Extract Text from Video

Indonesian Journal of Electrical Engineering and Computer Science, 2022

Automatic summarization is a technique for quickly introducing key information by abbreviating large sections of material. Summarization may apply to text and video with a different method to display the abstract of the subject. Natural language processing is employed in automated text summarization in this research, which applies to YouTube videos by transcribing and applying the summary stages in this study. Based on the number of words and sentences in the text, the method term frequencyinverse document frequency (TF-IDF) was used to extract the important keywords for the summary. Some videos are long and boring or take more time to display the information that sometimes finds in a few minutes. Therefore, the essence of the proposed system is to find the way to summarize the long video and introduce the important information to the user as a text with few numbers of lines to benefit the students or the researchers that have no time to spend with long videos for extract the useful data. The results have been evaluated using Rouge method on the convolutional neural network (CNN)-dailymail-master data set.

2008 3rd International Conference on Information and Communication Technologies: From Theory to Applications, 2008

In this paper, we propose a spatial temporal video-text detection technique which proceed in two principal steps: potential text region detection and a filtering process. In the first step we divide dynamically each pair of consecutive video frames into sub block in order to detect change. A significant difference between homologous blocks implies the appearance of an important object which may be a text region. The temporal redundancy is then used to filter these regions and forms an effective text region. The experimentation driven on a variety of video sequences shows the effectiveness of our approach by obtaining a 89,39% as precision rate and 90,19 as recall.

— The goal of this paper is to detect the text from video. With the increasing popularity of practical vision systems and smart phones, text detection in natural scenes becomes a critical yet challenging task. In a society driven by visual information and with the drastic expansion of low-priced cameras, text recognition is nowadays a fast changing field. The goal of this paper is develop a robust algorithm that extracts text from video with cluttered background. We propose a simple but efficient methodology for text detection in video frames. The method is based on the gradient information and edge map selection. In the proposed method we first find the gradient of the image and then enhance the gradient information. We later binarized the enhanced gradient image and select the edges by taking the intersection of the edge map with the binary information of the enhanced gradient image. We use the edge detector for generating the edge map. The selected edges are then morphologically dilated and opened using suitable structuring elements and used for text regions. We then perform the projection profile analysis to identify the boundary of the text region. At the end, we implement a false positive elimination methodology to improve the text detection results. Then we make the video from image frames which contain the detection of text.

2001

Abstract The detection and extraction of scene and caption text from unconstrained, general-purpose video is an important research problem in the context of content-based retrieval and summarization of visual information. The current state of the art for extracting text from video either makes simplistic assumptions as to the nature of the text to be found, or restricts itself to a subclass of the wide variety of text that can occur in broadcast video. Most published methods only work on artificial text (captions) that is composited on the video frame.

Videos are very important and helpful in our daily life for understanding and comprehend the information. With the help of videos user can gain the knowledge and spreads that knowledge to the other peoples. Hence, here it becomes important to make videos available to the people having auditory problems and even more for the people to remove the gaps of their native language. This all things are getting by using the subtitles for videos. There are several websites which are providing the subtitle files for the videos but not for all videos. Downloading subtitles from internet is a monotonous process. Hence to generate subtitles automatically with the help of software is the valid subject to research, this research paper resolves the problems mentioned above through the speech recognition technology. There are three models helps to generate subtitles for videos, Audio Extraction helps to extract audio from video and convert into .wav format for speech recognition process. Here 24% reduction rate has been achieved in the size of the video after the extraction. With the help of PocketSphinx speech recognition engine the .wav file get processed and the speech is get converted into text format and stored in .srt file for future use.

International Journal of Innovative Research in Computer and Communication Engineering, 2013

This paper represents text extracting information (represented by data) from a sequence of images (video) is the main objective of Video segmentation. In order to extract and search important information from a huge amount of video data, we are focusing on extraction of texts from video. However variations of the text due to differences in text style, font, size, orientation, alignment as well as low image contrast and complex background make the problem of automatic text extraction extremely difficult and challenging job. A large number of techniques have been proposed to address this problem and the purpose of this paper is to design algorithms for each phase of extracting text from a video using java libraries and classes. Here first we frame the input video into stream of images using the Java Media Framework (JMF) with the input being a real time or a video from the database and considering the connected component analysis form. We apply preprocessing algorithms to convert the ...

2021

In current situations, videos provide much help to better understand the information regarding any type of concept or any data relevant to the user. Therefore it becomes very important to make such content available to a wider audience along with audiences with disabilities and remove the barrier of languages. This can be achieved through the subtitles that are embedded inside the frames of the videos. However, these subtitles are limited by the language that is decided by the content creators. Solving this problem of restriction is an important subject of research. Therefore this paper includes the literature review of text extraction and text detection. The paper also proposes a method for extracting and translating the subtitles from videos. It also includes comparison between proposed method and an exhaustive method that does not include a support system and the proposed system that does. It shows how the proposed system goes around the problem of identifying the frames that con...

International Journal of Computer Applications, 2019

With the advent of the internet and e-resources, there has been an exponential growth of data available to the users. Amongst many content providers, YouTube succeeds in securing the second most popular website in the world. The data from YouTube is easily available to the users, due to which many researchers gather YouTube videos as their dataset for research. Searching the required video for data analysis from YouTube is a cumbersome task as YouTube is overloaded with trillions of videos. Researchers thus need to spend a huge amount of time to get required dataset. To save the time taken by researchers for accumulating dataset, an open source application "TubeExtractor" is proposed in this paper. The TubeExtractor application will allow researchers to download the videos and its metadata from YouTube based on the desired parameters provided by the researcher. The TubeExtractor will also provide as an output a plain text file of the downloaded video. This file can be used by the researchers to do additional processing of their choice if required. The keywords to download the videos are provided to the crawler in the form of a document, generated using a keyphrase extractor algorithm. If the vtt (Video Text Tracks) file of the video to be downloaded is available then a

Journal of Intelligent Software Systems

Youtube is a video platform which not only provides entertainment but also education in which knowledge can be dug based on video transcripts. The results of this knowledge can be formed as a knowledge graph to build a knowledge base that saves storage space. Moreover, it can be used for other purposes such as recommendation systems and search engines. Prosen built a knowledge graph using NLP to extract the text by identifying the subject-verb-object (SVO) and stored in the graph database. The construction of a knowledge graph on a Youtube video transcript was successfully carried out. However, there are still obstacles in the process of extracting text using NLP which is less optimal so it is possible that there is still a lot of knowledge that has failed to be obtained.

2011 International Conference on Document Analysis and Recognition, 2011

In this paper, we present a new method for video script identification which is essential before choosing an appropriate OCR engine for identifying text lines when a video frame contains more than one language. The input for script identification is the text lines obtained by our text detection method. We extract upper and lower extreme points for each connected component of Canny edges of text lines. The extracted points are connected to study the behavior of upper and lower lines. The direction of each 10-pixel segment of the lines is determined using PCA. The average angle of the segments of the upper and lower lines is computed to study the smoothness and cursiveness of the lines. In addition, to discriminate the scripts accurately, the method divides a text line into five equal zones horizontally to study the smoothness and cursiveness of the upper and lower lines of each zone. We evaluate the method by conducting experiments on different combinations of languages such as English and Chinese, English and Tamil, Chinese and Tamil, and English, Chinese and Tamil.