2019年人工智能视觉在制造业应用.pptx

1、,AI History,人工智能的过去,人工智能发展的两个主要阶段Two main stages of AI,物理符号系统PSSH(Physical Symbol System Hypothesis),左侧：赫伯特西蒙 右侧：艾伦纽厄尔Left:Herbert A.Simon Right:Alan Newell,2012年以前：专家系统Before 2012:Experts Definition,3,Empower With AI,2012年以后：深度学习After 2012:Deep Learning,4,Empower With AI,人工智能发展的两个主要阶段Two main stage

2、s of AI,人工智能技术 AI Technologies,自然语言理解Natural Language Processing,计算机视觉Computer Vision,5,Empower With AI,人工智能三要素 Three Elements of AI,反馈Feedback,数据3.Data,模型2.Model,人工Artificial,智能Intelligence,深度学习计算框架DL computing framework,计算力1.Computing power,人工智能大脑AI Brain,6,Empower With AI,活的人工智能让产品更强大Live AI make

3、 products better,7,Empower With AI,深度学习训练Deep Leaning Training,现象 Phenomenon 1,000,001,结果 Result,?,8,Empower With AI,The challenges of AI,人工智能的挑战,Artificial Intelligence,AI,大量的人工高昂的成本A lot of manual effortsHigh labor costs,10,Empower With AI,准确率的提升Improvement Of Accuracy,准确率Accuracy,成本Cost,100%的准确率难

4、度极大The accuracy of 100%Impossibly Difficult,11,Empower With AI,Industrial AI,智能制造,传统工业视觉 vs 人工智能Traditional Industrial Vision vs AI,传统工业视觉Traditional Industrial Vision,简单外观检测 Simple appearance detection,测距 Distance measurement,13,Empower With AI,传统工业视觉缺陷Traditional Industrial VisionLimitations,固定位置（

5、Fixed position）固定环境（Fixed setting）固定算法（Fixed algorithm）,14,Empower With AI,拍摄条件要求低（Low shooting requirements）异常扩展性好（Good expansibility in exception）,人工智能优势Artificial IntelligenceAdvantages,传统工业视觉 vs 人工智能Traditional Industrial Vision vs AI,人工智能能做什么？What can AI do?,分类-什么Classification:What?,Plant Iden

6、tification x AI Deep Learning,形色,10000 Species x 98%x 30 million,15,Empower With AI,植物识别 x 人工智能,检测-哪里Detection:Where?,自动批改数学作业 x 人工智能Correct math homework x AI Deep Learning,98%x 9 million x 8000 Years,爱作业,16,Empower With AI,人工智能能做什么？What can AI do?,质检=什么+哪里Quality Assurance=What