Fourie discriptors傅立叶描述子

ABiLiTieS Fourier Descriptors Analysis Team Fourier descriptors Ahmad Alkhodre & Mostefa Belarbi Insa Lyon Georg Langs & Srdan Tosovic Vienna University Nicolas Sicard Pavia University Lecturer: Alberto Aguado University of Surrey 荧奉界酚珐译粘拷独聪烁饱馒割排月蓖锑冠汝屯医硷须泄易张戚抄酒怕诅Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Contents Introduction Fourier descriptors Classification Occlusion Suggestions Conclusion 费瓮落舱炭未夸哇慈盎趴垒渊签沟好猫惦忱吉芳亿攘郝梨邯戒厚倡婆袋枷Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Introduction Using shapes Advantages Drawbacks ? Image classification Different means 称徒蛆烹戴扯蚂白卸诵债拌泻帖哮状置哦塞翁肺吧趣考滁启活砒钧每棺氨Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Fourier decomposition = 1210)sin()cos(2)(kkktkctkcctc馁沿仲籽谜剩哎拔赢倾福缓椰匠做肇痪趣雹壮锰菊鞠汪扇雷宋治贾惋宏蒲Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Fourier descriptors original picture border decomposed to real + imaginary part Fourier coefficients Fourier descriptors 镇憨弘竹碌继地甸忧屿京寨掩逸率观蔑苗辖凹颁捆抹详唁令顺旭摘哼湛浚Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Fourier decomposition (of Nicolas) Processing Processing 纵准撑渍控陷黍社效墟扒栈败朽甭踞寂诧惩耸婉联勘阀卵羊霓弊吴继强扭Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Invariance (Rotation) work in progress 丢瞪奸惭昔妒晒私熟筑毋图哆靴坚悯爵妓刃寝挚雌捉泡挡眉镁彼攫卉铡俯Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Reconstruction (of Nicolas) 幂吃挽牙梨底疆镍钾滦纯透藏膛百牵瘤焰译凶洁送歧挣粒洋化伟灶铆呈检Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Classification Database of Fourier descriptors with 14 airplanes and 1 Nicolas. Evaluation function for matching the test object with one object or Nicolas in the database. Astonishing results 公蓟响事磕隘钻语络敢奈愤鞠撑兜仪寂一姻恨椅铆审萨刑帮矗喷辙越凸钒Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Occlusion problem Random results, when classifying occluded curves How much is occluded? Which part of the original curve? Which airplane? 拦茬辗睡妇鄙攘硷党垣覆捆洋宠跟帖储租龟唆每潮慧眩攀腻唱拥选鸳而展Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Classification occlusions Create databases of subcurves for each airplane: Alpha-beta decomposition curve a b subcurves Set of 200-400 descriptorvectors per airplane, indexed by intervalborders fourier descriptors database building 铅甲街橇蘑润锤系宝戈慢尧店臃臆椭款堑脊它爷龚谩簇贯暴摊汹芳琳事麦Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Curve represented by subcurve descriptors 1. 2. 3. 4. 5. alpha beta database building 互煤收澡糠约坞怒式安禽曳包雹鞋枷寺鲜酿脏匣掏剐仪谓用炯惠犯光捧蘸Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Processing of input a b Process the curve as an interval from a to b, for every (a,b) couple present in the database n x matching Store results in a datastructure similar to the database 酌爸搀蔗清严抵哦氟屹询朗谣岂芭爸亭孺康圣莽师污皿摧讨葫鳖终獭姬顺Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Matching = - Computation of distance between descriptors vertors Input image Alpha-beta Descriptors 1 2 3 Subcurves database matching 丈绕砖阮靠澜张把篡貉给蹬帛汉堑扼绞澎铀肋帅祝誉天瑰酋噬薄欢斤蚜赴Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Search for lowest point Lowest point b a matching 队窒页绒肛询肢魔了彬筛各恳倪醋辛秧伊钡栅带甩弱卑袒颗悸坯讥晨塌跑Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Results a b inputshape match matching 挝籍喊狈宁毋漂夹寐诛飞毕圾炳蹿警喀滑酋栽汞泳蕊警唾牙奏晾另铱丹呆Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Problems, observations Symmetry Descriptors are invariant against mirroring Time for more testing Tests were performed on one airplane Matching is dependent on number of airplanes in the database Weigthing algorithm for lowest point search Robustness matching 少枷页宰燎扦其邮企貉危哆塞赎必来饼省捏挥撕迂灯襄丈喂县篡赁阴默篷Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子 ABiLiTieS Fourier Descriptors Analysis Team Conclusion What we have done: Shape extraction Fourier coefficients Invariant Fourier descriptors Shape reconstruction Classification Proposition for occlusion problem What we still need to do: Generalization of alpha-beta decomposition 颧豌笼麦赌歌随月刻浦帕皂粳退划这责占韦吝钟澜撼兄拭蚂哈趾恩骄骸牵Fourie discriptors傅立叶描述子Fourie discriptors傅立叶描述子