[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118551-en":3,"doc-seo-118551-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118551,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","AUTOMATING MICROSCOPIC IMAGE ANALYSIS POST-PHOTOLITHOGRAPHY WITH MACHINE LEARNING","This thesis addresses the challenges of manual analysis of semiconductor microscopy images by using machine learning to automate the workflow, with emphasis on the photolithography stage. It compares machine learning approaches for classifying images according to exposure and development levels, reducing the impact of human error in traditional inspection. A dedicated dataset and a full modeling framework support training, preprocessing, augmentation, evaluation, and selection. The work shifts from surface-defect detection toward interpreting underlying causes, enabling more precise, efficient analysis for academic semiconductor research and faster student feedback.","© 2024 Hardik Sandeep Fulfagar  \nAUTOMATING MICROSCOPIC IMAGE ANALYSIS POST-PHOTOLITHOGRAPHY  \nWITH MACHINE LEARNING  \nBY  \nHARDIK SANDEEP FULFAGAR  \nTHESIS  \nSubmitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science in the Graduate College of the  \nUniversity of Illinois Urbana-Champaign, 2024  \nUrbana, Illinois  \nAdviser:  \nProfessor Klara Nahrstedt  \nABSTRACT  \nThis thesis addresses the challenges in the manual analysis of semiconductor images by leveraging machine learning techniques to automate the process, with a focus on the photolithography stage. We compare various machine learning techniques for classifying images based on exposure and development levels, aimed at overcoming the limitations of human error in traditional analysis methods. In this thesis, we have created a dataset and used a comprehensive framework for the application of machine learning models. By shifting the focus from merely detecting surface defects to understanding the underlying causes during the photolithography process, this research aims to provide more targeted solutions for improving semiconductor manufacturing and understanding the errors. The findings of this thesis have the potential to enhance methodological precision and efficiency in semiconductor research, particularly beneficial in academic settings for instant analysis and feedback, thereby improving the learning experience for students studying this critical phase of semiconductor manufacturing.  \n”To my parents, family, and friends, for their love, support, and unwavering belief in me.”  \nACKNOWLEDGMENTS  \nI would like to express my deepest gratitude to my advisor, Professor Klara Nahrstedt, for her invaluable guidance and humble nature. Being one of her advisees has been an honor, and I am deeply thankful for her support throughout this journey.  \nImmense gratitude goes to my mom, dad, brother, and all my family members for their unwavering support and encouragement. Their belief in me has always been a constant source of strength, and I am truly blessed to have them by my side.  \nSpecial thanks to Beitong Tian and Robert Kaufman for their invaluable assistance and collaboration in this project. Their contributions have been instrumental in the success of this work. I extend my sincere thanks to Xiaoyang Wang for his assistance with this project.  \nI am profoundly grateful to University of Illinois Urbana-Champaign for providing me with a nurturing environment and a wealth of experiences. Being a part of this esteemed institution has been a privilege, and it will always hold a special place in my heart for the people I met, the lessons I learned, and all the memorable moments.  \nI’m also thankful to Aditi Tiwari, Saket Jajoo, and Rishabh Garg for their companionship and encouragement. Special gratitude is due to my friend Savya Khosla, who also helped by offering valuable suggestions for the project. I am deeply grateful to each of them for the countless invaluable memories that have made my time here truly enjoyable and unforgettable.  \nTo everyone who has been a part of this journey, I extend my deepest gratitude. Your support and encouragement have been the pillars of my success, and I am forever grateful.  \nTABLE OF CONTENTS  \nCHAPTER 1 INTRODUCTION ............................ 1  \n1.1 Motivation and Problem ............................. 1  \n1.2 Related Work ................................... 2  \n1.3 Contributions ................................... 3  \n1.4 Outline of the Thesis ............................... 5  \nCHAPTER 2 BACKGROUND ............................. 6  \n2.1 Cleanrooms .................................... 6  \n2.2 Photolithography ................................. 7  \n2.3 Machine Learning Techniques .......................... 8  \nCHAPTER 3 METHODOLOGY ............................ 15  \n3.1 Data Collection and Dataset Creation ...................... 15  \n3.2 Data Analysis ................................... 17  \n","cbCaid3BfFhinGTu","https://ap.wps.com/l/cbCaid3BfFhinGTu","pdf",10060631,1,53,"English","en",105,"# Chapter 1 Introduction\n## Motivation and Problem\n## Related Work\n## Contributions\n## Outline of the Thesis\n# Chapter 2 Background\n## Cleanrooms\n## Photolithography\n## Machine Learning Techniques\n# Chapter 3 Methodology\n## Data Collection and Dataset Creation\n## Data Analysis\n## Data Preprocessing\n## Data Augmentation\n## Machine Learning Models\n## Model Evaluation and Selection\n# Chapter 4 Results\n## Data Analysis Results\n## Machine Learning Techniques\n## Model Efficiency Analysis\n# Chapter 5 Summary\n## Conclusion\n## Future Work","[{\"question\":\"What problem does the thesis target in semiconductor microscopy analysis?\",\"answer\":\"The thesis targets the time-consuming and error-prone manual inspection of microscopy images to detect defects and inaccuracies, especially after photolithography.\"},{\"question\":\"How does the thesis use machine learning in the photolithography workflow?\",\"answer\":\"It trains machine learning models to classify images based on exposure and development levels, using a dataset and a complete pipeline including preprocessing, augmentation, and evaluation.\"},{\"question\":\"What is the key shift in focus compared with traditional defect detection?\",\"answer\":\"Instead of only detecting surface defects, the research aims to understand underlying causes during the photolithography process to support more targeted improvements in semiconductor manufacturing.\"}]","AUTOMATING MICROSCOPIC IMAGE ANALYSIS POST-PHOTOLITHOGRAPHY WITH MACHINE LEARNING | PDF",1785684110,134,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"automating-microscopic-image-analysis-post-photolithography-with-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/automating-microscopic-image-analysis-post-photolithography-with-machine-learning/118551/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis target in semiconductor microscopy analysis?","Question",{"text":75,"@type":76},"The thesis targets the time-consuming and error-prone manual inspection of microscopy images to detect defects and inaccuracies, especially after photolithography.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis use machine learning in the photolithography workflow?",{"text":80,"@type":76},"It trains machine learning models to classify images based on exposure and development levels, using a dataset and a complete pipeline including preprocessing, augmentation, and evaluation.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the key shift in focus compared with traditional defect detection?",{"text":84,"@type":76},"Instead of only detecting surface defects, the research aims to understand underlying causes during the photolithography process to support more targeted improvements in semiconductor manufacturing.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]