{"type":"ScholarlyArticle","title":"Direction Coding Method And Its Application To Scene Analysis","authors":[{"name":"M. Ejirl","slug":"m-ejirl","given":"M.","family":"Ejirl","affiliation":""},{"name":"H. Yode","slug":"h-yode","given":"H.","family":"Yode","affiliation":""},{"name":"J. Motolke","slug":"j-motolke","given":"J.","family":"Motolke","affiliation":""}],"abstract":"In order to cope with image signal variations in imaging devices, a direction coding method is proposed for stable scene analysis and object recognition. This method makes extensive use of macroscopic processing of direction-coded images to achieve noise-free analysis. Examples showing recognition of obliquely-imaged box-like objects whose surfaces are rather complicated are included. Additional efforts are made to recognize surface information of objects by spatially transforming the surface image as if it were viewed from a vertical direction. This method also involves positioninvariant and rotation-invariant image data transformation techniques, thus raising the possibility of more effective image analysis in actual application.","doi":null,"url":"https://ijcai.org/proceedings/1975/97","pdf":"https://ijcai.org/proceedings/1975/0097.pdf","markdown":"https://ijcai.org/proceedings/1975/97.md","bibtex":"https://ijcai.org/proceedings/1975/bibtex/97","volume":{"slug":"1975","title":"Proceedings of the Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 1975","url":"https://ijcai.org/proceedings/1975/","year":1975,"location":"Tbilisi, Georgia, USSR","dates":"","editors":"Patrick Winston and Carl Hewitt","isbn":"","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Visual Information Processing","track":"Visual Information Processing","number":97,"pages":{"first":620,"last":626},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}