Artificial Intelligence

Single image super-resolution (SISR) is a common and challenging vague problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions. To solve the SISR problem, recently powerful deep learning algorithms have been employed and achieved the state-of-the-art performance. Diagram showing Super Resolution The end goal is to recover the high resolution image, which one can resample depending on the input images and imaging model. It is very important for the imaging model for the super resolution to be accurate. An incorrect modeling can degrade the image quality. Deep learning can be easily applied to perform the Super resolution rather than using the traditional approach of using images from multiple cameras or video sequence. Applications of Super Resolution A high resolution image is of utmost importance in the field of medical imaging for diagnosis of any healthy issues. Other fields requiring the execution of super resolution imaging incl

Facial recognition technology was a part of the science fiction genre. This technology not only became a reality but also is widespread. It is difficult to read technology news without seeing something posted about face detection . Different industries are benefiting from this technology including law enforcement agencies, retailers, airports, and smartphone companies. When Did Facial Technology Come Into Existence? - The Brief History Facial technology has been under development for many decades. We will share a brief history of how this technology came into existence. 1. Manual Measurement (1960s) Woodrow Wilson Bledsoe develops the RAND tablet system, which could manually record the coordinate locations of facial features including eyes, nose, mouth, and hairline. 2. The 21 Markers (1970s) Goldstein, Harmon, and Lesk add accuracy to the manual facial recognition system in the 1970s with 21 specific markers to identify faces. 3. EigenFaces (1980-1990) Sirovich and Kirby apply line