![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/6244/media/kagglenot2p.PNG\")
Manually correcting a huge amount of data is a very time-consuming task, also creating an intelligent system without being 100% accurate won't be a usable solution, as we can't accept that a student doesn't get what he/she deserves, that's why we're not targeting only high accuracy, but we're targeting a perfect solution.
\r\nThe challenges you'll face during building your automatic solution are usually due to students not following the rules:
\r\n
![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/6244/media/kaggledon'tfill.PNG\")
![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/6244/media/kagglemultipleanswers.PNG\")
![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/6244/media/kaggle1.PNG\")
![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/6244/media/kaggle3.PNG\")
![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/inclass/6244/media/kaggle5.PNG\")
These are mainly the challenges that you'll need to handle while building your correction algorithm.
\r\nGood luck to all of you.
\r\nWe'd like to thank CSE011 Professors for giving us access to the dataset.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation metric for this competition is Mean Absolute Error. The Mean Absolute Error score, In our case, will represent the deviation from the actual mark that the student should take.
\r\nIn statistics, the mean absolute error (MAE) is a quantity used to measure how close forecasts or predictions are to the eventual outcomes. The mean absolute error is given by
\r\n$$
\\mathrm{MAE} = \\frac{1}{n}\\sum_{i=1}^n \\left| y_i - \\hat{y_i}\\right| =\\frac{1}{n}\\sum_{i=1}^n \\left| e_i \\right|.
$$
Where
$$ AE = |e_i| = |y_i-\\hat{y_i}| $$
$$ Actual Mark = y_i $$
$$ Corrected Mark = \\hat{y_i} $$
One submission file needs to be submitted, submission file should contain two columns: FileName and Mark. Mark should be the calculated score for each scanned answer sheet, and it should range from 0 to 45, and FileName should be the corresponding filename for the calculated mark.
\r\nThe file should contain a header and have the following format:
\r\nFleName,Mark", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "
S_1_hppscan1.png,32
S_1_hppscan112.png,36
S_1_hppscan113.png,33
S_1_hppscan114.png,31
S_1_hppscan115.png,34
etc.
You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.
\r\nThis competition is part of a term project for \"CSE 464: Image Processing and Pattern Recognition\" course for Ain Shams University students, so you're all required not to share codes about any part of your correction pipeline, though you can share tooling tools, related to programming in general.
\r\nTeam mergers are not allowed in this competition.
\r\nThere is no maximum team size.
\r\nYou may submit a maximum of 2 entries per day.
\r\nYou may select up to 2 final submissions for judging.
\r\nStart Date: Wed 1 Mar 2017
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: Sun 25 Jun 2017 12:00 AM UTC
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }