Skip to content

Latest commit

 

History

History
 
 

gen2-text-blur

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
imgs
imgs
 
 
models
models
 
 
utils
utils
 
 
README.md
README.md
 
 
main.py
main.py
 
 
requirements.txt
requirements.txt
 
 

README.md

[Gen2] Text blurring on DepthAI

This example shows an implementation of Text Detection on DepthAI in the Gen2 API system with additional text blurring. ONNX is taken from PINTO's Model ZOO, and reexported with preprocessing flags.

Supported input shape is 480 x 640 (H x W), with expected ~3 FPS.

Image example

Cat image is taken from here, dog image is taken from here.

Pre-requisites

Install requirements:

python3 -m pip install -r requirements.txt

Usage

python3 main.py [options]

Options:

  • -nn, --nn_model: Select model path for inference. Default: models/text_detection_db_256x320_openvino_2021.4_6shave.blob.
  • -bt, --box_thresh: Set the box confidence threshold. Default: 0.2.
  • -t, --thresh: Set the bitmap threshold. Default: 0.1.
  • -ms, --min_size: Set the minimum size of box (area). Default: 1.
  • -mc, --max_candidates: Maximum number of returned box candidates. Default: 75.