What is इंडिक लेआउट पार्सर?
A Unified Toolkit for Deep Learning Based Document Image Analysis.
Accurate Layout Detection with a Simple and Clean Interface
With the help of state-of-the-art deep learning models, Indic Layout Parser enables extracting complicated Sanskrit document structures using only several lines of code. This method is also more robust and generalizable as no sophisticated rules are involved in this process.
A Wealth of Pre-trained Models on Different Datasets
To accommodate heterogenous document layout structures, Indic Layout Parser a collection of DL models trained on different datasets. Currently the are 9 models trained on 5 diverse datasets, and they can be loaded via a unified interface.
Easy Layout Data Manipulation and Processing
Layout Parser supports different levels of abstraction of layout data, and provide three classes of representation for layout data, namely, Coordinates, TextBlock, and Layout. The same operations and transformations are supported inter and intra these classes to maximize the efficiency when processing the layout data.
Highly Customizable Layout Data Visualization
Layout Parser visualizes the layout data using a simple syntax: lp.draw_box or lp.draw_text. It provides two modes for displaying the layout data: Mode I directly overlays the layout region bounding boxes and categories over the original image. Mode II recreates the original document via drawing the OCR’d texts at their corresponding positions on the image canvas.
