Giter Site home page Giter Site logo

Comments (12)

gaulghost avatar gaulghost commented on August 15, 2024 2

@GrayFlash I made the project in colab to identify the changes by contour menthod but it is also detecting some part of image which is same, I am trying to find a way so that I can eliminate that
Original Image
image
Changed Image
image
Difference in contours
image

In the above Image I have removed some extra contours (See the difference in Contours Image and Changed Image) by specifing width and height of contour but still I am not getting how to perfect it and detect it properly.
One easy way would be counting the number of contours present of specific width and height and if their number is higher than that specified by you... It will tell the change in slides. Drawback would be such as if there is a slide with only one or two words changed it might not detect it.

from eduhelp.

AasthaRS avatar AasthaRS commented on August 15, 2024 1

We can check size of images and channels of both images by getting pixel value difference of both the images.
@shankhanil007 please assign this issue to me as a part of gssoc'21.
I want to work on it.

from eduhelp.

yashasvimatta avatar yashasvimatta commented on August 15, 2024 1

this can be done using structural similarity index. Can i work on this issue?

from eduhelp.

GrayFlash avatar GrayFlash commented on August 15, 2024 1

@yashasvimatta please go ahead with it.

from eduhelp.

GrayFlash avatar GrayFlash commented on August 15, 2024 1

@gaulghost I see you are going great, and your work will be a potential up-gradation on how we did this, it will be great if you can make a folder in our repo Jupyter_Notebooks and add your notebook there, keep the file name as (your work_(GithubId)).ipynb.
Make a PR, I will merge it and it will be great if @shankhanil007 and you can have a discussion on it, cause he worked on this earlier. Any other mentor @D3ADSH0T25 and @Apurva-tech are also welcome to participate in this issue.

from eduhelp.

shankhanil007 avatar shankhanil007 commented on August 15, 2024

@AasthaRS go ahead

from eduhelp.

gaulghost avatar gaulghost commented on August 15, 2024

I think we should convert the image into hsv format then analyse the pixels of bith the images. if the pixel in the one image is a 95% match with the pixel in another image, we shall pass it. So making a list of different valued pixel will tell if both images are same or not.

from eduhelp.

gaulghost avatar gaulghost commented on August 15, 2024

I also want to ask if there are two images both are same, difference is only that a filter is applied to one image then shall those images be considered same or different.

from eduhelp.

GrayFlash avatar GrayFlash commented on August 15, 2024

The purspose behind this comparision between two images is that we are going to screenshot of your desktop screen while you are attending your meet, and we wish to save a screen shot only when the slide being presented in the meeting changes, So it will be great if you think accordingly.

For this issue you need to avoid changing fomat of image and consider that there are 3 channels in both images for RGB and you have to just compare and see by how much these two images vary.

from eduhelp.

GrayFlash avatar GrayFlash commented on August 15, 2024

if the pixel in the one image is a 95% match with the pixel in another image,

I am afraid for our requirement this may not suffice, consider two images of two slides of a ppt on your desktop, most of the pixels are going to remain the same as only the region where presentation goes on will change and that too the presentation template mostly remains same, i.e., the same background of slides. So it will be better to hardcode a bit higher threshold.

from eduhelp.

GrayFlash avatar GrayFlash commented on August 15, 2024

@AasthaRS @gaulghost what is your status?? If you are stuck somewhere please discuss it here or in the discord channel.

from eduhelp.

GrayFlash avatar GrayFlash commented on August 15, 2024

@gaulghost @shankhanil007 @Apurva-tech @D3ADSH0T25 please discuss here #28.

from eduhelp.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.