当前位置：首页 > news >正文

vs2022+tesseract ocr识别中英文编译好的库下载

news 2025/8/8 0:43:26

测试图片

效果

编译其实挺麻烦的，可参考：在Windows上用Visual Studio编译Tesseract_windows编译tesseract-CSDN博客

#include "baseapi.h"
#include "allheaders.h"
#include <iostream>
#include <fstream>  // 用于文件操作int main()
{tesseract::TessBaseAPI* api = new tesseract::TessBaseAPI();// 初始化，加载中文和英文语言包if (api->Init("tessdata", "chi_sim+eng") != 0) {std::cout << "Could not initialize tesseract with chi_sim and eng languages" << std::endl;return -1;}// 读取图像（假设是 BMP 格式）Pix* image = pixRead("d:/sss.bmp");if (image) {api->SetImage(image);// 获取识别结果（UTF-8 编码）char* outText = api->GetUTF8Text();// 将结果写入文件std::ofstream outputFile("result2.txt");if (outputFile.is_open()) {outputFile << outText;  // 将 OCR 结果写入文件outputFile.close();     // 关闭文件std::cout << "OCR result has been written to result.txt" << std::endl;} else {std::cout << "Failed to open output file" << std::endl;}// 清理delete[] outText;pixDestroy(&image);} else {std::cout << "Failed to load image" << std::endl;}// 结束 Tesseractapi->End();delete api;return 0;
}

针对vs2022编译文件下载

leptonica下载地址：leptonica.7z - 蓝奏云

tesseract下载地址：tesseract.7z - 蓝奏云

配置：包含目录中添加如下图路径