ARTIFICIAL INTELLIGENCE USED FOR VIDEO CENSORSHIP.

Abstract

The invention relates to a method that uses artificial intelligence algorithms to detect smoking scenes in videos or live broadcasts and to censor the relevant portion of the image.

Description

1 TARIFF ARTIFICIAL INTELLIGENCE USED FOR VIDEO CENSORSHIP. Technical Area The invention removes unwanted images from videos or live broadcasts (streaming). It relates to a method that enables censorship. 5 The invention specifically uses artificial intelligence to analyze smoking scenes in videos or live streams. detection by algorithms and censorship of the relevant part of the image It is related to a method that provides. State of the Art Nowadays, censoring cigarettes from videos involves removing a cigarette or cigarette smoke that appears in a video. It is the process of obscuring, concealing, or censoring the act of drinking. This process, This is done to prevent the promotion of smoking or to protect young audiences. Some digital content platforms or television channels broadcast harmful content, such as cigarette smoke. To avoid encouraging such habits in viewers, they prefer to censor these kinds of scenes. They can. Smoking censorship, especially in content watched by children and young people, is even more prevalent now. It is common. With current technology, the censorship process that takes place is based on a specialist identifying elements in a video. by identifying scenes of smoking and censoring smoking individually. This is why simultaneous censorship during a live broadcast is not possible. As a result of the research conducted on this subject, document number 2022 / 016108, “Artificial Intelligence 20 An application titled "A Supported Content Blurring and Censorship System" was found. The system displays videos of prohibited objects according to specific rules set by legal authorities. blurring of images with the help of artificial intelligence, thus reducing the visibility of images. with a system that allows the image to be censored without cutting any part of it It is related. More broadly, the system identifies 25 prohibited objects in video content. It focuses on blurring, but it's a dedicated solution for live streams. It does not offer. In conclusion, due to the negative aspects described above and the current solutions being the subject of discussion... Due to its shortcomings, an improvement is needed in the relevant technical field. It has been made. 30 2 The purpose of the invention The invention was created by drawing inspiration from existing situations and overcoming the aforementioned drawbacks. It aims to solve the problem. The main purpose of the invention is to automatically detect smoking scenes in video content. The goal is to provide an AI-based method for censoring. 5 Another purpose of the invention is to quickly and effectively remove smoking scenes from videos. a system that enables automatic censorship by defining it The goal is to offer a method. Another purpose of the invention is to automatically censor smoking scenes. Significantly more efficient, faster, and user-friendly compared to traditional methods. The goal is to develop a method that offers a user-friendly solution. This solution provides content creators with access to media. significant time and effort for companies and other video content providers This allows them to save money and make their content more ethical and appropriate. Another aim of the invention is to create a method that offers the following features together. to put: 15 - Automatic Object Recognition: The artificial intelligence model uses the dataset it has been trained on. It detects cigarette-related objects. - Fast Processing: Works quickly on each frame in the video, providing instant results. It enables censorship. - High Accuracy: 20 with high-quality object recognition algorithms and training data. It provides high accuracy in detecting cigarette smoke. - Flexibility: Due to its modular structure, it supports different video formats and It can work with various resolutions. For the purposes described above, the invention, video or publication It is a method that allows for the censorship of unwanted scenes in content. Accordingly, 25 method;  The image content intended to be censored must identify the object intended to be censored. an object recognition and censorship artificial intelligence algorithm that runs The content unit transmits the relevant images to the processing unit. 3  By looping through each frame of the image transmitted in a processing unit, images of the object to be censored and the object that has been pre-trained Recognition and censorship are analyzed using an artificial intelligence algorithm.  Object recognition and censorship artificial intelligence run via a processing unit the algorithm identifies the object to be censored and the image of that object. 5 locating its position on the relevant image frame,  Object recognition and censorship artificial intelligence run via a processing unit the algorithm's target for censorship in the relevant image frame placing blur on the image,  The content unit of the new blurred image frame created via the processing unit is 10 replacing the original content on it It includes the steps involved in the process. The structural and characteristic features and all the advantages of the invention are given in the figures below. Thanks to the detailed explanation written with references to these figures, it becomes clearer. 15 This will be understood as such, and therefore the evaluation will also take these forms and detailed explanations into account. This should be done taking that into consideration. Ways to Help Understand the Discovery Figure 1 shows a schematic of an example system in which the method described in the invention is applied. It gives the appearance of 20 Figure 2 shows a schematic representation of the process flow that is the subject of the invention. Explanation of Part References 1. Content unit 2. Processing unit 1001. Identifying the object to be censored within the image content that is intended to be censored. 25 a process that runs an artificial intelligence algorithm capable of object recognition and censorship the content containing the relevant images is transmitted to the unit by a content unit 4 1002. By looping through each frame of the image transmitted in a processing unit, object recognition and pre-trained methods are used with images of the object to be censored. analyzed using a censorship algorithm 1003. Object recognition and censorship algorithm run via processing unit. The object to be censored and its position on the image are specified in the relevant 5 points. detect it in the image frame 1004. Object recognition and censorship algorithm run via processing unit. In the relevant image frame, a blur is applied to the image of the object that is intended to be censored. placement 1005. The content unit of the new blurred image frame created via the processing unit is 10. replacing the original content on it Detailed Description of Find In this detailed explanation, the preferred configurations of the method in question are described only. This is explained to facilitate a better understanding of the subject. The invention identifies 15 unwanted elements found in various types of content such as live broadcasts, streaming, and video. This allows images to be blurred and censored using artificial intelligence algorithms. It describes a method. The method we invented utilizes an object recognition and censorship algorithm. is being operated. The preferred application of the system includes the aforementioned object recognition and The censorship algorithm is an algorithm that has been pre-trained with cigarette images. It is characterized and run via a processing unit (2). The mentioned processing unit (2) is a server, computer, processor, etc. that contains an algorithm. It is characterized as any hardware capable of running the software. The video content that is intended to be censored is content that includes the original version of the video content in question. The content is transmitted to the processing unit (2) via the content unit (1). The content unit (1) is, for example, a CDN 25 It can be characterized as a (Content Delivery Network) server. Processing unit (1) Each frame of the image is then subjected to an object recognition and censorship algorithm. It is processed through this means. Object recognition and censorship algorithm processing run via processing unit (2) The image captured shows the object to be censored and the image of that object. It detects its location and blurs that location, thus removing the unwanted element. This allows for the censorship of the image. This is the preferred method in practice. The object recognition and censorship algorithm detects a cigarette in an image and takes the relevant 5 steps. It blurs the areas in the image frame where the cigarette image appears. The censored image frames are transmitted to the content unit (1) via the processing unit (2). And the original visual frames are replaced with censored frames.

Claims

6 REQUESTS 1. Censoring unwanted scenes in video or broadcast content. It is a method that provides, and its characteristic is;  The image content intended to be censored must identify the object intended to be censored. a 5 that runs an artificial intelligence algorithm capable of object recognition and censorship. to the processing unit (2), by a content unit (1) containing the relevant images transmission (1001),  In a processing unit (2), each frame of the transmitted image is looped through, images of the object to be censored and the object that has been pre-trained Analysis of recognition and censorship with artificial intelligence algorithm (1002), 10  Object recognition and censorship artificial intelligence run via processing unit (2) the algorithm identifies the object to be censored and the image of that object Determining its position on the relevant image frame (1003),  Object recognition and censorship artificial intelligence run via processing unit (2) The algorithm identifies 15 objects in the relevant image frame that are intended to be censored. placing blur on the image (1004),  content unit of the new blurred image frame created via processing unit (2) (1) Replacement with the original content on (1005) It includes the steps of the process.

Images