CASPIAN JOURNAL
MANAGEMENT AND HIGH TECHNOLOGIES
RESEARCH ON APPLICATION OF NEURAL NETWORKS FOR RESTORING DAMAGED VIDEO FILES OF AVI AND MP4 FORMATS
 |
Read | Geraskin Aleksey S., Ukolov Rodion V. RESEARCH ON APPLICATION OF NEURAL NETWORKS FOR RESTORING DAMAGED VIDEO FILES OF AVI AND MP4 FORMATS // Caspian journal : management and high technologies. — 2021. — №3. — pp. 25-32. |
Geraskin Aleksey S. - Saratov State University, gerascinas@mail.ru
Ukolov Rodion V. - Saratov State University, trustgreen1@mail.ru
In the modern world, video files play a special role. The development of video compression algorithms and the growth of the Internet’s capabilities make it possible to transfer video files. Damage inevitably occurs when transferring video files. Accordingly, the question arises about restoring a damaged file and obtaining information from it. The article discusses the most commonly used video file extensions AVI, MP4. As a result of the study, it was revealed that the most common damage is in the headers, which leads to errors when opening files by players, data is damaged less often. Data corruption leads to the fact that a certain fragment of the video file is either played with errors, distortions, or is skipped. The article discusses the possibility of recovering damaged video file using the removal of undistorted data and proposes an algorithm for analyzing frames using a neural network. As part of the algorithm, a neural network is used to identify damaged frames in video data. The algorithm was implemented as a software product. For the first stage of checking the efficiency of the algorithm, deliberate distortions of one frame were made for each video file under study. As a result of experimental verification of the developed algorithm, it was revealed that it provides high accuracy in detecting distorted frame sequences.
Key words: neural network, editing, data area of the video file, pasting into the video file, gluing the video file, clipping from the video file