vitis::ai::OCR - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English
Base class for ocr.

Input is an image (cv:Mat).

Output is a struct of detection results, named OCRResult.

Sample code :

Mat img = cv::imread("sample_ocr.jpg");
auto ocr = vitis::ai::OCR::create("ocr_pt",true); 
auto results = ocr->run(img); 
// please check test samples for detail usage.

Quick Function Reference

The following table lists all the functions defined in the vitis::ai::OCR class:

Table 1. Quick Function Reference
Type Member Arguments
std::unique_ptr< OCR > create
  • const std::string & model_name
  • bool need_preprocess
vitis::ai::OCRResult run
  • const cv::Mat & img
std::vector< vitis::ai::OCRResult > run
  • const std::vector< cv::Mat > & imgs
int getInputWidth
  • void
int getInputHeight
  • void
size_t get_input_batch
  • void