Skip to main content

Document Image Analysis


Document Image Analysis is our first exercise in Advance Image Processing. In this exercise, I will use OpenCV and Python.

The shaded area in the form below should be classified.


All the forms were pre-processed with given center of the circles. The circles should be classified in three different categories: shaded, not shaded, and crossed-out. 

First, the given center of the circles should be plotted from csv to the python code.  
At first, I had a hard time dealing with the syntax of python so I spent quite a few hours studying and trying out sample codes so that I can use the basic operations and functions for this exercise. I used a normal file upload then I loop the file line by line. Finally, I boxed all the circles in green lines using OpenCV's rectangle function.

After the initial boxing, the mean intensity of the boxed circles was gathered. Lower intensity means darker. The darker circles are detected blue (I assumed that the student crossed-out the circle so it is darker than the filled circle). A threshold between the black and the unshaded circle are colored by red. 

This is a sample resulting image.

I found minor errors such as filled circles with minimum intensity and those misaligned images. However, I believe that my exercise has a higher accuracy of attaining the correct answer.
  

Comments

Post a Comment

Popular posts from this blog

Document Layout Analysis

Document Layout Analysis is our second exercise. Using the three images above our program needs to do the following: Individual characters are boxed Individual words are boxed Lines are boxed Paragraphs are boxed The paragraphs with margins I used a bottom-up approach for this exercise. It means that I started detecting and boxing the letters to words to line to paragraph and lastly to the paragraph with margin. I created a function for each of the objectives. I used a trial and error approach for determining the appropriate kernel size for the specific function. I have a very simple step for every objectives: Load the images. Assigning of output images Convert images to grayscale Cleaning the images using Otsu's Thresholding method. (with the inversed binarized image) Assigning kernel size (1 or 2 kernels depending in the objective) Morphological Operations (Dilation, Erosion, Closing and Opening) Find the Contours Box the contours (I added some offs...
Post a Comment
Read more

Color Image Processing

Color Image Processing is our 4th Exercise. The objective of this exercise is to detect an object using color spaces. For this exercise our object is a pig with green tag. We need to detect the pig and the green tag. I use HSV color space for detecting the green tag and YCRCB color space for detecting the pig. The range of minimum and maximum for the pig detection is hardcoded. I use this http://www.wseas.us/e-library/conferences/2011/Mexico/CEMATH/CEMATH-20.pdf as reference for detecting the pig. I cleaned the images using opening method with a kernel size of 20. Here are my sample outputs detecting the green tag: Some bad outputs detecting the pig:         The rest of the pig detection are okay:
Post a Comment
Read more

Installing AsgardCMS for your Web Application

AsgardCMS is a full-featured modular and multilingual CMS on top of the Laravel Framework. Here are the steps for installing the aforementioned CMS. You can get the code using this command: composer create-project asgardcms/platform your-project-name If the terminal ask you for a token. Just follow the steps of generating a new token here: https://help.github.com/articles/creating-an-access-token-for-command-line-use/  After that, the installation must be smooth-sailing. Go t the directory of your project php artisan asgard:install Then, you will now set-up the database connection and admin creation. Finally, you can run  php artisan serve or php artisan serve --port=your-port Access the application: Application : localhost:your-port/en Admin: localhost:your-port/en/backend References:  https://asgardcms.com/install https://www.youtube.com/watch?v=MeX_D-aql6g http://asgardcms.blogspot.in/2015/12/asgardcms-inst...
4 comments
Read more