PHPackages mohuishou/image-ocr - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. [Image & Media](/categories/media) 4. / 5. mohuishou/image-ocr ActiveLibrary[Image & Media](/categories/media) mohuishou/image-ocr =================== 验证码识别 0.1.2(7y ago)2732.8k68[2 issues](https://github.com/mohuishou/ImageOCR/issues)1MITPHPPHP >5.5 Since Oct 7Pushed 6y ago14 watchersCompare [ Source](https://github.com/mohuishou/ImageOCR)[ Packagist](https://packagist.org/packages/mohuishou/image-ocr)[ RSS](/packages/mohuishou-image-ocr/feed)WikiDiscussions master Synced 2mo ago READMEChangelog (3)DependenciesVersions (6)Used By (1) ImageOCR ======== [](#imageocr) > php 验证码识别库，对于非粘连字符具有很好的识别效果，对于一般粘连字符也能有较为良好的识别 除噪算法支持孤立点除杂和连通域除噪，分割算法支持等宽分割、连通域分割以及滴水算法分割 示例效果 ---- [](#示例效果) [![示例](./img/1.png)](./img/1.png) Install ------- [](#install) ``` composer require mohuishou/image-ocr ``` 使用方法 ---- [](#使用方法) 例子详见 [example](./example) ### use docker [](#use-docker) ``` docker run --rm -p 8088:8088 mohuishou/image-ocr ``` 点击 查看效果 ### 大致流程： [](#大致流程) ``` 初始化 -> 灰度化 ---> 二值化 ---> 除噪点 -> 分割 -> 标准化 -> 识别 ``` #### 初始化 [](#初始化) 对象初始化 ``` $image=new Image($img_path); $image_ocr=new ImageOCR($image) ``` 初始化二值化阈值 ``` $image_ocr->setMaxGrey(90); $image_ocr->setMinGrey(10); ``` 初始化标准化图片宽高 ``` $image_ocr->setStandardWidth(13); $image_ocr->setStandardHeight(20); ``` #### 开启 Debug [](#开启-debug) ``` $image_ocr->setDebug(true); ``` #### 灰度化 [](#灰度化) ``` try{ $image_ocr->grey(); }catch (\Exception $e){ echo $e->getMessage(); } ``` #### 二值化 [](#二值化) 注意：这一步的前提是需要先执行上一步灰度化，不然会抛出一个错误 ``` try{ $image_ocr->hash($max_grey=null,$min_grey=null); }catch (\Exception $e){ echo $e->getMessage(); } ``` 二值化支持两种方式，第一种`$image_ocr->hash($max_grey=null,$min_grey=null)`即为上面那种固定的阈值范围，第二种为`hashByBackground($model=self::MAX_MODEL,$max_grey=null,$min_grey=null)`，通过背景图像的灰度值，动态取阈值，支持三种模式`MAX_MODEL`,`MIN_MODEL`,`BG_MODEL`分别是最大值、最小值和背景模式，最大值模式会用背景的灰度值替换阈值的上限，最小值模式替换下限，背景模式上下限都替换，即为只去除背景 #### 除噪点 [](#除噪点) 前置条件为二值化 ##### 孤立点除噪法 [](#孤立点除噪法) ``` try{ $image_ocr->removeSpots(); }catch (\Exception $e){ echo $e->getMessage(); } ``` ##### 连通域除噪法 [](#连通域除噪法) *\[如果要使用连通域分割法，可以跳过连通域除噪点，分割的同时可以一并除噪\]* ``` try{ //使用之前需要初始化连通域对象 $image_ocr->setImageConnect(); //除噪 $image_ocr->removeSpotsByConnect(); }catch (\Exception $e){ echo $e->getMessage(); } ``` #### 分割 [](#分割) ##### 非粘连字符串 [](#非粘连字符串) 连通域分割法 ``` try{ //使用之前需要初始化连通域对象 $image_ocr->setImageConnect(); //分割 $image_ocr->splitByConnect(); }catch (\Exception $e){ echo $e->getMessage(); } ``` ##### 粘连字符串 [](#粘连字符串) 滴水算法分割 TODO: 待测试 #### 标准化 [](#标准化) ``` try{ $standard_data=$image_ocr->standard(); }catch (\Exception $e){ echo $e->getMessage(); } ``` #### 识别 [](#识别) TODO:待完善 API --- [](#api) ``` ImageOCR::__construct(Image $image) ImageOCR::saveImage($path) ImageOCR::grey() ImageOCR::hash($max_grey=null,$min_grey=null) ImageOCR::hashByBackground($model=self::MAX_MODEL,$max_grey=null,$min_grey=null) ImageOCR::removeSpots() ImageOCR::removeSpotsByConnect() ImageOCR::standard() ImageOCR::setImageConnect() ImageOCR::setImage(Image $image) ImageOCR::getStandardData() ImageOCR::setMaxGrey($max_grey) ImageOCR::setMinGrey($min_grey) ImageOCR::setStandardWidth($standard_width) ImageOCR::setStandardHeight($standard_height) //ImageTool的方法均为静态方法 ImageTool::removeZero($data) ImageTool::removeZeroColumn($hash_data) ImageTool::drawBrowser($data) ImageTool::transposeAndRemoveZero($hash_data) ImageTool::hashTranspose($hash_data) ImageTool::img2hash($img) ImageTool::hash2img($hash_data,$padding=0) ``` CHANGELOG --------- [](#changelog) ### 0.2 \[2017-4-1\] [](#02-2017-4-1) ### 0.1 \[2016-10-7\] [](#01-2016-10-7) 1. 默认模板保存方式由数据库改为文件，保存路径为./db/db.json 2. 使用 composer 安装 ### Health Score 35 — LowBetter than 80% of packages Maintenance20 Infrequent updates — may be unmaintained Popularity37 Limited adoption so far Community20 Small or concentrated contributor base Maturity52 Maturing project, gaining track record Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Release Activity Cadence Every ~413 days Total 3 Last Release 2676d ago PHP version history (2 changes)0.1.1PHP >5.4 0.1.2PHP >5.5 ### Community Maintainers ![](https://www.gravatar.com/avatar/c4310fed2a58e61c12f5855cadb7a7f70b165f93006e434cb6f93156911e66cf?d=identicon)[mohuishou](/maintainers/mohuishou) --- Top Contributors [![mohuishou](https://avatars.githubusercontent.com/u/15172509?v=4)](https://github.com/mohuishou "mohuishou (35 commits)") --- Tags captchaimageimageocrocrphpimageOCR ### Embed Badge ![Health badge](/badges/mohuishou-image-ocr/health.svg) ``` [![Health](https://phpackages.com/badges/mohuishou-image-ocr/health.svg)](https://phpackages.com/packages/mohuishou-image-ocr) ``` ### Alternatives [intervention/image PHP Image Processing 14.3k194.3M2.2k](/packages/intervention-image)[league/glide Wonderfully easy on-demand image manipulation library with an HTTP based API. 2.6k51.2M116](/packages/league-glide)[liip/imagine-bundle This bundle provides an image manipulation abstraction toolkit for Symfony-based projects. 1.7k38.3M217](/packages/liip-imagine-bundle)[spatie/image Manipulate images with an expressive API 1.4k54.4M138](/packages/spatie-image)[intervention/image-laravel Laravel Integration of Intervention Image 1496.5M101](/packages/intervention-image-laravel)[alimranahmed/laraocr Laravel Optical Character Reader(OCR) package using different OCR engines like Tesseract 17081.9k](/packages/alimranahmed-laraocr) PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)