LaTeX Code generator for tabular figures

          LaTeX code generator for tabular figures is a software that generates the given tabular image in LaTeX format automatically. By detecting the horizontal and vertical lines from the image, the software crops each cell of the image, extract the te

Project Title

LaTeX Code generator for tabular figures

Project Area of Specialization

Artificial Intelligence

Project Summary

          LaTeX code generator for tabular figures is a software that generates the given tabular image in LaTeX format automatically. By detecting the horizontal and vertical lines from the image, the software crops each cell of the image, extract the text from the cropped image and places every information of the table in LaTeX format. At the end, the output of the project that is the LaTeX code of the given table is compiled in LaTeX tool to check the result.

Project Objectives

          Overcoming the problem of writing the code of table in LaTeX format manually. Less user involvement and generate the error free code within short time span.

Project Implementation Method

In preprocessing, Binarization and image enhancement techniques are applied on the given image.

Binarization is the process of converting a pixel image into a binary image. A Binary image can have only 0 or 1 value for each pixel. The simplest way to use image binarization is to choose a threshold-value; all classify all pixels with values above this threshold as white (1), and other pixels as black (0). . After binarization, binarized image is inverted so that we will have only text and lines in the foreground. Note that image enhancement e.g., image sharpening may be applied if necessary.

Then Segmentation is applied to get horizontal and vertical lines from the image.

Image segmentation is the process of dividing a digital image into multiple parts. This is typically used to identify objects or other relevant information in digital images. The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. In this project, we will segment the image into horizontal and vertical lines by drawing horizontal and vertical histogram of the image respectively.

Lines are extracted from both the histograms. We will choose a threshold value, all values in histogram images greater than threshold value will be count as a line and all smaller values will be neglected. All these values will be saved in an Array vertically for horizontal lines and horizontally for vertical lines. Vertical Array will have those specific pixels vertically, which are counted as a horizontal line.

Horizontal Array will have those specific pixels horizontally, which are counted as a vertical line. After lines extraction we will count rows and columns in image.

After that specific row is extracted which is taken as a horizontal line and save them in a 2-D array with their x and y coordinates.

Then specific column is extracted which is taken as vertical line and save them in a 2-D array with their x and y coordinates.

Now we will crop each cell of tabular image using both extracted arrays of rows and columns.

From cropped images text is extracted using OCR. All the text is save in a text file with required syntax of LaTeX Editor .Including all information about table.

Benefits of the Project

Less user involvement is required in creating the table in LaTeX. The system will generate code within short time span and error free.

Technical Details of Final Deliverable

The final deliverable is a file with .p extension. This file is basically “encrypted .m files” so there is no way to check the source code.

Final Deliverable of the Project

Software System

Type of Industry

Education

Technologies

Artificial Intelligence(AI)

Sustainable Development Goals

Quality Education

Required Resources

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