<![CDATA[In conducting research, there are often obstacles to supporting media to support the observations and experiments under study. Especially in the case of research involving photos, not a few quality problems that use cameras show results that are not ideal, such as dimness, disturbing-colored dots, or other disturbances. In line with the rapid development of technology today, these problems can be overcome by computer programming through the Opensource Computer Vision Library (OpenCV). OpenCV is a programming module that contains various features, one of which is improving image quality with super-resolution. In practice, photos that have low quality will be enhanced using the efficient subpixel convolutional neural network (ESPCN) model. The deep learning algorithm used is a convolutional neural network (CNN) to support the testing means. CNN works to obtain the percentage accuracy of the photos under study as a representation of the final test results. This test aims to improve the low quality of photos with the ESPCN model to compare the accuracy with the original photos. The test result is the application of ESPCN to low-quality photos. The test result is higher accuracy than the original photo with a difference of 1.2%. The original photo had an accuracy of 90.6%, while the enhanced photo had an accuracy of 91.8%. The final result shows that low-quality photos can be upscaled using ESPCN to produce better accuracy.]]>
Copyrights © 2023
