Inducing Features from Visual Noise using Statistical Machine Learning Techniques

使用统计机器学习技术从视觉噪声中归纳特征

• 批准号: 0631602
• 负责人: Andrew Cohen
• 金额: $ 15万
• 依托单位: University of Massachusetts Amherst
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2006
• 资助国家: 美国
• 起止时间: 2006-11-15 至 2010-01-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0631602&HistoricalAwards=false
• 关键词: Inducing; Features; Visual; Noise; using

Understanding how humans differentiate between visual objects is a central problem for psychologists who want to understand the visual system and for computer scientists who want to emulate its abilities. Previous work has developed techniques for determining the image locations and spatial frequencies most responsible for human performance in classification and identification tasks. These techniques, however, cannot tell us if the important image features are detected in a single step, for example, by matching the visual object to a single internal representation such as a template, or by combining the result of multiple detectors. With support from the National Science Foundation, Dr. Andrew Cohen from the University of Massachusetts, Amherst, will develop a new model, the Multiple Independent Template Induction Model (MITIM), designed to answer such questions.Human behavioral experiments on tasks such as word recognition in noisy images have suggested that people do not always recognize objects holistically. Rather, they appear detect pieces independently and then combine those results. If this is true in domains such as face or object classification and recognition, understanding these abilities requires knowledge of the independently detected parts and their relative importance. The proposed MITIM algorithm will use statistical techniques from artificial intelligence research to process human image classification data and discover the independent templates used in object recognition. The insights gained will help illuminate human visual performance and help scientists and engineers better understand how to build computer systems that can replicate that performance, functionality that is increasingly important in web search, robotic, and security applications.This award was supported as part of the fiscal year 2006 Mathematical Sciences priority area special competition on Mathematical Social and Behavioral Sciences (MSBS).

对于想要了解视觉系统的心理学家和想要模拟其能力的计算机科学家来说，理解人类如何区分视觉对象是一个中心问题。之前的工作已经开发出确定图像位置和空间频率的技术，这些位置和空间频率对人类在分类和识别任务中的表现最有影响。然而，这些技术无法告诉我们是否在单个步骤中检测到重要的图像特征，例如，通过将视觉对象与单个内部表示（例如模板）相匹配，或者通过组合多个检测器的结果。在美国国家科学基金会的支持下，马萨诸塞大学阿默斯特分校的安德鲁·科恩博士将开发一种新模型——多重独立模板归纳模型（MITIM），旨在回答此类问题。针对单词等任务的人类行为实验噪声图像中的识别表明人们并不总是整体地识别物体。相反，它们会独立检测片段，然后将这些结果组合起来。如果在人脸或物体分类和识别等领域确实如此，那么理解这些能力就需要了解独立检测到的部分及其相对重要性。所提出的 MITIM 算法将使用人工智能研究的统计技术来处理人类图像分类数据并发现用于对象识别的独立模板。获得的见解将有助于阐明人类视觉性能，并帮助科学家和工程师更好地了解如何构建可以复制在网络搜索、机器人和安全应用中日益重要的性能和功能的计算机系统。该奖项作为2006 财政年度数学科学优先领域数学社会和行为科学（MSBS）特别竞赛。