مسار بولونيا
EN

سجاد هلال كمر كرم الموسوي

السنة عنوان البحث نشر البحث
2026 Estimating a High-resolution Image from a Single Low-resolution Image, Using Deep Learning Algorithm مجلة جامعة الكوت
Single-image super-resolution (SISR) is an advanced and highly significant technique in computer vision and artificial intelligencefields. It aimsto reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts, presentingconsiderable challenges due to the loss of fine details during image downscaling. Applications of SISR range from medical imaging and satellite imagery toconsumer photography and video streaming. Over recent years, the advent of deep learning has revolutionized the SISR domain, with convolutional neural networks (CNNs) emerging as the most promising approach. These networks have demonstrated remarkable accuracy, outperforming traditional image processing methods.This paper focuseson the Very Deep Super-Resolution (VDSR) model, a specialized CNN architecture designed to improve the quality of single-image super-resolution. VDSR excels by learning the intricate relationships between low-and high-resolution images, particularly the mapping of the high-frequency details lost in LR images. This capability is achieved through a deeper network structure and the use of residual learning, which facilitates faster convergence and enhances performance. The paper conducted experiments to estimate HR images from LR inputs using the VDSR model and compared the results with traditional methods such as bicubic interpolation.The findings revealthat the VDSR model delivers superior performance, producing HR images with greater accuracy and preserving finer details compared to bicubic interpolation. These results highlight the potential of VDSR in real-world applications where high-quality image reconstruction is critical. This study underscores the ongoing importance of deep learning in addressing challenges in SISR and paves the way for further advancements in the field.Keywords:High-resolution images,Super-resolution techniques, Deep learning, Network training, Low-resolution imagesandBicubic interpolation.