[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118207-en":3,"doc-seo-118207-105":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},118207,8796095461610,"Oliver","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","A MACHINE LEARNING PIPELINE FOR LABELING CHESS PIECES IMAGES","The thesis presents a machine learning pipeline dedicated to recognizing and differentiating chess-piece images. It improves a starting dataset of chessboard images by adding curated captures from physical tournaments and generating digital recreations of real professional games in a simulated physical environment. The work then builds a tailored preprocessing pipeline to prepare training data, automate meticulous labeling of raw inputs, and ensure consistent data curation. The resulting contributions support ongoing computer-vision system development.","A MACHINE LEARNING PIPELINE FOR LABELING CHESS PIECES IMAGES  \nROGER MOLLON PRAT  \nThesis supervisor: SILVERIO JUAN MARTÍNEZ FERNÁNDEZ (Department of Service and Information  \nSystem Engineering)  \nThesis co-supervisor: SANTIAGO DEL REY JUAREZ (Department of Service and Information System  \nEngineering)  \nDegree: Bachelor Degree in Informatics Engineering (Software Engineering)  \nBachelor's thesis  \nFacultat d'Informàtica de Barcelona (FIB) Universitat Politècnica de Catalunya (UPC) -BarcelonaTech  \n16/10/2023  \nResum  \nAvui en dia hi ha molts casos d'ús i camps emergents de les tecnologies d'intel·ligència artificial/aprenentatge automàtic. Un dels diversos camps rellevants és el de la formació de models de reconeixement d'imatges, que ja té diverses aplicacions potencials endesenvolupament. Aquest projecte estudia aquest camp a través d'un cas concret d'estudi: un model d'aprenentatge automàtic construït per reconèixer i diferenciar imatges de pecesd'escacs.  \nPerquè els models discerneixin amb precisió què se'ls presenta, és fonamental reunir irefinar meticulosament les dades que reben. En aquest projecte, basat en un conjunt dedades ja existent d'imatges de tauler d'escacs, aprofundim amb l'adquisició d'imatges de tauler d'escacs seleccionades, cadascuna representant un espectre d'estats i escenaris dejoc. Això es fa de dues maneres: en primer lloc, capturant imatges de taulers d'escacs físics durant tornejos presencials i, en segon lloc, recreant versions digitals de jocs d'escacs professionals reals en un entorn físic artificial per tal d'enriquir substancialment el nostreconjunt de dades. Aquest pas fonamental proporciona els components bàsics del nostre canal de recollida de dades, que és la segona part del projecte.  \nUn cop s'ha completat el pas anterior, procedim a construir un canal de preprocessament adaptat per preparar dades per a l'entrenament del model, automatitzar l'etiquetatge meticulós de dades en brut i curar dades de manera consistent.  \nEn resum, aquesta tesi es dedica íntegrament a la millora i perfeccionament d'un conjunt dedades d'aprenentatge automàtic per al reconeixement d'imatges de taulers d'escacs, millorant la recollida de dades i automatitzant els fluxos de treball de preprocessament dedades. Les idees obtingudes d'aquest projecte tenen importància per al desenvolupament continuat de sistemes de visió per ordinador.  \nResumen  \nHoy en d ía, hay muchos casos de uso y campos emergentes para las tecnologías de inteligencia artificial/aprendizaje automático. Uno de varios campos relevantes es el del entrenamiento de modelos de reconocimiento de imágenes, que a su vez tiene variasaplicaciones potenciales que ya están en desarrollo. Este proyecto estudia este campo através de un caso de estudio específico: un modelo de aprendizaje automático creado para reconocer y diferenciar imágenes de piezas de ajedrez.  \nPara que los modelos disciernan con precisión lo que se les presenta, es fundamental reuniry refinar meticulosamente los datos que reciben. En este proyecto, basado en un conjunto de datos previamente existente de imágenes de tableros de ajedrez, profundizamos en la adquisición de imágenes seleccionadas de tableros de ajedrez, cada una de las cuales representa un espectro de estados y escenarios del juego. Esto se hace de dos maneras: en primer lugar, capturando imágenes de tableros de ajedrez físicos durante torneos presenciales y, en segundo lugar, recreando versiones digitales de partidas de ajedrez profesionales reales en un entorno físico artificial para enriquecer sustancialmente nuestro conjunto de datos. Este paso fundamental proporciona los componentes básicos de nuestro canal de recopilación de datos, que es la segunda parte del proyecto.  \nUna vez que se ha completado el paso anterior, procedemos a construir un canal de preprocesamiento personalizado para preparar datos para el entrenamiento de modelos, automatizar el etiquetado meticuloso de los datos sin procesar y curar datos de ","cbCaicv7XFM2uX4v","https://ap.wps.com/l/cbCaicv7XFM2uX4v","pdf",1094762,1,76,"English","en",105,"# Data acquisition and dataset enrichment\n## Capturing physical tournament chessboard images\n## Recreating professional games in a simulated environment\n# Preprocessing and labeling pipeline\n## Data preparation for model training\n## Automated labeling and consistent curation","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"It focuses on training a machine learning model that can recognize and distinguish chess piece images accurately.\"},{\"question\":\"How is the dataset improved in the project?\",\"answer\":\"By augmenting an existing chessboard-image dataset with both physical captures from real tournaments and digital recreations of professional chess games.\"},{\"question\":\"What steps does the pipeline include after data collection?\",\"answer\":\"It constructs a preprocessing pipeline for training readiness, automates labeling of raw data, and curates the dataset consistently.\"}]","A MACHINE LEARNING PIPELINE FOR LABELING CHESS PIECES IMAGES | PDF",1785682202,192,{"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},"a-machine-learning-pipeline-for-labeling-chess-pieces-images","",{"@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/a-machine-learning-pipeline-for-labeling-chess-pieces-images/118207/",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 address?","Question",{"text":75,"@type":76},"It focuses on training a machine learning model that can recognize and distinguish chess piece images accurately.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the dataset improved in the project?",{"text":80,"@type":76},"By augmenting an existing chessboard-image dataset with both physical captures from real tournaments and digital recreations of professional chess games.",{"name":82,"@type":73,"acceptedAnswer":83},"What steps does the pipeline include after data collection?",{"text":84,"@type":76},"It constructs a preprocessing pipeline for training readiness, automates labeling of raw data, and curates the dataset consistently.","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"]