ITR/PE: Digital Imaging Techniques for the Simulation and Enhancement of Low Vision

ITR/PE：用于模拟和增强低视力的数字成像技术

• 批准号: 0113310
• 负责人: James Ferwerda
• 金额: $ 45.08万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2001
• 资助国家: 美国
• 起止时间: 2001-10-01 至 2006-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0113310&HistoricalAwards=false
• 关键词: ITR; PE; Digital; Imaging; Techniques

In this project the PIs will carry out a program of research and development to apply digital imaging techniques to the problem of low vision. The work will focus on two related thrusts. First, low vision simulation methods will be developed that accurately show people with normal vision what the world looks like to people with visual deficits. The goal is to develop simulation tools that designers can use to understand the visual limitations (and abilities) of people with low vision and thereby eliminate barriers to access from their designs. Applications in the areas of architectural design, driving safety, and the development of graphical user interfaces will be demonstrated. Second, the PIs will develop low vision image enhancement tools that can be used to transform images from digital cameras or graphics applications to create new images that are more comprehensible to people with low vision. The objective is to use computational models of low vision to develop image enhancement algorithms that can be incorporated into digital imaging systems to give people with low vision better access to the visual world. The PIs plan to use these algorithms to develop two new kinds of assistive technology: image profiling and enhancement tools for Web browsers to enable low vision access to Web-based graphical information; and portable augmented vision systems that can facilitate orientation, mobility and object recognition for people with low vision. The hope is that the methods developed will provide better understanding of the challenges facing people with low vision, and lead to effective assistive technologies that can help people with low vision live easier, fuller and more productive lives.

在该项目中，PI 将实施一项研究和开发计划，将数字成像技术应用于解决低视力问题。 这项工作将集中在两个相关的重点上。 首先，将开发低视力模拟方法，准确地向视力正常的人展示视力缺陷者眼中的世界。 目标是开发模拟工具，设计人员可以使用这些工具来了解弱视人士的视觉限制（和能力），从而消除访问其设计的障碍。 将展示建筑设计、驾驶安全和图形用户界面开发等领域的应用。 其次，PI 将开发低视力图像增强工具，可用于转换来自数码相机或图形应用程序的图像，以创建低视力人群更容易理解的新图像。 目标是使用低视力的计算模型来开发图像增强算法，该算法可以合并到数字成像系统中，让低视力的人更好地接触视觉世界。 PI 计划使用这些算法开发两种新型辅助技术：用于 Web 浏览器的图像分析和增强工具，使弱视者能够访问基于 Web 的图形信息；便携式增强视觉系统，可以帮助弱视人士定向、移动和识别物体。 希望所开发的方法能够更好地理解低视力人群所面临的挑战，并带来有效的辅助技术，帮助低视力人群过上更轻松、更充实和更富有成效的生活。