An exemplar-based method for improvement in image completion using Local Binary Pattern
Publish place: 2rd International Conference on Soft Computing
Publish Year: 1396
نوع سند: مقاله کنفرانسی
زبان: English
View: 504
This Paper With 9 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
CSCG02_157
تاریخ نمایه سازی: 7 اسفند 1396
Abstract:
Image restoration or completion is an issue of image processing and machine vision, in which the corrupted regions are reconstructed from safe regions. Exemplar-based completion approaches that are based on patches propose better results compared to pixel-based methods. In this paper, we introduce a novel exemplar-based algorithm to improve the image reconstruction or completion. The proposed method include two kinds of changes. Firstly, the patches texture features are extracted (computation of the local binary algorithm). Secondly, the search region is limited with the purpose of computational complexity reduction and improvement in algorithm operation. The obtained results depict that this approach for improvement in quality of exemplar-based method is efficient
Keywords:
Authors
Zahra Ahmadi
M.S.c student, Azad University, Buein Zahra Branch
Abbas Koochari
Assistant professor, Azad University, Science and Research Branch