A study on seal imprints segmentation and repair for traditional painting

• Main Authors: Chiang Meng-lin, 江孟霖
• Other Authors: Wang Ching-lin
• Format: Others
• Language: zh-TW
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/75488405900201436280

碩士 === 國立勤益科技大學 === 研發科技與資訊管理研究所 === 100 === From 2002 year, Taiwan promoted the e-Learning &; Digital Archives Program to save the precious cultural relics. Be achieved the digital preservation and value-added application. Traditional paintings carrying out digital preservation work, through artificial way to cut the seal imprint in the traditional paintings. It will waste a lot of manpower and time. If we can cut the seal imprint by using automatic way, then we can increase efficiency of digital preservation process. However, the seal related research most focus on personal seals or bank stamps. Only few scholars have mentioned that cutting seal issues on traditional paintings. We based on technology development and innovation to present the algorithm in Digital Archives field. The algorithm of seal segmentation can automatic to capture two type of eigenvalue of seal and to find the location of seal imprint. It is not only applies to all kinds of different types of paintings, but also reduces the computational time. Maintain the efficiency of a large number of captured images.