使用Tesseract 识别验证码-优快云博客

本文链接：https://blog.youkuaiyun.com/iteye_16188/article/details/82610897

本文介绍如何利用Tesseract OCR进行图文识别，包括安装、图片预处理、命令行调用及参数设置等步骤，并提供了限制识别字符范围的方法及训练Tesseract的参考资料。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

参考：
[url]http://code.google.com/p/tesseract-ocr/[/url]
[url]https://stackoverflow.com/questions/2363490/limit-characters-tesseract-is-looking-for[/url]
[url]http://resources.infosecinstitute.com/case-study-cracking-online-banking-captcha-login-using-python/[/url]

[color=blue][b]1. 安装：[/b][/color]

apt-get install tesseract-ocr

[color=blue][b]2. 预先处理图片，代码片段：[/b][/color]


from PIL import Image
import os
import time


def crack(cap_name):

    img = Image.open(cap_name+'.JPEG')
    img = img.convert("RGB")
    pixdata = img.load()

    for y in xrange(img.size[1]):
        for x in xrange(img.size[0]):
            if pixdata[x, y][0] < 90:
                pixdata[x, y] = (0, 0, 0, 255)
    for y in xrange(img.size[1]):
        for x in xrange(img.size[0]):
            if pixdata[x, y][1] < 136:                 pixdata[x, y] = (0, 0, 0, 255)     for y in xrange(img.size[1]):         for x in xrange(img.size[0]):             if pixdata[x, y][2] > 0:
                pixdata[x, y] = (255, 255, 255, 255)
    ext = ".tif"
    img.save(cap_name + ext)

[color=blue][b]3. 使用tesseract命令识别图片：[/b][/color]

tesseract imagename outbase [-l lang] [-psm N] [configfile ...]

[quote]0 = Orientation and script detection (OSD) only.
1 = Automatic page segmentation with OSD.
2 = Automatic page segmentation, but no OSD, or OCR
3 = Fully automatic page segmentation, but no OSD. (Default)
4 = Assume a single column of text of variable sizes.
5 = Assume a single uniform block of vertically aligned text.
6 = Assume a single uniform block of text.
[color=blue]7 = Treat the image as a single text line.[/color]
8 = Treat the image as a single word.
9 = Treat the image as a single word in a circle.
10 = Treat the image as a single character.[/quote]

[color=blue][b]4. 限制Tesseract搜索的字符[/b][/color]
1）在tessdata/configs文件夹中创建一个新的配置文件
2）在配置文件中添加如下：
[quote]tessedit_char_whitelist abcdefghijklmnopqrstuvwxyz [/quote]
3. 使用新建的配置文件调用tessdata命令。

[color=blue][b]5. 训练Tesseract识图能力[/b][/color]
参考文章：
[url]http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract2[/url]
[url]http://code.google.com/p/tesseract-ocr/wiki/TrainingTesseract3[/url]