vitis::ai::TextMountain - 3.5 English

Vitis AI Library User Guide (UG1354)

Document ID
Release Date
3.5 English
Base class for TextMountain (text detection)

Input is an image (cv:Mat).

Output is a struct of classification results, named TextMountainResult.

Sample code :

Mat img = cv::imread("sample_TextMountain.jpg");
auto TextMountain = vitis::ai::TextMountain::create("textmountain_pt",true);
auto result = TextMountain->run(img);
// result is structure holding the text information
std::cout << result.res.size() <<"\n";

Quick Function Reference

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

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