[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-427474-105":59,"doc-detail-427474-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","a-visual-vocabulary-for-flower-classification","A Visual Vocabulary for Flower Classification","","The paper studies how “bag of visual words” models can separate flower categories that look visually similar while still allowing substantial within-class variation. A nearest-neighbor classifier is developed and optimized using vocabularies that explicitly encode the distinguishing aspects of flowers: colour, shape, and texture. Vocabulary selection and combination are tuned on a validation set. Experiments on 1,360 images across 17 species show strong performance, exceeding baseline methods that rely on colour cues alone.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/a-visual-vocabulary-for-flower-classification/427474/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/a-visual-vocabulary-for-flower-classification/427474.png","ImageObject",300,407,{"name":92,"@type":93},"Muffet","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-09","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":19},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address in flower classification?","Question",{"text":112,"@type":113},"It examines how to classify flower categories that are visually similar in challenging real-world conditions such as viewpoint, scale, illumination changes, occlusions, and cluttered backgrounds.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed method represent flower appearance?",{"text":117,"@type":113},"It builds separate visual vocabularies for colour, shape, and texture, quantizes each representation into visual words, and models each aspect using histograms.",{"name":119,"@type":110,"acceptedAnswer":120},"How is the classifier evaluated and what metric is used?",{"text":121,"@type":113},"A ranked-list evaluation is used, optimizing a shortlist-based performance cost so correct categories appear within the top-n hypotheses, supporting retrieval-style use cases.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},427474,1791074215,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":19,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":46},962090768927,"https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45","A Visual Vocabulary for Flower Classification  \nMaria-Elena Nilsback and Andrew Zisserman Robotics Research Group, Department of Engineering Science University of Oxford, United Kingdom  \nmen,[az@robots.ox.ac.uk](az@robots.ox.ac.uk)  \nAbstract  \nWe investigate to what extent ‘bag of visual words’ models can be used to distinguish categories which have significant visual similarity. To this end we develop and optimize a nearest neighbour classifier architecture, which is evaluated on a very challenging database of flower images. The flower categories are chosen to be indistinguishable on colour alone (for example), and have considerable variation in shape, scale, and viewpoint.  \nWe demonstrate that by developing a visual vocabulary that explicitly represents the various aspects (colour, shape, and texture) that distinguish one flower from another, we can overcome the ambiguities that exist between flower categories. The novelty lies in the vocabulary used for each aspect, and how these vocabularies are combined into a fi nal classifier. The various stages of the classifier (vocabulary selection and combination) are each optimized on a validation set.  \nResults are presented on a dataset of 1360 images consisting of 17 flower species. It is shown that excellent performance can be achieved, far surpassing standard baseline algorithms using (for example) colour cues alone.  \n1. Introduction  \nThere has been much recent success in using ‘bag of features’ or ‘bag of visual words’ models for object and scene classification [1, 3, 5, 7, 14, 15, 17] . In such methods the spatial organization of the features is not represented, only their frequency or occurrence is significant. Previous work dealing with object classification has focused on cases where the different object categories in general have little visual similarities (e.g. Caltech, 101), and models have tended to use off-the-shelf features (such as affineHarris [12] detectors with SIFT [10] descriptors) .  \nIn this paper we investigate whether a carefully honed visual vocabulary can support object classification for categories that have a significant visual similarity (whilst still maintaining significant within-class variation) .  \nTo this end we introduce a new dataset consisting of different flower species. Classifying flowers is a difficult task even for humans– certainly harder than discriminating a car from a bicycle from a human. As can be seen from the examples in figure 2, in typical flower images there are huge variations in viewpoint and scale, illumination, partial occlusions, multiple instances etc. The cluttered backgrounds also makes the problem difficult as we risk classifying background content rather than the flower itself. Perhaps the greatest challenge arises from the intra-class vs inter-class variability, i.e. there is a smaller variation between images of different classes than within a class itself, and yet subtle differences between flowers determine their classification. In figure 1, for example, two of the flowers belong to the same category. Which ones?  \nBotanists use keys [6], where a series of questions need to be answered in order to classify flowers. In most cases some of the question are related to internal structure that can only by made visible by disecting the flower. For a visual object classification problem this is not possible. It is possible however to narrow down the choices to a short list of plausible flowers. Consequently, in this work as well as using the standard classification performance measures, we also use a measure on whether the correct classification is achieved within the top n ranked hypotheses. Measures of this type are very suitable for page based retrieval systems where the goal is to return a correct classification on the first page, but not necessarily as first ranked.  \nFigure 1 . Three images from two different categories. The left and right images are both dandelions. The middle one is a colts’ foot. The intra-class variation between the two images ","cbCaivAKzZLNQYfE","https://ap.wps.com/l/cbCaivAKzZLNQYfE","pdf",1363908,"English","# Introduction\n## Overview and performance measure","[{\"question\":\"What problem does the paper address in flower classification?\",\"answer\":\"It examines how to classify flower categories that are visually similar in challenging real-world conditions such as viewpoint, scale, illumination changes, occlusions, and cluttered backgrounds.\"},{\"question\":\"How does the proposed method represent flower appearance?\",\"answer\":\"It builds separate visual vocabularies for colour, shape, and texture, quantizes each representation into visual words, and models each aspect using histograms.\"},{\"question\":\"How is the classifier evaluated and what metric is used?\",\"answer\":\"A ranked-list evaluation is used, optimizing a shortlist-based performance cost so correct categories appear within the top-n hypotheses, supporting retrieval-style use cases.\"}]","A Visual Vocabulary for Flower Classification | PDF",1790643951]