2019年人工智能視覺在制造業應用.pptx

1、,AI History,人工智能的過去,人工智能發展的兩個主要階段Two main stages of AI,物理符號系統PSSH(Physical Symbol System Hypothesis),左側：赫伯特西蒙 右側：艾倫紐厄爾Left:Herbert A.Simon Right:Alan Newell,2012年以前：專家系統Before 2012:Experts Definition,3,Empower With AI,2012年以后：深度學習After 2012:Deep Learning,4,Empower With AI,人工智能發展的兩個主要階段Two main stage

2、s of AI,人工智能技術 AI Technologies,自然語言理解Natural Language Processing,計算機視覺Computer Vision,5,Empower With AI,人工智能三要素 Three Elements of AI,反饋Feedback,數據3.Data,模型2.Model,人工Artificial,智能Intelligence,深度學習計算框架DL computing framework,計算力1.Computing power,人工智能大腦AI Brain,6,Empower With AI,活的人工智能讓產品更強大Live AI make

3、 products better,7,Empower With AI,深度學習訓練Deep Leaning Training,現象 Phenomenon 1,000,001,結果 Result,?,8,Empower With AI,The challenges of AI,人工智能的挑戰,Artificial Intelligence,AI,大量的人工高昂的成本A lot of manual effortsHigh labor costs,10,Empower With AI,準確率的提升Improvement Of Accuracy,準確率Accuracy,成本Cost,100%的準確率難

4、度極大The accuracy of 100%Impossibly Difficult,11,Empower With AI,Industrial AI,智能制造,傳統工業視覺 vs 人工智能Traditional Industrial Vision vs AI,傳統工業視覺Traditional Industrial Vision,簡單外觀檢測 Simple appearance detection,測距 Distance measurement,13,Empower With AI,傳統工業視覺缺陷Traditional Industrial VisionLimitations,固定位置（

5、Fixed position）固定環境（Fixed setting）固定算法（Fixed algorithm）,14,Empower With AI,拍攝條件要求低（Low shooting requirements）異常擴展性好（Good expansibility in exception）,人工智能優勢Artificial IntelligenceAdvantages,傳統工業視覺 vs 人工智能Traditional Industrial Vision vs AI,人工智能能做什么？What can AI do?,分類-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,植物識別 x 人工智能,檢測-哪里Detection:Where?,自動批改數學作業 x 人工智能Correct math homework x AI Deep Learning,98%x 9 million x 8000 Years,愛作業,16,Empower With AI,人工智能能做什么？What can AI do?,質檢=什么+哪里Quality Assurance=What+Where,分類Classificat

7、ion,檢測Detection,+,17,Empower With AI,人工智能能做什么？What AI can do?,智能制造應用案例Cases in Industrial AI,零件視覺索引管理Visual Index Management for Parts,配件管理（Parts Management）安全生產（Safety Control）,18,Empower With AI,NO,Yes,配置檢測Configuration Inspection,19,Empower With AI,智能制造應用案例Cases in Industrial AI,復雜場景類裸眼質量檢測Automa

8、tion QA in Complex Scenes,20,Empower With AI,智能制造應用案例Cases in Industrial AI,曲面檢測Curved Surface Measurement,面臨的挑戰 Challenges:,劃痕（Nicks）灰塵（Dust）多角度（Multi-angle）,21,Empower With AI,智能制造應用案例Cases in Industrial AI,Cooperation,期待與您合作,About Us,A high-tech company specializing in the research and developmen

9、t of key technologies for AI,With the vision to develop the AI technology that augments peoples experiences in life,Glority has devoted years in the fields of computer vision and natural language understanding.Great advances are being made in AI technology,big data and large-scale user data and thei

10、r application in education,manufacturing and lifestyle.Components of our team:300 employees and 80%engineers.,23,Empower With AI,一家專注于人工智能關鍵技術研發的高科技企業,杭州睿琪軟件有限公司成立于2009年，在計算機視覺和自然語言理解領域深耕多年。通過人工智能賦能，在生活、財務、制造、醫療、旅游等多個領域，已經形成有由人工智能技術、大數據和大規模用戶共同構成的領先優勢?，F有員工300余人，研發人員占80%。,杭州睿琪軟件有限公司,THANKS,Empower With AI,