|
|
<h1 align="center">
|
|
|
<strong>中药图片拍照识别系统-移动端+后端</strong>
|
|
|
</h1>
|
|
|
<p align="center">
|
|
|
<img src="https://img.shields.io/badge/release-v3.1-green.svg"/>
|
|
|
<img src="https://img.shields.io/badge/language-Java 11-green.svg" />
|
|
|
<img src="https://img.shields.io/badge/language-Python 3-green.svg" />
|
|
|
<img src="https://img.shields.io/badge/dependency-SpringBoot-green.svg" />
|
|
|
<img src="https://img.shields.io/badge/dependency-TensorFlow-green.svg" />
|
|
|
<img src="https://img.shields.io/badge/license-MulanPSL-green.svg" />
|
|
|
</p>
|
|
|
|
|
|
## 项目说明
|
|
|
中药识别系统主要采用APP端拍照上传的方式，构建卷积神经网络（CNN）对图像进行识别，具有识别效率高，准确度高的特点。APP端的功能包括但不限于拍照识别、中药问答（付费咨询）、检索查询、中药性状以及功效查看、方剂智能推荐【开发中】等；本系统包含APP端以及服务器端。
|
|
|
|
|
|
## 版本说明 3.x
|
|
|
1. APP端使用**Flutter**重写界面，使用体验得到提升。
|
|
|
2. 深度学习运行时框架采用**ONNX Runtime**。**计算速度**得到明显加快，同时深度学习框架依赖部署文件减小到**40M**。
|
|
|
|
|
|
## 项目介绍
|
|
|
**本项目包含六个模块：**
|
|
|
|
|
|
- **medicine-app：**[APP端](medicine-app)
|
|
|
- **medicine-server：**[服务器端](medicine-server)
|
|
|
- **medicine-crawler：**[爬虫工程](medicine-crawler)
|
|
|
- **medicine-model：**[卷积神经网络](medicine-model)
|
|
|
- **medicine-util：**[公用工具类](medicine-util)
|
|
|
- **medicine-dataset：**[数据集](medicine-dataset)
|
|
|
|
|
|
## 项目预览
|
|
|
|
|
|
- **项目运行展示**
|
|
|
<table>
|
|
|
<tr>
|
|
|
<td>
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/启动屏.png" width="191px" height="338px" alt="">
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/首页.png" width="191px" height="338px" alt="">
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/筛选.png" width="191px" height="338px" alt="">
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/中药详细信息.png" width="191px" height="338px" alt="">
|
|
|
</td>
|
|
|
</tr>
|
|
|
<tr>
|
|
|
<td>
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/拍照识别.png" width="191px" height="338px" alt="">
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/预测结果.png" width="191px" height="338px" alt="">
|
|
|
<img src="https://gitee.com/xiaohaoo/chinese-medicine-identification/raw/master/assets/搜索结果.png" width="191px" height="338px" alt="">
|
|
|
</td>
|
|
|
</tr>
|
|
|
</table>
|
|
|
|
|
|
- [**视频演示**](https://www.bilibili.com/video/BV14T4y157rM)
|
|
|
- [**APP下载地址**](https://gitee.com/xiaohaoo/chinese-medicine-identification/releases)
|
|
|
|
|
|
|
|
|
## 开发文档
|
|
|
|
|
|
[阅读文档](http://xiaohaoo.gitee.io/chinese-medicine-identification-admin/)
|
|
|
|
|
|
|
|
|
## 技术简介
|
|
|
|
|
|
1. **medicine-app APP端**
|
|
|
- Flutter开发
|
|
|
|
|
|
2. **medicine-server服务器端工程**
|
|
|
|
|
|
Gradle构建
|
|
|
|
|
|
SpringBoot框架,一键启动与部署
|
|
|
|
|
|
文档数据库：MongoDB
|
|
|
|
|
|
全文检索：Elasticsearch + IK分词器
|
|
|
|
|
|
数据库：MySQL
|
|
|
|
|
|
深度学习运行时架构：ONNX Runtime（ONNX Runtime is a cross-platform inference and training machine-learning accelerator）
|
|
|
|
|
|
|
|
|
3. **medicine-crawler爬虫工程**
|
|
|
|
|
|
爬虫主要用来爬取**训练集**以及**中药的详细信息**，包含但不限于：中药名称、中药形态、图片、
|
|
|
别名、英文名、配伍药方、功效与作用、临床应用、产地分布、药用部位、
|
|
|
性味归经、药理研究、主要成分、使用禁忌、采收加工、药材性状等信息。
|
|
|
|
|
|
爬虫框架：WebMagic（[参考代码](./medicine-crawler/src/main/java/cn/xiaohaoo/datacollection/MedicineCountPageProcessor.java)）
|
|
|
|
|
|
数据持久化：MongoDB
|
|
|
|
|
|
数据结构（简略展示）
|
|
|
|
|
|
- 中药一级分类信息
|
|
|
|
|
|
|
|
|
|
|
|
- 中药详细信息
|
|
|
|
|
|
|
|
|
|
|
|
4. **medicine-model卷积神经网络工程**
|
|
|
|
|
|
- Language: Python
|
|
|
|
|
|
- 使用TensorFlow 深度学习框架，使用Keras会大幅缩减代码量
|
|
|
|
|
|
- [数据集](medicine-dataset)
|
|
|
|
|
|
- 常用的**卷积网络模型**及在ImageNet上的准确率
|
|
|
|
|
|
|模型|大小|Top-1准确率|Top-5准确率|参数数量|深度|
|
|
|
|:---:|:---:|:---:|:---:|:---:|:---:|
|
|
|
|**Xception**|**88 MB**|**0.790**|**0.945**|**22,910,480**|**126**|
|
|
|
|VGG16|528 MB|0.713|0.901|138,357,544|23|
|
|
|
|VGG19|549 MB|0.713|0.900|143,667,240|26|
|
|
|
|ResNet50|98 MB|0.749|0.921|25,636,712|168|
|
|
|
|ResNet101|171 MB|0.764|0.928|44,707,176|-|
|
|
|
|ResNet152|232 MB|0.766|0.931|60,419,944|-|
|
|
|
|ResNet50V2|98 MB|0.760|0.930|25,613,800|-|
|
|
|
|ResNet101V2|171 MB|0.772|0.938|44,675,560|-|
|
|
|
|ResNet152V2|232 MB|0.780|0.942|60,380,648|-|
|
|
|
|ResNeXt50|96 MB|0.777|0.938|25,097,128|-|
|
|
|
|ResNeXt101|170 MB|0.787|0.943|44,315,560|-|
|
|
|
|InceptionV3|92 MB|0.779|0.937|23,851,784|159|
|
|
|
|InceptionResNetV2|215 MB|0.803|0.953|55,873,736|572|
|
|
|
|MobileNet|16 MB|0.704|0.895|4,253,864|88|
|
|
|
|MobileNetV2|14 MB|0.713|0.901|3,538,984|88|
|
|
|
|DenseNet121|33 MB| 0.750|0.923|8,062,504|121|
|
|
|
|DenseNet169|57 MB| 0.762|0.932|14,307,880|169|
|
|
|
|DenseNet201|80 MB|0.773|0.936|20,242,984|201|
|
|
|
|NASNetMobile|23 MB|0.744|0.919|5,326,716|-|
|
|
|
|NASNetLarge|343 MB|0.825|0.960|88,949,818|-|
|
|
|
|
|
|
由于硬件条件限制，综合考虑模型的准确率、大小以及复杂度等因素，采用了**Xception模型**，该模型是134层（包含激活层，批标准化层等）拓扑深度的卷积网络模型。
|
|
|
|
|
|
- **Xception函数定义：**
|
|
|
|
|
|
```python
|
|
|
def Xception(include_top=True,
|
|
|
weights='imagenet',
|
|
|
input_tensor=None,
|
|
|
input_shape=None,
|
|
|
pooling=None,
|
|
|
classes=1000,
|
|
|
**kwargs)
|
|
|
|
|
|
# 参数
|
|
|
# include_top：是否保留顶层的全连接网络
|
|
|
# weights：None代表随机初始化，即不加载预训练权重。'imagenet’代表加载预训练权重
|
|
|
# input_tensor：可填入Keras tensor作为模型的图像输入tensor
|
|
|
# input_shape：可选，仅当include_top=False有效，应为长为3的tuple，指明输入图片的shape，图片的宽高必须大于71，如(150,150,3)
|
|
|
# pooling：当include_top=False时，该参数指定了池化方式。None代表不池化，最后一个卷积层的输出为4D张量。‘avg’代表全局平均池化，‘max’代表全局最大值池化。
|
|
|
# classes：可选，图片分类的类别数，仅当include_top=True并且不加载预训练权重时可用
|
|
|
```
|
|
|
|
|
|
- **构建代码**
|
|
|
|
|
|
[基于Xception的模型微调,详细请参考代码](medicine-model/src)
|
|
|
|
|
|
1. 设置Xception参数
|
|
|
|
|
|
迁移学习参数权重加载：xception_weights
|
|
|
|
|
|
```python
|
|
|
# 设置输入图像的宽高以及通道数
|
|
|
img_size = (299, 299, 3)
|
|
|
|
|
|
base_model = keras.applications.xception.Xception(include_top=False,
|
|
|
weights='..\\resources\\keras-model\\xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
|
|
|
input_shape=img_size,
|
|
|
pooling='avg')
|
|
|
|
|
|
# 全连接层，使用softmax激活函数计算概率值，分类大小是628
|
|
|
model = keras.layers.Dense(628, activation='softmax', name='predictions')(base_model.output)
|
|
|
model = keras.Model(base_model.input, model)
|
|
|
|
|
|
# 锁定卷积层
|
|
|
for layer in base_model.layers:
|
|
|
layer.trainable = False
|
|
|
```
|
|
|
|
|
|
2. 全连接层训练(v1.0)
|
|
|
|
|
|
```python
|
|
|
from base_model import model
|
|
|
|
|
|
# 设置训练集图片大小以及目录参数
|
|
|
img_size = (299, 299)
|
|
|
dataset_dir = '..\\dataset\\dataset'
|
|
|
img_save_to_dir = 'resources\\image-traing\\'
|
|
|
log_dir = 'resources\\train-log'
|
|
|
|
|
|
model_dir = 'resources\\keras-model\\'
|
|
|
|
|
|
# 使用数据增强
|
|
|
train_datagen = keras.preprocessing.image.ImageDataGenerator(
|
|
|
rescale=1. / 255,
|
|
|
shear_range=0.2,
|
|
|
width_shift_range=0.4,
|
|
|
height_shift_range=0.4,
|
|
|
rotation_range=90,
|
|
|
zoom_range=0.7,
|
|
|
horizontal_flip=True,
|
|
|
vertical_flip=True,
|
|
|
preprocessing_function=keras.applications.xception.preprocess_input)
|
|
|
|
|
|
test_datagen = keras.preprocessing.image.ImageDataGenerator(
|
|
|
preprocessing_function=keras.applications.xception.preprocess_input)
|
|
|
|
|
|
train_generator = train_datagen.flow_from_directory(
|
|
|
dataset_dir,
|
|
|
save_to_dir=img_save_to_dir,
|
|
|
target_size=img_size,
|
|
|
class_mode='categorical')
|
|
|
|
|
|
validation_generator = test_datagen.flow_from_directory(
|
|
|
dataset_dir,
|
|
|
save_to_dir=img_save_to_dir,
|
|
|
target_size=img_size,
|
|
|
class_mode='categorical')
|
|
|
|
|
|
# 早停法以及动态学习率设置
|
|
|
early_stop = EarlyStopping(monitor='val_loss', patience=13)
|
|
|
reduce_lr = ReduceLROnPlateau(monitor='val_loss', patience=7, mode='auto', factor=0.2)
|
|
|
tensorboard = keras.callbacks.tensorboard_v2.TensorBoard(log_dir=log_dir)
|
|
|
|
|
|
for layer in model.layers:
|
|
|
layer.trainable = False
|
|
|
|
|
|
# 模型编译
|
|
|
model.compile(optimizer='rmsprop', loss='categorical_crossentropy', metrics=['accuracy'])
|
|
|
|
|
|
history = model.fit_generator(train_generator,
|
|
|
steps_per_epoch=train_generator.samples // train_generator.batch_size,
|
|
|
epochs=100,
|
|
|
validation_data=validation_generator,
|
|
|
validation_steps=validation_generator.samples // validation_generator.batch_size,
|
|
|
callbacks=[early_stop, reduce_lr, tensorboard])
|
|
|
# 模型导出
|
|
|
model.save(model_dir + 'chinese_medicine_model_v1.0.h5')
|
|
|
```
|
|
|
|
|
|
3. 对于顶部的6层卷积层，我们使用数据集对权重参数进行微调
|
|
|
```python
|
|
|
# 加载模型
|
|
|
model=keras.models.load_model('resources\\keras-model\\chinese_medicine_model_v2.0.h5')
|
|
|
|
|
|
for layer in model.layers:
|
|
|
layer.trainable = False
|
|
|
for layer in model.layers[126:132]:
|
|
|
layer.trainable = True
|
|
|
|
|
|
history = model.fit_generator(train_generator,
|
|
|
steps_per_epoch=train_generator.samples // train_generator.batch_size,
|
|
|
epochs=100,
|
|
|
validation_data=validation_generator,
|
|
|
validation_steps=validation_generator.samples // validation_generator.batch_size,
|
|
|
callbacks=[early_stop, reduce_lr, tensorboard])
|
|
|
model.save(model_dir + 'chinese_medicine_model_v2.0.h5')
|
|
|
|
|
|
```
|
|
|
|
|
|
4. 服务器端，使用ONNX Runtime调用训练好的模型
|
|
|
|
|
|
- **模型概览**
|
|
|
|
|
|
[模型详细结构](medicine-doc/assets/images/model.png)
|
|
|
|
|
|
- **训练过程正确率以及损失函数可视化展示**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5. **medicine-dataset数据集**
|
|
|
- [数据集：](medicine-dataset/dataset2)像素：299*299
|
|
|
- [中药名字编码表](medicine-doc/assets/medicine_label.txt)
|
|
|
|
|
|
6. **medicine-util公用工具类**
|
|
|
|
|
|
- 关于[MongoDbUtil](medicine-util/src/main/java/cn/xiaohaoo/medicine/util/mongo/)说明
|
|
|
|
|
|
|
|
|
## 依赖环境说明
|
|
|
|
|
|
|依赖|版本|
|
|
|
|:---:|:---:|
|
|
|
|JDK|11+|
|
|
|
|Python|3.6|
|
|
|
|Gradle|6.5|
|
|
|
|TensorFlow|2.0|
|
|
|
|MongoDB|4.2.2|
|
|
|
|MySQL|8.0+|
|
|
|
|Spring Boot|2.2.2|
|
|
|
|Elasticsearch|7.4.2|
|
|
|
|IK分词器|7.4.2|
|
|
|
|ONNX Runtime|1.8.1|
|
|
|
|
|
|
## 开源软件使用须知
|
|
|
- **允许用于个人学习;**
|
|
|
- **开源版不适合商用;**
|
|
|
- **禁止将本项目的代码和资源进行任何形式的出售，产生的一切任何后果责任由侵权者自负;**
|
|
|
- **[LICENSE](LICENSE)**
|
|
|
|
|
|
|
|
|
#### 开源不易，感谢各位朋友的star！ ^_^ |
