کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
4977508 | 1451927 | 2017 | 34 صفحه PDF | دانلود رایگان |
عنوان انگلیسی مقاله ISI
Robust coupled dictionary learning with â1-norm coefficients transition constraint for noisy image super-resolution
دانلود مقاله + سفارش ترجمه
دانلود مقاله ISI انگلیسی
رایگان برای ایرانیان
کلمات کلیدی
موضوعات مرتبط
مهندسی و علوم پایه
مهندسی کامپیوتر
پردازش سیگنال
پیش نمایش صفحه اول مقاله
چکیده انگلیسی
Conventional coupled dictionary learning approaches are designed for noiseless image super-resolution (SR), but quite sensitive to noisy images. We find that the cause is the commonly used âF-norm coefficients transition term. In this paper, we propose a robust â1-norm solution by introducing two sub-terms: LR coefficient sparsity constraint term and HR coefficient conversion term, which are able to prevent the noise transmission from noisy input to output. By incorporating our simple yet effective non-linear model inspired by auto-encoder, the proposed â1-norm dictionary learning achieves a more accurate coefficients conversion. Moreover, to make the coefficients conversion more reliable in the iterative process, we bring the non-local self-similarity constraint to regularize the HR sparse coefficients updates. The improved sparse representation further enhances SR inference on both synthesized noisy and noiseless images. Using standard metrics, we show that results are significantly clearer than state-of-the-arts on noisy images and sharper on denoised images. In addition, experiments on real-world data further demonstrate the superiority of our method in practice.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Signal Processing - Volume 140, November 2017, Pages 177-189
Journal: Signal Processing - Volume 140, November 2017, Pages 177-189
نویسندگان
Bo Yue, Shuang Wang, Xuefeng Liang, Licheng Jiao,