Study on Damaged Region Segmentation Model of Image
After studying the damaged region classification of Thangka image, and in light of the specific damaged situation, as for damaged region can be segmented accurately and the advantages of different image segmentation algorithms can be full played, it is proposed a damaged region segmentation model of image. Model integrates different image segmentation algorithms, the system can segment damaged regions using different algorithms according to the feature of the image damaged regions, so it can avoid looking for universal algorithms for segmenting image damaged regions. For the image segmentation results, it is needed to evaluate through by segmentation evaluation, at the same time, considering the error segmented region condition, here subjective evaluation is introduced in the model. The system selects algorithm, and the results of the evaluation and so on, these features are stored in the information database of image segmentation, decision-making module analysis and learning continually, and will optimize all types of segmentation algorithm in the information database. Decision-making module can make use of the historical information to guide the image damaged region segmentation, increase system segmentation efficiency and accuracy.
the image damaged region image segmented decision-making module the segmentation model
Huaming Liu Yun Chen Xuehui Bi
Computer and information school,Fuyang Normal College,Fuyang, Anhui province, China
国际会议
厦门
英文
678-681
2010-10-29（万方平台首次上网日期，不代表论文的发表时间）