptom patterns. Participants also rated the realism of each condition and provided feedback on how the symptom style and skin tone impacted their perceptions.Results: Students rated the symptoms displayed by the computer-generated AR filters as marginally more realistic than those displayed by the real image AR filters. However, students identified symptoms earlier with the real-image filters. Additionally, SET-M and Theory of Planned Behavior questions indicate that the activity increased students’ feelings of confidence and self-efficacy. Finally, we found that similar to the real world, where symptoms on dark skin tones are identified at later stages of development, students identified symptoms at later stages as skin tone darkened regardless of cue type.Conclusion: This work implemented a novel approach to develop AR filters that display time-based visual cues on diverse skin tones. Additionally, this work provides evidence-based recommendations on how and when generative AI-based AR filters can be effectively used in healthcare education.\",\"PeriodicalId\":502489,\"journal\":{\"name\":\"Frontiers in Virtual Reality\",\"volume\":\"7 10\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in Virtual Reality\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/frvir.2024.1363193\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Virtual Reality","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frvir.2024.1363193","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
介绍:肤色的变化会明显改变皮疹或瘀伤等症状的外观。遗憾的是,以前利用增强现实技术(AR)模拟视觉症状的工作往往没有考虑到这一关键方面,可能导致培训和教育不足。本研究试图通过将生成式人工智能(AI)整合到 AR 滤镜设计过程中来弥补这一不足:我们对佛罗里达大学护理专业二年级学生(117 人)进行了一项 2 × 5 的主体内研究。研究操纵了两个因素:症状生成风格和肤色。症状生成方式是通过基于真实症状图像的滤镜或基于计算机生成的症状图像的滤镜来操控的。肤色的变化是通过将 AR 滤镜应用于计算机生成的人脸图像而产生的,这些图像具有从浅到深的五种肤色。为了控制光照或 3D 跟踪等因素,我们为每种情况创建了 101 张预先生成的图像,代表了不同的滤镜透明度水平(0-100)。参与者使用计算机屏幕上的视觉模拟刻度来调整图像中症状的透明度,直到他们观察到图像变化和明显的症状模式。参与者还对每种情况的逼真度进行评分,并就症状样式和肤色如何影响他们的感知提供反馈:结果:学生对计算机生成的 AR 滤镜所显示症状的评分略高于真实图像 AR 滤镜所显示症状的评分。不过,使用真实图像滤镜时,学生更早识别出症状。此外,SET-M 和计划行为理论问题表明,该活动增强了学生的自信心和自我效能感。最后,我们发现,与现实世界中深色肤色的症状在发育后期才被识别出来的情况类似,无论线索类型如何,学生都能在肤色变深的后期识别出症状:这项研究采用了一种新颖的方法来开发 AR 滤镜,以显示不同肤色的基于时间的视觉提示。此外,这项工作还就如何以及何时在医疗保健教育中有效使用基于生成式人工智能的 AR 滤镜提出了循证建议。
Developing augmented reality filters to display visual cues on diverse skin tones
Introduction: Variations in skin tone can significantly alter the appearance of symptoms such as rashes or bruises. Unfortunately, previous works utilizing Augmented Reality (AR) in simulating visual symptoms have often failed to consider this critical aspect, potentially leading to inadequate training and education. This study seeks to address this gap by integrating generative artificial intelligence (AI) into the AR filter design process.Methods: We conducted a 2 × 5 within-subjects study with second-year nursing students (N = 117) from the University of Florida. The study manipulated two factors: symptom generation style and skin tone. Symptom generation style was manipulated using a filter based on a real symptom image or a filter based on a computer-generated symptom image. Skin tone variations were created by applying AR filters to computer-generated images of faces with five skin tones ranging from light to dark. To control for factors like lighting or 3D tracking, 101 pre-generated images were created for each condition, representing a range of filter transparency levels (0–100). Participants used visual analog scales on a computer screen to adjust the symptom transparency in the images until they observed image changes and distinct symptom patterns. Participants also rated the realism of each condition and provided feedback on how the symptom style and skin tone impacted their perceptions.Results: Students rated the symptoms displayed by the computer-generated AR filters as marginally more realistic than those displayed by the real image AR filters. However, students identified symptoms earlier with the real-image filters. Additionally, SET-M and Theory of Planned Behavior questions indicate that the activity increased students’ feelings of confidence and self-efficacy. Finally, we found that similar to the real world, where symptoms on dark skin tones are identified at later stages of development, students identified symptoms at later stages as skin tone darkened regardless of cue type.Conclusion: This work implemented a novel approach to develop AR filters that display time-based visual cues on diverse skin tones. Additionally, this work provides evidence-based recommendations on how and when generative AI-based AR filters can be effectively used in healthcare education.