{"title":"A CNN-based framework for 2D still-image segmentation","authors":"G. Iannizzotto, P. Lanzafame, F. L. Rosa","doi":"10.1109/CAMP.2005.3","DOIUrl":null,"url":null,"abstract":"When strong CPU power consumption constraints must be met, and high computation speed is mandatory (realtime processing), it can be preferable to adopt custom hardware for some computationally intensive image processing tasks. An alternative approach to conventional approaches is provided by the Cellular Neural Network (CNN) paradigm. CNNs have been extensively used in image processing applications: in the past, we developed a still image segmentation technique based on an active contour obtained via single-layer CNNs. This technique suffered from sensitivity to noise as most of edge-based methods: noise may create insignificant false edges or determine some \"edge fragmentation\". The aim of this paper is to re-formulate the algorithm previously proposed in order to step-over the cited weakness. The new formulation is introduced and justified and experimental results are presented. Finally, a competition-based approach for a parameterless version of the presented algorithm is proposed and discussed as an ongoing work.","PeriodicalId":393875,"journal":{"name":"Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2005-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CAMP.2005.3","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
When strong CPU power consumption constraints must be met, and high computation speed is mandatory (realtime processing), it can be preferable to adopt custom hardware for some computationally intensive image processing tasks. An alternative approach to conventional approaches is provided by the Cellular Neural Network (CNN) paradigm. CNNs have been extensively used in image processing applications: in the past, we developed a still image segmentation technique based on an active contour obtained via single-layer CNNs. This technique suffered from sensitivity to noise as most of edge-based methods: noise may create insignificant false edges or determine some "edge fragmentation". The aim of this paper is to re-formulate the algorithm previously proposed in order to step-over the cited weakness. The new formulation is introduced and justified and experimental results are presented. Finally, a competition-based approach for a parameterless version of the presented algorithm is proposed and discussed as an ongoing work.