Single Image Super resolution
1. INTRODUCTION
Obtaining a high-resolution (HR) image from single or multiple low-resolution (LR) images, known as “super-resolution” has been a problem. High resolution means high pixel density, also referred to as high-definition (HD). An HR image brings out details that would be blocked out in an LR image. More pixels in the same area imply a higher sampling frequency thereby offering more details. Due to the tremendous progress in sensor and chip manufacturing techniques, we can now obtain high resolution images from a high-end camera without any postprocessing. However, there is still a demand for increasing the resolution of images obtained using the current technology in certain applications such as medical imaging, satellite imaging, and computer vision. In some applications, it is infeasible to install high-end cameras (e.g. cell phones, surveillance cameras). Hence, increasing the resolution of an LR image is quite an active area of research.
Super-resolution is the task of obtaining a high-resolution image of a scene given low resolution image(s) of the scene. Applications of super-resolution include forensic, satellite, medical imaging, surveillance, displaying video on large screens, etc. Obtaining high-resolution images directly via better hardware (better image sensors, larger chip size) is quite costly.
Furthermore, most of the smart-phones today would be hard-pressed to incorporate hardware enhancements for achieving high resolution images. Hence, a signal processing approach to increase the resolution of images obtained from the phone camera is desirable.
Image interpolation methods are not considered as super-resolution methods since even the ideal sinc interpolation cannot recover the high frequency components that are lost in the low-resolution sampling process. Most of the super-resolution approaches work on the principle of combining multiple slightly-shifted low-resolution images of the scene. This involves image
Obtaining a high-resolution (HR) image from single or multiple low-resolution (LR) images, known as “super-resolution” has been a problem. High resolution means high pixel density, also referred to as high-definition (HD). An HR image brings out details that would be blocked out in an LR image. More pixels in the same area imply a higher sampling frequency thereby offering more details. Due to the tremendous progress in sensor and chip manufacturing techniques, we can now obtain high resolution images from a high-end camera without any postprocessing. However, there is still a demand for increasing the resolution of images obtained using the current technology in certain applications such as medical imaging, satellite imaging, and computer vision. In some applications, it is infeasible to install high-end cameras (e.g. cell phones, surveillance cameras). Hence, increasing the resolution of an LR image is quite an active area of research.
Super-resolution is the task of obtaining a high-resolution image of a scene given low resolution image(s) of the scene. Applications of super-resolution include forensic, satellite, medical imaging, surveillance, displaying video on large screens, etc. Obtaining high-resolution images directly via better hardware (better image sensors, larger chip size) is quite costly.
Furthermore, most of the smart-phones today would be hard-pressed to incorporate hardware enhancements for achieving high resolution images. Hence, a signal processing approach to increase the resolution of images obtained from the phone camera is desirable.
Image interpolation methods are not considered as super-resolution methods since even the ideal sinc interpolation cannot recover the high frequency components that are lost in the low-resolution sampling process. Most of the super-resolution approaches work on the principle of combining multiple slightly-shifted low-resolution images of the scene. This involves image