PHP使用OCR技术实现识别图片中的文字

sudo apt update
sudo apt install tesseract-ocr
sudo apt install tesseract-ocr-chi-sim # 安装中文语言包

brew install tesseract
brew install tesseract-lang

composer require thiagoalessio/tesseract_ocr

<?php
require 'vendor/autoload.php';

use thiagoalessio\TesseractOCR\TesseractOCR;

// 选择图片
$imagePath = 'test-image.png';

// 初始化 Tesseract
$ocr = new TesseractOCR($imagePath);

// 设置语言（中文）
$ocr->lang('chi_sim'); // 简体中文
$result = $ocr->run();

echo "识别结果：\n";
echo $result;

composer require guzzlehttp/guzzle

<?php
require 'vendor/autoload.php';

use GuzzleHttp\Client;

function getAccessToken($apiKey, $secretKey) {
    $client = new Client();
    $response = $client->post('https://aip.baidubce.com/oauth/2.0/token', [
        'form_params' => [
            'grant_type' => 'client_credentials',
            'client_id' => $apiKey,
            'client_secret' => $secretKey,
        ]
    ]);

    $data = json_decode($response->getBody(), true);
    return $data['access_token'] ?? null;
}

$apiKey = '你的API Key';
$secretKey = '你的Secret Key';

$token = getAccessToken($apiKey, $secretKey);
echo "Access Token: $token\n";

<?php
require 'vendor/autoload.php';

use GuzzleHttp\Client;

function recognizeText($imagePath, $accessToken) {
    $client = new Client();

    // 读取图片并进行 Base64 编码
    $imageData = base64_encode(file_get_contents($imagePath));

    $response = $client->post('https://aip.baidubce.com/rest/2.0/ocr/v1/general_basic', [
        'headers' => [
            'Content-Type' => 'application/x-www-form-urlencoded',
        ],
        'query' => [
            'access_token' => $accessToken,
        ],
        'form_params' => [
            'image' => $imageData,
        ],
    ]);

    $data = json_decode($response->getBody(), true);
    return $data['words_result'] ?? [];
}

$imagePath = 'test-image.png';
$accessToken = '你的Access Token';

$result = recognizeText($imagePath, $accessToken);

echo "识别结果：\n";
foreach ($result as $item) {
    echo $item['words'] . "\n";
}