Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Parameter name

Parameter setting method

Description

Data type

Default value

Value range

1

Use GPU checkboxCheck the box

Enables the use of GPU (graphics processing unit) computing resources to improve the license plate recognition performance

-No
  • Checkbox is set - the GPU computing resources are used to increase the performance of license plate recognition.
  • Checkbox is not set - set − the CPU (central processing unit) computing resources  are used.
2Accuracy drop-down listSelecting the value in the listSelecting the numbers recognition accuracyListMaximum
  1. Maximum - enables maximum recognition accuracy, but it causes great CPU and/or GPU load.  
  2. High - enables − enables high recognition accuracy, it requires less computing less computing resources than for maximum accuracy.
  3. Fast - enables high recognition speed, but the accuracy becomes worse.
3Strategy drop-down listSelecting the value in the listSelecting the computing resources use modeListSystem
  1. Process  - Process − mild mode: no more than 1 core for 1 license plate.
  2. System - default mode: all available computing cores are in use;.
  3. Core - Core  strict mode: 1 core per stream.
4Platform drop-down listSelecting the value in the listSelecting the device on which the module will operateListCPU
  • Default CPU resources are used for computing.
  • TensorRT NVIDIA GPU resources are used for computing.
  • CV22, NCNN, HISI, Qualcomm, TFLite, OpenVino - other device resources are used for computing, if available. These options apply to platforms other than x86/x64.
5Interval fieldEnter the value in the text field

Specifying the minimum time interval lasting between the frames processing (i.e. all frames within this interval will not be processed)

ms0In range of 0 to 999
6Profile drop-down listSelecting the value in the listSelecting the profile of country license plates that are to be recognized. Greater profile number enables more accurate LPR comparing to the solution with smaller number, but it is more demanding to computing resourcesList0