首页|Patent Issued for Techniques for generating training data for machine learning e nabled image enhancement (USPTO 11983853)
Patent Issued for Techniques for generating training data for machine learning e nabled image enhancement (USPTO 11983853)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Meta Plattforms Inc. (Menlo Park, Cali fornia, United States) has been issued patent number 11983853, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent’s inventors are Ozgirin, Ege (Cambridge, MA, US), Shen, Liying (Charl estown, MA, US), Yang, Haitao (Boston, MA, US), Zhu, Bo (Charlestown, MA, US). This patent was filed on November 2, 2020 and was published online on May 14, 20 24. From the background information supplied by the inventors, news correspondents o btained the following quote: “Images (e.g., digital images, video frames, etc.) may be captured by many different types of devices. For example, video recording devices, digital cameras, image sensors, medical imaging devices, electromagnet ic field sensing, and/or acoustic monitoring devices may be used to capture imag es. Captured images may be of poor quality as a result of the environment or con ditions in which the images were captured. For example, images captured in dark environments and/or under poor lighting conditions may be of poor quality, such that the majority of the image is largely dark and/or noisy. Captured images may also be of poor quality due to physical constraints of the device, such as devi ces that use low-cost and/or low-quality imaging sensors.
NETL
NSTL
