Filling techniques are often used in the restoration of images.Yet the existing filling technique approaches either have high computational costs or present problems such as filling holes redundantly.This paper propos...Filling techniques are often used in the restoration of images.Yet the existing filling technique approaches either have high computational costs or present problems such as filling holes redundantly.This paper proposes a novel algorithm for filling holes and regions of the images.The proposed algorithm combines the advantages of both the parity-check filling approach and the region-growing inpainting technique.Pairing points of the region’s boundary are used to search and to fill the region.The scanning range of the filling method is within the target regions.The proposed method does not require additional working memory or assistant colors,and it can correctly fill any complex contours.Experimental results show that,compared to other approaches,the proposed algorithm fills regions faster and with lower computational cost.展开更多
Labeling information in a complex irregular region is a useful procedure occurring frequently in sheet metal and the furniture industry which will be beneficial in parts management.A fast code-based labeler(FCBL) is p...Labeling information in a complex irregular region is a useful procedure occurring frequently in sheet metal and the furniture industry which will be beneficial in parts management.A fast code-based labeler(FCBL) is proposed to accomplish this objective in this paper.The region is first discretized,and then encoded by the Freeman encoding technique for providing the 2D regional information by 1D codes with redundancies omitted.We enhance the encoding scheme to make it more suitable for our complex problem.Based on the codes,searching algorithms are designed and can be extended with customized constraints.In addition,by introducing a smart optimal direction estimation,the labeling speed and accuracy of FCBL are significantly improved.Experiments with a large range of real data gained from industrial factories demonstrate the stability and millisecond-level speed of FCBL.The proposed method has been integrated into a shipbuilding CAD system,and plays a very important role in ship parts labeling process.展开更多
基金The research is jointly supported by the National Natural Science Foundation of China No.61561035by Ukrainian government project No.0117U007177the Slovak Research and Development Agency project number APVV-18-0214.
文摘Filling techniques are often used in the restoration of images.Yet the existing filling technique approaches either have high computational costs or present problems such as filling holes redundantly.This paper proposes a novel algorithm for filling holes and regions of the images.The proposed algorithm combines the advantages of both the parity-check filling approach and the region-growing inpainting technique.Pairing points of the region’s boundary are used to search and to fill the region.The scanning range of the filling method is within the target regions.The proposed method does not require additional working memory or assistant colors,and it can correctly fill any complex contours.Experimental results show that,compared to other approaches,the proposed algorithm fills regions faster and with lower computational cost.
基金supported by the National Natural Science Foundation of China(Nos.60873181,60673006 and 60533060)the Program for New Century Excellent Talents in University,China(No.NCET-05-0275)
文摘Labeling information in a complex irregular region is a useful procedure occurring frequently in sheet metal and the furniture industry which will be beneficial in parts management.A fast code-based labeler(FCBL) is proposed to accomplish this objective in this paper.The region is first discretized,and then encoded by the Freeman encoding technique for providing the 2D regional information by 1D codes with redundancies omitted.We enhance the encoding scheme to make it more suitable for our complex problem.Based on the codes,searching algorithms are designed and can be extended with customized constraints.In addition,by introducing a smart optimal direction estimation,the labeling speed and accuracy of FCBL are significantly improved.Experiments with a large range of real data gained from industrial factories demonstrate the stability and millisecond-level speed of FCBL.The proposed method has been integrated into a shipbuilding CAD system,and plays a very important role in ship parts labeling process.
