[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-116910-en":3,"doc-seo-116910-105":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},116910,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Automatic detection of knots and wood logs classification using machine learning","This project addresses the shortage of wood by improving timber defect detection and grading, since defects such as knots, cracks, and mildew strongly influence wood quality and market value. A deep learning pipeline detects knots from CT Log scanner data, converts coordinates, enlarges the dataset through image cropping, and assigns scores based on defect number and radius. Crops are separated into two classes and categorized via a classification threshold. Evaluation with accuracy metrics reports strong precision and recall, and the method completes detection and classification in about 1.20 s.","Università degli Studi di Padova  \nDEPARTMENT OF INFORMATION ENGINEERING  \nAutomatic detection of knots and wood logs classification using machine learning  \nAdvisors  \nProf. Pietro Zanuttigh  \nCandidate :  \nMarian Ashaq  \nCompany Tutor :  \nEnrico Ursella  \nAcademic Year: 2022 / 2023  \nAcknowledgement  \nFirstly, all praise to God, the absolute source of knowledge and wisdom. Secondly, I would like to express my deepest gratitude to my academic supervisor Prof. Pietro Zanuttigh and my supervisor from Microtec Company Enrico Ursella, for their direct supervision, continuous help, constant guidance and valuable Advice that have greatly contributed in achieving these results. Thirdly, I also want to express my gratitude to my family especially my husband and my parents for their continuous encouragement and patience throughout my master studies at Padua University. Finally, many thanks to teaching assistantsand professors at Padua University who helped us since our first days at Padova  \nUniversity till graduation.  \nAbstract  \nThese days the world is suffering shortage in some natural resources such as wood. There are two possible solutions to solve this problem. One possible solution is to maximize the usage and the other is to reduce the rejection losses. The process to maximize the value of wood is mainly depending on defects detection and then grading based on type and severity of these defects. For example, these defects could be knots, cracks or mildew.  \nOne widely studied topic in machine vision applications is timber defects detection. To illustrate, the number and the dimensions of knots in each wood log determine its quality and consequently its price. In this project, we propose a method for detection of knots and classification of wood logs based on the number and dimensions of defects detected in each wood log. Firstly, we read all information about knots that were detected in each wood log using CT Log scanner. Then, this information was used to compute the distance between each knot and the surface. Thirdly, Cartesian coordinates were converted into polar coordinates. After that, all images were cropped into several crops in order to artificially enlarge our dataset. As a fifth step, scores were given to each wood log crop based on the number and the dimensions (radius) of knots found in each wood log crop. Then, crops were classified into two classes before processing by the deep learning algorithm where class zero represents crops with almost no knots whereas class one represents crops with many knots. Finally, crops were categorized using a classification threshold.  \nThe proposed algorithm was evaluated using accuracy, precision and recall. The experimental results showed that our method achieved a precision of 0.96 and 0.90 , and a recall of 0.98 and 0.94 for crops from both classes (zero and one) respectively.  \nIn conclusion, by using this improved deep CNN model, we achieved an overall accuracy of 0.96, 0.94, 0.95 on training, test and validation sets respectively; that is, only 1.20 s was needed for both detection (image pre-processing and identification) and wood log crops classification. These results showed that the proposed CNN model could recognize knots and classify wood logs more accurately and effectively than conventional methods while using CT Log images.  \nList of Figures  \nFigure 2.1 Graph partitioning………………………………………………………………… 5  \nFigure 2.2 PCA feature fusion steps…………………………………………………………. 7  \nFigure 2.3 Linear and kernel SVM …………………………………………………………... 8  \nFigure 2.4 The process of online classification method……………………………………… 10  \nFigure 2.5 Schematic representation explaining main steps of the proposed method ……….. 11  \nFigure 2.6 Estimated dependence of knot probabilities on the pixel intensities of virtual 12  \nimages……………………………………………………………………………...  \nFigure 2.7 Three types of internal defects…………………………………………………….. 13  \nFigure 2.8 Dataset used in DCNN……………………………………………………………. 14  \nFigure 2.9 St","cbCaiip6axHfFA7V","https://ap.wps.com/l/cbCaiip6axHfFA7V","pdf",6425238,1,97,"English","en",105,"# Abstract\n## Objective and problem motivation\n## Proposed method pipeline\n## Dataset expansion and scoring\n## Deep learning classification and thresholding\n## Experimental evaluation and results\n## Conclusion\n# List of Figures\n## Figures 2.1-2.10\n## Figures 3.1-3.11\n## Figures 4.1-4.10","[{\"question\":\"What problem does the project address?\",\"answer\":\"The project tackles wood shortage by improving how timber defects are detected and graded, since defect types and severity determine quality and price.\"},{\"question\":\"How are knots detected and used for classification?\",\"answer\":\"Knot information is read from CT Log scanner outputs, distances to the surface are computed, and coordinates are transformed before cropping and scoring each wood-log crop by knot number and radius.\"},{\"question\":\"What results were achieved and how fast is the approach?\",\"answer\":\"The method reports high precision and recall for both classes and reaches an overall accuracy around 0.96/0.94/0.95 on training, test, and validation sets, with about 1.20 s needed for detection and classification.\"}]","Automatic detection of knots and wood logs classification using machine learning | PDF",1785672432,244,{"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},"automatic-detection-of-knots-and-wood-logs-classification-using-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/automatic-detection-of-knots-and-wood-logs-classification-using-machine-learning/116910/",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 project address?","Question",{"text":75,"@type":76},"The project tackles wood shortage by improving how timber defects are detected and graded, since defect types and severity determine quality and price.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are knots detected and used for classification?",{"text":80,"@type":76},"Knot information is read from CT Log scanner outputs, distances to the surface are computed, and coordinates are transformed before cropping and scoring each wood-log crop by knot number and radius.",{"name":82,"@type":73,"acceptedAnswer":83},"What results were achieved and how fast is the approach?",{"text":84,"@type":76},"The method reports high precision and recall for both classes and reaches an overall accuracy around 0.96/0.94/0.95 on training, test, and validation sets, with about 1.20 s needed for detection and classification.","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"]