{"title":"Image Inclination Measurement Based on Edge Directions and an Analysis of Relation between Visual Inclination","authors":"Hidekazu Ohmi, F. Saitoh","doi":"10.1541/IEEJEISS.124.112","DOIUrl":"https://doi.org/10.1541/IEEJEISS.124.112","url":null,"abstract":"This paper proposes a method to measure the inclined angle of an objective image based on the most frequent edge direction. This paper also describes a relation between the measured inclined angles by the proposal method and the visual inclined angles. An edge direction is changed according to the inclination of an objective image. The most frequent edge direction is supposed to show the global inclination of the image. The proposed method measures the inclined angle of the image by detecting the edge direction with the peak in the histogram that represents the distribution of all edge directions in the image. The experimental results show that the measured inclined angles by the proposed method were similar to the visual inclined angles evaluated by the subjects.","PeriodicalId":295384,"journal":{"name":"IAPR International Workshop on Machine Vision Applications","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116803647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Components Recognition by the Generalized Hough Transform Using Multiple Two-dimensional Parameter Spaces","authors":"F. Saitoh","doi":"10.2493/JJSPE.62.1577","DOIUrl":"https://doi.org/10.2493/JJSPE.62.1577","url":null,"abstract":"The generalized Hough transform is a method for extracting similar figures to the template figure in an image. The generalized Hough transform needs huge memory for the fourdimensional parameter space which represents positions, scales and rotation angles of objective figures and requires processor power for conversing addresses from an image space into the parameter space. The paper proposes a method using multiple two dimensional parameter spaces for reducing the volume of the parameter space and for performing high speed processing. As the experimental result, the method provided high rate repeatability on the position, the scale and the rotation angle of extracted figures and performed short processing time.","PeriodicalId":295384,"journal":{"name":"IAPR International Workshop on Machine Vision Applications","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125098855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-time Soft Shadows in Mixed Reality Using Shadowing Planes","authors":"Tetsuya Kakuta, Takeshi Oishi, K. Ikeuchi","doi":"10.1007/978-0-387-75807_22","DOIUrl":"https://doi.org/10.1007/978-0-387-75807_22","url":null,"abstract":"","PeriodicalId":295384,"journal":{"name":"IAPR International Workshop on Machine Vision Applications","volume":"65 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123522142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
H. Doi, Y. Hara, K. Karasaki, Tadashi Iida, T. Furutani, Shigeki Kitamura, Norihiro Minatani, Satashi Shinada
{"title":"Automated Inspection of Printed Circuit Board Patterns Referenced to CAD Data","authors":"H. Doi, Y. Hara, K. Karasaki, Tadashi Iida, T. Furutani, Shigeki Kitamura, Norihiro Minatani, Satashi Shinada","doi":"10.2493/JJSPE.59.993","DOIUrl":"https://doi.org/10.2493/JJSPE.59.993","url":null,"abstract":"Automated detcct~on of defects !n pr~nted circuit board ,,,, c~~~~~~ allgnm~nt Combarrurn I~gnsl% c~rcu~rs <lrtw~tr / patterns fnr mainframe computers is accomplished by a lystcm which compares PCB pattern< with correrponding CAD data. High speed fluorescence detectlon is achieved, using highly efficient fiber optic illumination. A ~impltfied reconstruction technique provtdes preciw images. A binarbzarion meihod that uses maximum and minimum derection along wi~h constant hinariraiton allow? detection of narrow cut.; and thin shorts. A bit pattern generator produces a bitrn;ippzd design data image from vector format CAD data. A partlrinn~ng and dividing technique reduces the design dara imegc lo flner hi1 irnapes ro hc adapted lo thosc detected by h~ur acquisirion system. To nvercorne thc rnevitahlc distortlons In PCBs, stretched or contracted patterns are carnpensated hy dynamically changing prxeI sire. A propo~ed defect c. ,~l,atity . recognition technique examinea not only defect rlze. hut alro ihe i-elationqhip wtih nearhy pnttems. As a rewlr, only hiltd~ l clcfect G are recognized ar defecta. Fatality rs recognized asynchronously in u stand-done ~rnage processor. so it does not waste inspection lime. This state-ot-the-an automated inxpection Fyqtem can dctect short circuiis ax rrnall as 7pm wirle in 4.5 min. on a MX)xHWmm PCB. P11nt.d C~rturt BoardPattem~","PeriodicalId":295384,"journal":{"name":"IAPR International Workshop on Machine Vision Applications","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117156330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Tracking Multiple Pedestrians in Crowd","authors":"Kyousuke Uchida, J. Miura, Y. Shirai","doi":"10.5687/ISCIE.14.180","DOIUrl":"https://doi.org/10.5687/ISCIE.14.180","url":null,"abstract":"In the domain of city design, the demand for the development of the visual tracking method is increasing, which provides the pedestrian paths. This paper proposes the tracking method which reduces the ambiguity of matching. When features of a pedestrian are ambiguous in the original image, the proposed method generates plural candidates for the pedestrian path. In the following frames the proposed method veri es them to eliminate false ones. We experiment on real image sequences.","PeriodicalId":295384,"journal":{"name":"IAPR International Workshop on Machine Vision Applications","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123812128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}