# Iris Recognition
This is based on the work by [Thuy Ng](https://www.github.com/thuyngch). His original Iris Recognition System implemented in both MatLab and Python can be found [here](https://github.com/thuyngch/Iris-Recognition).
## Description
This system is incomplete for a real-world application. A complete system must have a specific camera to capture the iris of the eye. However, these cameras are very expensive. Therefore available image databases [CASIA-IrisV1](http://biometrics.idealtest.org/dbDetailForUser.do?id=1) and [MMU2](http://andyzeng.github.io/downloads/MMU2IrisDatabase.zip) are used to replace the costly cameras. All testing and machine learning classification are carried out using images in these databases.
Typically, a recognition system involves two operation modes, namely Enrollment and Verification.
**Enrollment** is extracting features from an eye image and saving it into a template database.
**Verification** allows users extract their features and match with existing entities in the template database to identify the origination of the input image.
These system utilizes all CPU cores to boost computation time.
## Set Up
These system was deployed and executed on an Ubuntu 20.04 OS and the Python interpreter is Python 3.8.5.
First, create a virtual environment
```bash
python3 -m venv iris_venv
source iris_venv/bin/activate
```
Clone this repository
```bash
git clone https://github.com/Th3nn3ss/python-iris-recognition.git
cd python-iris-recognition
```
Install requirements
```bash
pip install -r requirements.txt
```
## Folder Structure
```bash
.
+-- CASIA-database/
| +-- 001_1_1.jpg
| +-- ...
| +-- 108_2_4.jpg
|
+-- MMU2-database/
| +-- 010101.bmp
| +-- ...
| +-- 1000205.bmp
+-- python/
| +-- fnc/
| +-- boundary.py
| +-- ...
| +-- template-database/ # Created when an image is enrolled
| +-- 1.mat
| +-- ...
| +-- enroll-casia1.py
| +-- enroll-mmu2.py
| +-- eval_casia1.py
| +-- eval_mmu2.py
| +-- requirements.txt
| +-- verify.py
```
* Folder <code> CASIA-database</code> includes original eye images. These system uses these images as the input.
* Folder <code>python</code>contains the following folders.
- Folder <code>fnc</code>, this contains the back-end functions. _
- Folder <code>template-database </code> stores registered template extracted from eye images, it is created when an image is enrolled.
- File <code>enroll-casia1.py</code>enrolls the images in the CASIA1 folder.
- File <code>enroll-mmu2.py</code> enrolls the images in the MMU2 folder.
- File <code>eval-casia1.py</code> is used to execute a Machine Learning Classification Algorithm that determines the Maximum fscore, Best eye_threshold and Best threshold for the CASIA1 Database. This process does not have to be repeated but you can re-run to check the following results,
![CASIA1-optimal.png](./sample_images/casia1_eval.png)
File <code>eval-mmu2.py</code> is used to execute a Machine Learning Classification Algorithm that determines the Optimal Maximum fscore, Best eye_threshold and Best threshold for the images in the MMU2 Database. This process does not have to be repeated but you can re-run to check the following results.
![mmu2-optimal](./sample_images/mmu2_eval.png)
File <code> verify.py </code> is used to verify if an image sample can be recognized by the system from the pool of template images. The default threshold used for matching is 0.38.
## Usage
### To Enroll a set of images
```bash
python enroll-casia1.py
```
In the above example, we are enrolling the CASIA1 Database into the system. This encodes the specially selected images using regex and the outputs are stored in a templates database sub-folder, in the case of this example a CASIA1 sub-folder.
![python enroll-casia1.py](./sample_images/enroll.png)
### To verify an image
```bash
python verify.py --file ../CASIA1/3/003_1_1.jpg --temp_dir ./templates/CASIA1/
```
In the above example, the file we are trying to verify is an image from the third folder in the CASIA1 Database. We point to the particular file by passing an argument to the <code> --file </code> flag.
Provided all images in the CASIA1 Database have been enrolled to the templates database. We can pass an argument to the <code>--temp_dir</code> flag, pointing to the templates sub-folder where the images were enrolled.
The default threshold used for matching is 0.38.
The outcome of the above code looks like this,
![python verify.py](./sample_images/verify.png)
The image above shows that the image file 003_1_1.jpg matches 2 samples.
## License
[MIT](./LICENSE)
没有合适的资源?快使用搜索试试~ 我知道了~
matlab眼睛识别源码-python-iris-recognition:Python实现的虹膜识别系统
共1792个文件
bmp:995个
jpg:756个
pyc:21个
需积分: 47 11 下载量 169 浏览量
2021-06-07
15:53:55
上传
评论 5
收藏 66.13MB ZIP 举报
温馨提示
matlab眼睛识别源码虹膜识别 这是基于 . 可以找到他在 MatLab 和 Python 中实现的原始虹膜识别系统。 描述 该系统对于实际应用程序来说是不完整的。 一个完整的系统必须有一个特定的相机来捕捉眼睛的虹膜。 然而,这些相机非常昂贵。 因此可用的图像数据库和用于替换昂贵的相机。 所有测试和机器学习分类都是使用这些数据库中的图像进行的。 通常,识别系统涉及两种操作模式,即注册和验证。 注册是从眼睛图像中提取特征并将其保存到模板数据库中。 验证允许用户提取他们的特征并与模板数据库中的现有实体进行匹配,以识别输入图像的来源。 这些系统利用所有 CPU 内核来提高计算时间。 设置 这些系统在 Ubuntu 20.04 操作系统上部署和执行,Python 解释器是 Python 3.8.5。 一、创建虚拟环境 python3 -m venv iris_venv source iris_venv/bin/activate 克隆这个仓库 git clone https://github.com/Th3nn3ss/python-iris-recognition.git cd python-
资源详情
资源评论
资源推荐
收起资源包目录
matlab眼睛识别源码-python-iris-recognition:Python实现的虹膜识别系统 (1792个子文件)
360105.bmp 223KB
390102.bmp 223KB
390201.bmp 223KB
360104.bmp 223KB
900102.bmp 223KB
300104.bmp 223KB
390203.bmp 223KB
840203.bmp 223KB
840103.bmp 223KB
690204.bmp 223KB
840104.bmp 223KB
360204.bmp 223KB
690202.bmp 223KB
300105.bmp 223KB
360202.bmp 223KB
300205.bmp 223KB
360205.bmp 223KB
900203.bmp 223KB
360101.bmp 223KB
390105.bmp 223KB
360203.bmp 223KB
390204.bmp 223KB
300102.bmp 223KB
690201.bmp 223KB
300103.bmp 223KB
690105.bmp 223KB
900104.bmp 223KB
300204.bmp 223KB
840202.bmp 223KB
360201.bmp 223KB
390103.bmp 223KB
690102.bmp 223KB
900105.bmp 223KB
900205.bmp 223KB
900202.bmp 223KB
900101.bmp 223KB
300203.bmp 223KB
840101.bmp 223KB
360103.bmp 223KB
390205.bmp 223KB
690205.bmp 223KB
300201.bmp 223KB
300202.bmp 223KB
390104.bmp 223KB
900103.bmp 223KB
300101.bmp 223KB
840204.bmp 223KB
690104.bmp 223KB
390202.bmp 223KB
690103.bmp 223KB
900204.bmp 223KB
360102.bmp 223KB
690203.bmp 223KB
840105.bmp 223KB
390101.bmp 223KB
690101.bmp 223KB
900201.bmp 223KB
840205.bmp 223KB
910205.bmp 223KB
750203.bmp 223KB
860203.bmp 223KB
860204.bmp 223KB
870203.bmp 223KB
870105.bmp 223KB
280102.bmp 223KB
570103.bmp 223KB
160205.bmp 223KB
870202.bmp 223KB
280204.bmp 223KB
910204.bmp 223KB
860102.bmp 223KB
110102.bmp 223KB
280104.bmp 223KB
630101.bmp 223KB
860205.bmp 223KB
110205.bmp 223KB
110101.bmp 223KB
760103.bmp 223KB
1000103.bmp 223KB
1000105.bmp 223KB
760203.bmp 223KB
040104.bmp 223KB
110201.bmp 223KB
870204.bmp 223KB
910104.bmp 223KB
760105.bmp 223KB
110104.bmp 223KB
1000104.bmp 223KB
1000201.bmp 223KB
160105.bmp 223KB
760101.bmp 223KB
040202.bmp 223KB
910101.bmp 223KB
750201.bmp 223KB
630204.bmp 223KB
910103.bmp 223KB
350202.bmp 223KB
350201.bmp 223KB
110105.bmp 223KB
1000205.bmp 223KB
共 1792 条
- 1
- 2
- 3
- 4
- 5
- 6
- 18
weixin_38710524
- 粉丝: 7
- 资源: 884
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0