Visvesvaraya Technological University, Belagavi, Karnataka, India.
Department of ECE, Sapthagiri College of Engineering Bengaluru, Bangalore, Karnataka, India.
Sci Rep. 2023 Jan 17;13(1):872. doi: 10.1038/s41598-023-27838-3.
With the advancement of technology in image capturing, people are accustomed to high-resolution images. One of the primary necessities of an image capturing system is to provide the same. However, in many cases, the image resolution may not be reaching the expectations of the user which leads to a decrease in user experience. This is a common phenomenon that occurs when the images are captured in low light or if the image encounters a distortion either because of lack of exposure or the image capturing devices may be equipped with a small size sensor. In this work, a resolution enhancement technique using the concepts of curvelet transform and iterative back projection is presented. Sparse representation of images can be enhanced using a combination of curvelet transforms with iterative back projection. Application of curvelet transform along with iterative back projection algorithm on low light images results in enhancing the resolution of the images. The resultant images from here then passed through the inverse transform block and gives an image with contrast enhancement which leads to the user experience improvement. The antiquated image enhancement with improvement in the resolution is validated with the measurement of peak signal-to-noise ratio and structural similarity index. The usage of curvelet transform with iterative back projection leads to the restoration of the image resolution by minimizing the distortions, thus leading to an enhanced image whose edge details are retained.
随着图像采集技术的进步，人们已经习惯了高分辨率的图像。图像采集系统的主要需求之一就是提供高分辨率的图像。然而，在许多情况下，图像的分辨率可能无法满足用户的期望，从而降低了用户体验。这种情况通常发生在图像在低光环境下拍摄时，或者由于曝光不足或图像采集设备配备的传感器尺寸较小，导致图像发生失真。在这项工作中，提出了一种使用曲波变换和迭代后投影概念的分辨率增强技术。通过将曲波变换与迭代后投影相结合，可以增强图像的稀疏表示。在低光图像上应用曲波变换和迭代后投影算法，可以提高图像的分辨率。从这里得到的结果图像然后通过逆变换块，通过对比度增强来提高图像质量，从而提高用户体验。通过峰值信噪比和结构相似性指数的测量，对改进分辨率的陈旧图像增强进行了验证。通过使用曲波变换和迭代后投影，可以最小化失真，从而恢复图像的分辨率，得到边缘细节保留的增强图像。
