Skip to content

ducanhvna/ocr-tessaract

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

30 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ocr-tessaract

Overview

Intersection over Union for object detection

In the remainder of this blog post I’ll explain what the Intersection over Union evaluation metric is and why we use it.

I’ll also provide a Python implementation of Intersection over Union that you can use when evaluating your own custom object detectors.

Finally, we’ll look at some actual results of applying the Intersection over Union evaluation metric to a set of ground-truth and predicted bounding boxes.

Idea

Build meta data by lableImage tool

build meta data data by lbl Image tool

Convert to json fomat

[
    {
        "formatid":1,
        "width" : 1024,
        "heigh": 800,
        "Blockes": [
            {
                "x": 50,
                "y": 50, 
                "width" : 50,
                "heigh" : 100
              }
  
          ]
    }
] 

Installation

pip install -r requirements.txt
python detecIoU.py

Result

Solution 1: Use only one area (textblock) - which has maximum IoU value

Solution 1

Solution 2: Use cobination 3 of block to bulid result

Solution 2

Other method

Use tessaract to annotation word level

conda install -c conda-forge tesserocr
python tesseract2wordLevel.py 

references

Intersection over Union (IoU) for object detection

Reading and Writing JSON to a File in Python

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages