VidToPick

As we have seen that a video consists of many different points, if we look at educational lecture videos there are usually main points that have been discussed. So from a particular video if someone wants to target a specific point he/she has to watch the whole video to reach there. That is basicall

Project Title

VidToPick

Project Area of Specialization

Artificial Intelligence

Project Summary

As we have seen that a video consists of many different points, if we look at educational lecture videos there are usually main points that have been discussed. So from a particular video if someone wants to target a specific point he/she has to watch the whole video to reach there. That is basically such a time taking process. Our main concern is to let users successfully reach at the point of their wish with the help of system generated keywords, moreover, they can trim and preview as per the desire. We will be using Natural language processing and Information retrieval technology to achieve this goal. Moreover, we are assuming that team members will have access to all the resources either human or material to complete the goal. Also, there are some risks that we have to deal with in order to complete our goal, some of them are unresolved conflicts and understanding of algorithms.

In this modern era, we are still watching and going through full videos just to reach a certain point or we can say a certain topic of that particular video.
Through this application the users reach the specific timestamp of a video and the user will be able to set foot on the specific content from that video.  While downloading a YouTube video through its link VIDTOPICK will allow users to trim and download the video as per their thirst, text file of the keywords will be provided to the user of the uploaded video. From the provided keyword, the user will be able to know about the subject/topic. After clicking the keywords the system will let the user hit the point of their need where that particular topic/content was discussed. To provide users with a better users with a better user experience, the system will provide previews of the desired video as well.
Users will be able to make accounts on our system so that they will be able to save video links for the future as well.  They will also be able to see their history as well and they will be able to delete it if they want. The data of each user will be stored in the database.
The business value of this system will be high as in the current situation people are more familiar with technology as the paradigm of the education system has been shifted to online. People need more systems that will help them in learning, so for this kind of need our system will provide the best service and take them towards the content of their need in each video, not only the education system, there will be many more areas that will be able to get advantage from this. So if they missed anything they will catch every point via our system. There are several platforms that are designed for keyword generation, also there are platforms that are providing captioning and some are providing video trimming, but there is no such application that provides all functions on the same platform.
 

Project Objectives

Our main objective is to eliminate the process of watching full videos to get to know about what has been discussed in the videos, in other words we want to achieve the goal to put our old education system towards technology and make our people more technical, so that they can easily and fast complete their chore.

Our VIDTOPICK will meet the following objectives:
 
?       The user will get generated keywords from the uploaded video.
?       The user will be able to trim and download the video as per their need.
?       The user will be able to reach a particular instance through selecting the keyword.
?       The text generated file will be available to the user.
Project scope

The project scope include:

The video will be processed, and an SRT file will be created. Keywords will be created from the SRT file. Trimmed Video can be downloaded by users. When a user provides a link to a YouTube video, the video takes time to process, therefore the user will provide a Gmail id and will be alerted once the video has been processed. YouTube is integrated into our mobile and website applications. Users can set up an account. The user history and highlighted links will be kept. Users may use filters to search for information on the search engine using our platform.

The life cycle would be based on agile and scrum technique. The work would be done on a modular basis.
Testing would be Black box and White box testing.
Majorly the data would be in video link format which should be provided by the user.
If the database would be used that would be Firebase real-time database. To save links to videos.
The major functionality which is included in the scope is that the provided video would be captionized and the user can jump to any timestamp by searching keyword.

The scope of this project includes and excludes the following items.

In scope:

Video will be processed and SRT File is generated
From the SRT file, keywords will be generated. 
Users can Trimmed Video and download .
When User gives a link to a YouTube video, the video takes time to be processed so the user will provide a Gmail id on which the user will be notified once the video has been processed.
Our Website Application is associated with YouTube.
Users can create an account.
User can Preview Video
User history and starred links will be maintained
Users can search for content on the search engine through our platform using filters.
 

Project Implementation Method

Our project's main module is to generate srt from and mapping timspan to mark instance in videos of desired search keywords, We have train our dataset on PANNCNN model, for SRT generate.These SRT file will be index for searching and mapping purpose,

Benefits of the Project

Followings are the benefit of our project that it saves user time by marking instance in the video where the user desired or search keyword is present, moreover user can download SRT, trim video according to their need.

The user will get generated keywords from the uploaded video.
?       The user will be able to trim and download the video as per their need.
?       The user will be able to reach a particular instance through selecting the keyword.
?       The text generated file will be available to the user.

?       The user will be able to save video(mark favourate).
?       And can view history 

Technical Details of Final Deliverable

HARDWARE
Our project does not require any specialized hardware.
SOFTWARE
>FRONTEND
In the software front-end we use HTML, CSS, and bootstrap. for a web application.

>BACKEND
We are using python scripts as our Backend, these scripts will run the Machine Learning Model, and different algorithms and functionalities that we have implemented.
. 
> MIDDLE LAYER
We are using Django as a middleware for our project. Django is a high-level Python web framework that encourages rapid development and easy-to-use design. Django takes care of a lot of the tedious aspects of web development, allowing you to focus on developing your app rather than reinventing the wheel. It's open-source and free.
.
>DATA STRUCTURE
Data structure that we are using is inverted index. It is used in document retrieval systems. It is designed to allow fast full-text searches. An inverted index consists of a list of all the unique words that appear in any document, and for each word, a list of the documents in which it appears.

Final Deliverable of the Project

Software System

Core Industry

Education

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Quality Education

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com