{"title":"Real time VLSI implementation of a fast split and merge segmentation algorithm","authors":"Pradipta Roy, Dipak Das, P. Biswas","doi":"10.1109/ICCIC.2012.6510209","DOIUrl":null,"url":null,"abstract":"In this paper, we propose a VLSI implementation scheme for region split and merge image segmentation. Region splitting is done using a parallel pixel network. We propose a modified merging criterion to reduce the execution time and corresponding hardware implementation is also proposed. We have shown the modified merge criterion will reduce the number of merging iteration steps. Implementation results are encouraging as the processing time in hardware with a 100MHz clock in XILINX VIRTEX IV FPGA is achieved a few order lower than the software implementation.","PeriodicalId":340238,"journal":{"name":"2012 IEEE International Conference on Computational Intelligence and Computing Research","volume":"34 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2012-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2012 IEEE International Conference on Computational Intelligence and Computing Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCIC.2012.6510209","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
In this paper, we propose a VLSI implementation scheme for region split and merge image segmentation. Region splitting is done using a parallel pixel network. We propose a modified merging criterion to reduce the execution time and corresponding hardware implementation is also proposed. We have shown the modified merge criterion will reduce the number of merging iteration steps. Implementation results are encouraging as the processing time in hardware with a 100MHz clock in XILINX VIRTEX IV FPGA is achieved a few order lower than the software implementation.
本文提出了一种区域分割与合并图像分割的VLSI实现方案。区域分割是使用并行像素网络完成的。我们提出了一种改进的合并准则以减少执行时间,并提出了相应的硬件实现方案。我们已经展示了修改后的合并准则将减少合并迭代步骤的数量。实现结果令人鼓舞,在XILINX VIRTEX IV FPGA中使用100MHz时钟的硬件处理时间比软件实现时间低几个数量级。