PHP使用OCR技术识别图片中的文字（无需接口）

sudo apt-get install tesseract-ocr

 composer require sbt/tesseract

sudo apt-get install php-tesseract

extension=tesseract.so

require 'vendor/autoload.php';
use Sbt\Tesseract\Tesseract;

$image = imagecreatefromjpeg('invoice.jpg');

$gray = imagecreatetruecolor($width, $height);
imagecopyresampled($gray, $image, 0, 0, 0, 0, $width, $height, $width, $height);
$threshold = 127;
$black = array();
$white = array();
for ($x = 0; $x < $width; $x++) {
    for ($y = 0; $y < $height; $y++) {
        $rgb = imagecolorat($gray, $x, $y);
        $r = ($rgb >> 16) & 0xFF;
        $g = ($rgb >> 8) & 0xFF;
        $b = $rgb & 0xFF;
        $grayscale = round(0.299 * $r + 0.587 * $g + 0.114 * $b);
        if ($grayscale < $threshold) {
            $black[] = imagecolorallocate($gray, $x, $y);
        } else {
            $white[] = imagecolorallocate($gray, $x, $y);
        }
    }
}
imagecolortransparent($gray, imagecolorallocate($gray, 0, 0, 0));
imagefill($gray, $black);
imagecolortransparent($gray, imagecolorallocate($gray, 255, 255, 255));
imagefill($gray, $white);

$tesseract = new Tesseract();
$tesseract->setDatapath('/usr/share/tesseract-ocr/4.00/tessdata'); // 设置tessdata路径
$text = $tesseract->doOCR($gray);
print_r($text);