Perancangan Aplikasi Perbaikan Citra Digital Pada Hasil Screenshot Dengan Menggunakan Metode Multiscale Retinex dan Median Filter

Abstract

Advances in technology today cannot be kept away from people's lives, because basically technology is built to provide convenience to the community. One example is in the field of digital images, digital images are a representation of the light intensity function in a discrete field in a two-dimensional plane, digital images can also be a source of information other than text, sound and video. However, sometimes the image can also experience a decrease in quality caused by noise, too contrasting colors, blurring, and so on. A distorted image is usually caused by poor image capture, poor lighting, low pixel resolution on the camera, and poor image capture capabilities. This is what underlies the improvement in digital images, digital image quality improvements can be done by various methods, one of which is the Multiscale Retinex and Median Filter methods. The advantages of the Multiscale Retinex method are that it can increase the brightness and color of digital images, especially those that tend to be dark, and the Median Filter method can reduce the disturbance that often occurs in digital images, namely noise. With the two methods used to improve the image, a digital image will look better with a degree and level of color that tends to be evenly distributed. The process begins by entering the test image with *.jpg file format into the program then processed by the Multiscale Retinex and Median Filter methods, then the initial image can be compared with the resulting image using a histogram. From the research that the author did, it resulted in a digital image processing application that can improve brightness and reduce noise in digital images.