计算机视觉 computer vision 中国科学技术大学 自动化系
中国科学技术大学 自动化系
第一章绪论
What is Computer Vision? Trucco and Verri computing properties of the 3D world from one or more digital images Stockman and Shapiro To make useful decisions about real physical objects and scenes based on sensed images Ballard and Brown The construction of explicit,meaningful description of physical objects from images Forsyth and Ponce To extract descriptions of the world from pictures or sequences of pictures
Trucco and Verri ◦ computing properties of the 3D world from one or more digital images Stockman and Shapiro ◦ To make useful decisions about real physical objects and scenes based on sensed images Ballard and Brown ◦ The construction of explicit, meaningful description of physical objects from images Forsyth and Ponce ◦ To extract descriptions of the world from pictures or sequences of pictures
天空 树林 房尾 道 也塘 地 从图像到识别 (a) (d) 天空 树林 房屋 道路 (b) 泡塘 田地 (e) 乡村景物 (c) (f)
TRAINING During the training phase.a neural network is fed thousands of labeled images of various animals, learning to classify them. INPUT An unlabeled image is shown to the pretrained 从图像到识别 network. FIRST LAYER 06●00 The neurons respond to different simple shapes,like edges. HIGHER LAYER Neurons respond to more complex structures. TOP LAYER Neurons respond to highly complex abstract concepts that we would identify as differ- ent animals. OUTPUT The network predicts what the object most likely is,based on its 10%WOLF 90%D0G treining