# 人工智能

## 自定义模型识别

```python
from AI import CustomModel
```

### 模型初始化
```python
CustomModel(labels,path)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| labels | list | 标签列表，必填 |
| path | str | 模型路径，必填 |

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import CustomModel

Screen = Screen() # 画布初始化
camera = cameraPython() # 摄像头初始化

labels = ["loadModel", "unload", "left", "right", "forward", "stop"] # 标签
path = "/root/preset/model/autologistics" # 模型路径
CustomModel = CustomModel(labels,path) # 初始化模型

while True:
    canvas = camera.capture() # 获取摄像头图像
    canvas = canvas.crop(48,8,224,224) # 裁剪图像为224*224
    data = CustomModel.loadModel(canvas) # 加载模型进行识别
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=(255,0,0),thickness=1) # 在屏幕绘制检测框
        canvas.draw_string(i["X"],i["Y"]-20,(str(i["name"])+":"+str(i["score"])),color=(255,0,0)) # 在屏幕上绘制名称与置信度
    Screen.show(canvas,48,8) # 显示画布
```
其中i["X"]表示识别结果的检测框起点X轴坐标，i["Y"]表示识别结果的检测框起点Y轴坐标，i["W"]表示识别结果的检测框宽度，i["H"]表示识别结果的检测框高度，i["name"]表示识别结果的名称，i["score"]表示识别结果的置信度，i["middleX"]表示识别结果的检测框中心点的X轴坐标，i["middleY"]表示识别结果的检测框中心点的Y轴坐标。

## 边缘检测

```python
from AI import EdgeDetection
```

### 模型初始化
```python
EdgeDetection()
```

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import EdgeDetection

Screen = Screen() # 画布初始化
camera = cameraPython() # 摄像头初始化
EdgeDetection = EdgeDetection() # 初始化

while True:
    img = camera.capture() # 获取摄像头数据
    img = img.crop(48,8,224,224) # 裁剪尺寸为224*224
    canvas = EdgeDetection.loadModel(img) # 加载模型
    Screen.show(canvas,48,8) # 显示画布
```

## 人脸检测

```python
from AI import Facedetection
```

### 模型初始化
```python
Facedetection()
```

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import Facedetection

Screen = Screen() # 画布初始化
camera = cameraPython() # 摄像头初始化
face = Facedetection() # 人脸检测初始化

while True:
    canvas = camera.capture() # 获取摄像头图像
    canvas = canvas.crop(48,8,224,224) # 裁剪图像尺寸
    data = face.loadModel(canvas) # 加载人脸检测模型
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=(255,0,0), thickness=1) # 在屏幕上绘制人脸检测框
        canvas.draw_string(5,5,str(len(data)), scale = 1, color = (255,255,255) , thickness = 1) # 在屏幕上显示人脸数量
    Screen.show(canvas,48,8) # 显示画布
```

## 人脸识别

```python
from AI import FaceRecognition
```

### 模型初始化
```python
FaceRecognition()
```

### 加载模型
加载人脸检测模型，获取人脸信息
```python
loadmodel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 添加人脸
录入人脸信息保存到本地
```python
add(name,feature,dataPath)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| name | str | 识别到的人脸名称，必填 |
| feature | list | 人脸数据，必填 |
| dataPath | str | 保存路径，选填，默认为"/root/user/model/recorded_face_features.py" |

### 删除人脸
删除本地保存的最后一条人脸数据
```python
remove(name,dataPath)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| name | str | 要删除的人脸名称，必填 |
| dataPath | str | 保存路径，选填，默认为"/root/user/model/recorded_face_features.py" |

### 加载人脸信息
加载人脸采集时保存到本地的人脸信息数据
```python
loadface(DataPath)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| dataPath | str | 保存路径，选填，默认为"/root/user/model/recorded_face_features.py" |

### 样例
#### 人脸采集
```python
import time
from cocopiPython import cameraPython,Screen
from AI import FaceRecognition
from CocoPi import BUTTON

# 按钮初始化
key_C = BUTTON(13)
key_D = BUTTON(7)

Screen = Screen()
camera = cameraPython()

FaceRecognition = FaceRecognition()
People_list = ["小明","小红","小刚","小花"]

FaceNum = 0
faceScore = 0
color = (255,0,0)

while True:
    canvas = camera.capture() # 获取摄像头数据
    canvas = canvas.crop(48,8,224,224) # 裁剪图片尺寸
    data = FaceRecognition.loadmodel(canvas) # 加载人脸检测模型
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=color,thickness=1) # 检测框
        if key_C.is_pressed() and FaceNum < len(People_list):
            while not key_C.is_pressed()== False:
                time.sleep(0.01)
            FaceRecognition.add(People_list[len(FaceRecognition)],i["feature"]) # 录入人脸保存
            canvas.draw_rectangle(0,0,320,20,color=(0,0,0),thickness=-1)
            canvas.draw_string(0,0,"已采集"+str(People_list[FaceNum])+"人脸数据",scale=1,color=(255,255,255),thickness=1)
            Screen.show(canvas,48,8)
            FaceNum = FaceNum + 1
            time.sleep(1)
    if key_D.is_pressed() and FaceNum > 0:
        while not key_D.is_pressed()== False:
            time.sleep(0.01)
        FaceRecognition.remove(People_list[len(FaceRecognition)-1]) # 删除人脸
        canvas.draw_rectangle(0,0,320,20,color=(0,0,0),thickness=-1)
        canvas.draw_string(0,0,"已删除"+str(People_list[FaceNum-1])+"人脸数据",scale=1,color=(255,255,255),thickness=1)
        Screen.show(canvas,48,8)
        FaceNum = FaceNum - 1
        time.sleep(1)
    Screen.show(canvas,48,8)
```

#### 人脸识别
```python
from cocopiPython import cameraPython,Screen
from AI import FaceRecognition

Screen = Screen()
camera = cameraPython()
FaceRecognition = FaceRecognition()

faceScore = 0
color = (255,0,0)
    
while True:
    canvas = camera.capture() # 获取摄像头数据
    canvas = canvas.crop(48,8,224,224) # 裁剪图片尺寸
    data = FaceRecognition.loadmodel(canvas) # 加载人脸检测模型
    FaceRecognition.loadface()
    for i in data:
        faceScore = round(i["recognizeScore"],2)
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=color,thickness=1) # 检测框
        canvas.draw_string(i["X"],i["Y"],str(i["name"])+":"+str(faceScore),scale=1,color=color,thickness=1)
        if faceScore > 80:
            color = (0,255,0)
        else:
            color = (255,0,0)
    Screen.show(canvas,48,8)
```

#### 人脸识别+人脸采集
```python
import time
from cocopiPython import cameraPython,Screen
from AI import FaceRecognition
from CocoPi import BUTTON

# 按钮初始化
key_C = BUTTON(13)
key_D = BUTTON(7)

Screen = Screen()
camera = cameraPython()

FaceRecognition = FaceRecognition()
People_list = ["小明","小红","小刚","小花"]

FaceNum = 0
faceScore = 0
color = (255,0,0)

while True:
    canvas = camera.capture() # 获取摄像头图像
    canvas = canvas.crop(48,8,224,224) # 裁剪图片尺寸
    data = FaceRecognition.loadmodel(canvas) # 加载人脸检测模型
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=color,thickness=1) # 检测框
        if key_C.is_pressed() and FaceNum < len(People_list):
            while not key_C.is_pressed()== False:
                time.sleep(0.01)
            FaceRecognition.add(People_list[len(FaceRecognition)],i["feature"]) # 录入人脸保存
            canvas.draw_rectangle(0,0,320,20,color=(0,0,0),thickness=-1)
            canvas.draw_string(0,0,"已采集"+str(People_list[FaceNum])+"人脸数据",scale=1,color=(255,255,255),thickness=1)
            Screen.show(canvas,48,8)
            FaceNum = FaceNum + 1
            time.sleep(1)
        faceScore = round(i["recognizeScore"],2)
        if faceScore > 70:
            color = (0,255,0)
            canvas.draw_string(i["X"],i["Y"],str(i["name"])+":"+str(faceScore),scale=1,color=color,thickness=1)
        else:
            color = (255,0,0)
    if key_D.is_pressed() and FaceNum > 0:
        while not key_D.is_pressed()== False:
            time.sleep(0.01)
        FaceRecognition.remove(People_list[len(FaceRecognition)-1]) # 删除人脸
        canvas.draw_rectangle(0,0,320,20,color=(0,0,0),thickness=-1)
        canvas.draw_string(0,0,"已删除"+str(People_list[FaceNum-1])+"人脸数据",scale=1,color=(255,255,255),thickness=1)
        Screen.show(canvas,48,8)
        FaceNum = FaceNum - 1
        time.sleep(1)
    Screen.show(canvas,48,8)
```

## 数字识别

```python
from AI import Digitalecognition
```

### 模型初始化
```python
Digitalecognition()
```

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import Digitalecognition

Screen = Screen() # 画布初始化
camera = cameraPython() # 摄像头初始化
Digit = Digitalecognition() # 人脸检测初始化

while True:
    canvas = camera.capture() # 获取摄像头图像
    canvas = canvas.crop(48,8,224,224) # 裁剪图像尺寸
    data = Digit.loadModel(canvas)
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=(255,0,0),thickness=1)
        canvas.draw_string(i["X"],i["Y"]-20,(str(i["name"])+":"+str(i["score"])),color=(255,0,0))
    Screen.show(canvas,48,8)
```

## 物体检测

```python
from AI import ObjectDetection
```

### 模型初始化
```python
ObjectDetection()
```

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import ObjectDetection

Screen = Screen() # 画布初始化
camera = cameraPython() # 摄像头初始化
object = ObjectDetection() # 物体检测初始化

while True:
    canvas = camera.capture() # 获取摄像头图像
    canvas = canvas.crop(48,8,224,224) # 裁剪图像尺寸
    data = object.loadModel(canvas)
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=(255,0,0),thickness=1)
        canvas.draw_string(i["X"],i["Y"]-20,(str(i["name"])+":"+str(i["score"])),color=(255,0,0))
    Screen.show(canvas,48,8)
```

## 猜拳识别

```python
from AI import RockPaperScissors
```

### 模型初始化
```python
RockPaperScissors()
```

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import RockPaperScissors

Screen = Screen()
camera = cameraPython()
RockPaperScissors = RockPaperScissors()

while True:
    canvas = camera.capture()
    canvas = canvas.crop(48,8,224,224)
    data = RockPaperScissors.loadModel(canvas)
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=(255,0,0),thickness=1)
        canvas.draw_string(i["X"],i["Y"]-10,(str(i["name"])+":"+str(i["score"])),color=(255,0,0))
    Screen.show(canvas,48,8)
```

## 自学习识别

```python
from AI import SelfLearning
```

### 模型初始化
```python
SelfLearning(lables)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| lables | 列表 | 要识别的物体名称列表，必填 |

### 添加类别
```python
addClass(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 训练
```python
trainSave(path)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| path | string | 保存路径，选填，默认为“/root/user/model/module.bin” |

### 加载识别
```python
loadModel(img,path)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |
| path | string | 保存路径，选填，默认为“/root/user/model/module.bin” |

### 样例
#### 采集
```python
import time
from cocopiPython import cameraPython,Screen
from AI import SelfLearning
from CocoPi import BUTTON

key_C = BUTTON(13)
key_D = BUTTON(7)

Screen = Screen()
camera = cameraPython()
lables=(['鼠标','键盘','水杯'])
SL = SelfLearning(lables)

is_train = 0
count = 0
str_display = "按C键添加类别，按D键進行学习"

while True:
    # 获取摄像头数据
    canvas = camera.capture()
    canvas = canvas.crop(48,8,224,224)
    if key_C.is_pressed():
        while not key_C.is_pressed()== False:
            time.sleep(0.01)
        if count < len(lables):
            # 采集数据添加到列表中
            time.sleep(1)
            SL.addClass(canvas)
            count += 1
    if key_D.is_pressed():
        while not key_D.is_pressed()== False:
            time.sleep(0.01)
        if count >= len(lables) and is_train == 0:
            time.sleep(1)
            # 训练并保存，参数：path 为保存路径默认/root/user/model/module.bin
            SL.train()
            is_train = 1
            str_display = "学习已完成"
    canvas.draw_string(0,0,str_display,scale=1,color=(255,0,0),thickness=1)
    canvas.draw_string(0,16,"采集次数："+str(count),scale=1,color=(255,0,0),thickness=1)
    Screen.show(canvas,48,8)
```
#### 识别
```python
from cocopiPython import cameraPython,Screen
from AI import SelfLearning

Screen = Screen()
camera = cameraPython()
SL= SelfLearning(['鼠标','键盘','水杯'])
SL.load()

while True:
    # 获取摄像头数据
    img = camera.capture()
    canvas = img.crop(48,8,224,224)
    data = SL.predict(canvas)
    canvas.draw_string(0,5,(str(data["name"])+":"+str(data["score"])),scale=1,color=(255,0,0),thickness=1)
    Screen.show(canvas,48,8)
```

## 拼音识别

```python
from AI import PinyinRecognition
```

### 模型初始化
```python
PinyinRecognition(keywords)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| keywords | 列表 | 拼音参数，文字的拼音与音调，必填 |

### 获取结果
```python
getresult()
```

### 样例
```python
from cocopiPython import Screen
from AI import PinyinRecognition

Screen = Screen()
canvas = Screen.create()

keywords = [["ni3 hao3",0.1],["hao3 de1",0.1],["wan3 shang4 hao3",0.1]] # 设置拼音参数
PinyinRecognition = PinyinRecognition(keywords)

data =""
while True:
    canvas.clear()
    data = str(PinyinRecognition.getResult()) # 获取拼音识别结果
    print("jieguo:"+str(data))
    canvas.draw_string(0,0, "请对准麦克风说出指令", scale = 2, color = (255,0,0) , thickness = 1)
    if data != "None":
        canvas.draw_string(0, 30, "拼音识别结果:", scale=2, color=(255,0,0), thickness = 1)
        canvas.draw_string(30, 60, (data), scale=2, color=(255,255,255), thickness = 1)
    Screen.show(canvas)
```

## 车牌识别

```python
from AI import PlateRecognition
```

### 模型初始化
```python
PlateRecognition()
```

### 加载识别
```python
loadModel(img)
```

### 参数说明
| 参数 | 类型 | 说明 |
| :--- | :--- | :--- |
| img | image.Image() | 要识别的Image对象，必填 |

### 样例
```python
from cocopiPython import cameraPython,Screen
from AI import PlateRecognition

Screen = Screen() # 画布初始化
camera = cameraPython() # 摄像头初始化
PlateRecognition = PlateRecognition() # 车牌识别初始化
while True:
    canvas = camera.capture() # 获取摄像头图像
    canvas = canvas.crop(48,8,224,224) # 裁剪图像尺寸
    data = PlateRecognition.load(canvas) # 加载识别
    for i in data:
        canvas.draw_rectangle(i["X"],i["Y"],i["X"]+i["W"],i["Y"]+i["H"],color=(255,0,0),thickness=1) # 检测框
        canvas.draw_string(i["X"],i["Y"]-10,(str(i["name"])),color=(255,0,0)) # 名称
    Screen.show(canvas,48,8) # 显示
```