Qualitative representations for recognition
Qualitative representations for recognition
复制标题
DOI：
10.1167/1.3.298
复制
发表时间：
2010-03
影响因子：
1.8
通讯作者：
K. Thoresz;Pawan Sinha
中科院分区：
文献类型：
--
作者：
K. Thoresz;Pawan Sinha
本文描述了一种物体和场景的表示，该表示对由照明变化引起的图像强度变化是稳定的，并且能够容忍图像退化（如传感器噪声）。这种表示称为比率模板，使用低分辨率顺序对比关系作为其匹配基元。这些原语的选择不仅考虑了计算的简单性和鲁棒性，而且还考虑了灵长类动物大脑中视觉处理的早期阶段的现有知识。尽管目前没有证据表明灵长类动物的视觉系统实际上使用了这种表征，但这种表征在生物学上是合理的。首先手工构造比率模板，然后可以从一组示例中自动学习比率模板。介绍了人脸检测和场景索引两种应用。该比例模板的检测率超过90%，可在2.6秒内处理一幅320× 280像素的多尺度图像。论文导师：Pawan Sinha职称：助理教授
This thesis describes a representation for objects and scenes that is stable against variations in image intensity caused by illumination changes and tolerant to image degradations such as sensor noise. The representation, called a ratio-template, uses low-resolution ordinal contrast relationships as its matching primitives. The choice of these primitives was inspired not only by considerations of computational simplicity and robustness, but also by current knowledge of the early stages of visual processing in the primate brain. The resulting representation is biologically plausible, although there is currently no evidence to suggest that the representation is actually used by the primate visual system. Constructed manually at first, the ratio-template can be learned automatically from a set of examples. Two applications—face detection and scene indexing—are described. The ratio-template achieves detection rates higher than 90% and can process a 320× 280 pixel image in 2.6 seconds at multiple scales. Thesis Supervisor: Pawan Sinha Title: Assistant Professor