(H)是色彩.ppt

Intelligent Database Systems Lab N.Y.U.S.T. I. M. Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology * A Study on Automatic Recognition of Road Signs Presenter : You Lin Chen Authors : Y.-Y. Nguwi and A.Z. Kouzani 2001.IVC.11 * Outline Motivation Objective Methodology Experiments Conclusion Comments Motivation A driver may not however notice road signs under adverse road condition. Failure to notice, or disregard of road signs may directly or indirectly contribute to some road accidents * Objectives This paper classifies the methods applied to road sign recognition. Recognition problem are reviewed, and a comparison of the features of these methods is given. * Methodology COLOUR-BASED APPROACHES Colour Thresholding Segmentation HIS/HSV Transformation （H）是色彩、（S）飽和度、（V）明度 Region Growing Transformation Based on CIE CAM97 Model hue色彩, chroma色度, and lightness 明亮度 Colour Indexing * Methodology SHAPE-BASED APPROACHES Hierarchical Spatial Feature Matching (HSFM) Hough Transform Template Matching Similarity Detection * Methodology Decision Tree Space Variant Sensor Window Genetic Algorithm Nearest Neighbour Classification Neural Networks * Methodology * Methodology * Conclusion Comparing to colour-based recognition, shape-based recognition faces more limitations. However, the faded colour on road sign can be compensated through the use of shape-based. * * Comments Advantage … Drawback Contribution is poor. Application Image processing * 對特殊影像的偵測及擷取往往需要在特殊參數平面來進行,霍氏轉換就是其中一種，其應用範圍十分的廣，直線，圓形，角落都可應用霍氏轉換來完成 * An image in the test set is recognised by assigning to it the label of most of the closest points in the learning set [36]. All images are then normalised to certain value. The image in the learning set that best correlates with the test image is then the result. * Intelligent Database Systems Lab N.Y.U.S.T. I. M. Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Te