对单个文件进行整合

TM.py

@@ -134,65 +134,45 @@ class HandDetector:
 class Main:
     def __init__(self):
         self.detector = None
-        self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
+        self.camera = None
-        self.camera.set(3, 1280)
+        # self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
-        self.camera.set(4, 720)
+        # self.camera.set(3, 1280)
+        # self.camera.set(4, 720)
 
-    def gesture_recognition(self):
+    def gesture_recognition(self, img, detector):
-        self.detector = HandDetector()
+        self.detector = detector
-        while True:
+        lm_list, bbox = detector.find_position(img)
-            frame, img = self.camera.read()
-            img = self.detector.find_hands(img)
-            lm_list, bbox = self.detector.find_position(img)
 
-            if lm_list:
+        if lm_list:
-                x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
+            x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
-                x1, x2, x3, x4, x5 = self.detector.fingers_up()
+            x1, x2, x3, x4, x5 = detector.fingers_up()
-                if (np.linalg.norm(lm_list[4]-lm_list[8]) < 50) and (np.linalg.norm(lm_list[4]-lm_list[12]) < 50):
+            if (np.linalg.norm(lm_list[4]-lm_list[8]) < 50) and (np.linalg.norm(lm_list[4]-lm_list[12]) < 50):
-                    cv2.putText(img, "7_SEVEN", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "7_SEVEN", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (np.linalg.norm(lm_list[4]-lm_list[8]) < 50) and (x4 == 1 and x5 == 1 and x3 == 1):
+            elif (x2 == 1 and x3 == 1) and (x4 == 0 and x5 == 0 and x1 == 0):
-                    cv2.putText(img, "OK", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "2_TWO", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (np.linalg.norm(lm_list[4]-lm_list[12]) < 50) and (x4 == 1 and x5 == 1 and x2 == 1):
+            elif (x2 == 1 and x3 == 1 and x4 == 1) and (x1 == 0 and x5 == 0):
-                    cv2.putText(img, "flip", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "3_THREE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (x2 == 1 and x3 == 1) and (x4 == 0 and x5 == 0 and x1 == 0):
+            elif (x2 == 1 and x3 == 1 and x4 == 1 and x5 == 1) and (x1 == 0):
-                    cv2.putText(img, "2_TWO", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "4_FOUR", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (x2 == 1 and x3 == 1 and x4 == 1) and (x1 == 0 and x5 == 0):
+            elif x1 == 1 and x2 == 1 and x3 == 1 and x4 == 1 and x5 == 1:
-                    cv2.putText(img, "3_THREE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "5_FIVE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (x2 == 1 and x3 == 1 and x4 == 1 and x5 == 1) and (x1 == 0):
+            elif (x2 == 1 and x1 == 0) and (x3 == 0 and x4 == 0 and x5 == 0):
-                    cv2.putText(img, "4_FOUR", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "1_ONE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif x1 == 1 and x2 == 1 and x3 == 1 and x4 == 1 and x5 == 1:
+            elif (x1 == 1 and x2 == 1) and (x3 == 0 and x4 == 0 and x5 == 0):
-                    cv2.putText(img, "5_FIVE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "8_EIGHT", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (x2 == 1 and x1 == 0) and (x3 == 0 and x4 == 0 and x5 == 0):
+            elif (x1 == 1 and x5 == 1) and (x3 == 0 and x4 == 0 and x2 == 0):
-                    cv2.putText(img, "1_ONE", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, "6_SIX", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                elif (x1 == 1 and x2 == 1) and (x3 == 0 and x4 == 0 and x5 == 0):
+            else:
-                    cv2.putText(img, "8_EIGHT", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                return 1
-                                (0, 0, 255), 3)
+        return 0
-                elif (x1 == 1 and x5 == 1) and (x3 == 0 and x4 == 0 and x2 == 0):
-                    cv2.putText(img, "6_SIX", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
-                elif x1 and (x2 == 0 and x3 == 0 and x4 == 0 and x5 == 0):
-                    cv2.putText(img, "GOOD!", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
-                elif (x1 == 1 and x2 == 1 and x5 == 1) and (x3 == 0 and x4 == 0):
-                    cv2.putText(img, "yo", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
-                else:
-                    cv2.putText(img, "unknown", (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
-            cv2.imshow("camera", img)
-            key = cv2.waitKey(1)
-            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
-                break
-            elif key == 27:
-                break
 
 
 if __name__ == '__main__':

ai.py

@@ -6,13 +6,12 @@
 @ by: Leaf
 @ date: 2022-05-28
 """
-
+import tkinter as tk
 import cv2
 import mediapipe as mp
 import torch
 import torch.nn as nn
 import numpy as np
-import tkinter as tk
 import shutil
 import math
 from scipy import stats
@@ -33,7 +32,7 @@ def rotate(angle, x, y, point_x, point_y):
 def normalize(x):
     max_x = np.max(x)
     min_x = np.min(x)
-    return (x-min_x)/(max_x-min_x)
+    return (x - min_x) / (max_x - min_x)
 
 
 class CNN(nn.Module):
@@ -57,7 +56,7 @@ class CNN(nn.Module):
             nn.MaxPool2d(2),
         )
         self.med = nn.Linear(32 * 11 * 2, 500)
-        self.med2 = nn.Linear(1*21*3, 100)
+        self.med2 = nn.Linear(1 * 21 * 3, 100)
         self.med3 = nn.Linear(100, 500)
         self.out = nn.Linear(500, m)  # fully connected layer, output 10 classes
 
@@ -285,6 +284,23 @@ class Main:
         self.len_x = 22
         self.len_y = 4
         self.label = ''
+        self.result = []
+        self.disp = ""
+
+    def change_state(self):
+        self.label = self.entry.get()  # 调用get()方法，将Entry中的内容获取出来
+        self.top1.quit()
+        if self.label == "":
+            self.top1.destroy()
+
+    def make_datasets(self, camera, datasets_dir="default", n=100):
+        if datasets_dir == "default":
+            return
+        if exists(datasets_dir):
+            shutil.rmtree(datasets_dir)
+        mkdir(datasets_dir)
+        self.camera = camera
+
         self.top1 = tk.Tk()
         self.top1.geometry('300x50')
         self.top1.title('请输入标签')
@@ -293,22 +309,6 @@ class Main:
         self.entry.place(x=80, y=10)
         tk.Button(self.top1, text='确定', command=self.change_state).place(x=235, y=5)
 
-    def change_state(self):
-        self.label = self.entry.get()  # 调用get()方法，将Entry中的内容获取出来
-        self.top1.quit()
-        if self.label == "":
-            self.top1.destroy()
-
-    def make_datasets(self, datasets_dir="default", n=100):
-        if datasets_dir == "default":
-            return
-        if exists(datasets_dir):
-            shutil.rmtree(datasets_dir)
-        mkdir(datasets_dir)
-        if self.camera is None:
-            self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
-            self.camera.set(3, 1280)
-            self.camera.set(4, 720)
         self.top1.mainloop()
         while not self.label == "":
             data = np.zeros([n, self.len_x, self.len_y])
@@ -349,7 +349,6 @@ class Main:
             open(datasets_dir + "/" + self.label + ".npz", "w")
             np.savez(datasets_dir + "/" + self.label + ".npz", label=self.label, data=data,
                      handtype=hand_type, shape=shape_list)
-
             self.top1.mainloop()
 
     def train(self, datasets_dir="default"):
@@ -359,21 +358,75 @@ class Main:
         ai.load_datasets()
         ai.train_cnn()
 
-    def gesture_recognition(self):
+    def gesture_recognition_camera(self, detector, img, cnn):
-        if self.camera is None:
+        self.detector = detector
-            self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
+        out_label = cnn.out_label
-            self.camera.set(3, 1280)
+        img = self.detector.find_hands(img)
-            self.camera.set(4, 720)
+        lm_list, bbox = self.detector.find_position(img)
+
+        if lm_list.any():
+            x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
+            data = torch.Tensor(lm_list)
+            data = data.unsqueeze(0)
+            data = data.unsqueeze(0)
+
+            test_output = cnn(data)
+            self.result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
+            if len(self.result) > 5:
+                self.disp = str(out_label[stats.mode(self.result)[0][0]])
+                self.result = []
+
+            cv2.putText(img, self.disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                        (0, 0, 255), 3)
+
+    def gesture_recognition_video(self, filedir):
         self.detector = HandDetector()
         cnn = torch.load("CNN.pkl")
         out_label = cnn.out_label
         result = []
         disp = ""
+        cap = cv2.VideoCapture(filedir)
         while True:
-            frame, img = self.camera.read()
+            ret, img = cap.read()
             img = self.detector.find_hands(img)
             lm_list, bbox = self.detector.find_position(img)
 
+            if lm_list.any():
+                x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
+                data = torch.Tensor(lm_list)
+                data = data.unsqueeze(0)
+                data = data.unsqueeze(0)
+
+                test_output = cnn(data)
+                result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
+
+                if len(result) > 5:
+                    disp = str(out_label[stats.mode(result)[0][0]])
+                    result = []
+
+                cv2.putText(img, disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                            (0, 0, 255), 3)
+
+            cv2.imshow("camera", img)
+            key = cv2.waitKey(1)
+            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
+                break
+            elif key == 27:
+                break
+        cap.release()
+
+    def gesture_recognition_img(self, filedir):
+        self.detector = HandDetector()
+        cnn = torch.load("CNN.pkl")
+        out_label = cnn.out_label
+        result = []
+        disp = ""
+        img = cv2.imread(filedir)
+        img = self.detector.find_hands(img)
+        while True:
+
+            lm_list, bbox = self.detector.find_position(img)
+
             if lm_list.any():
                 x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
                 data = torch.Tensor(lm_list)
@@ -402,4 +455,8 @@ if __name__ == '__main__':
     my_datasets_dir = "test"
     solution.make_datasets(my_datasets_dir, 100)
     solution.train(my_datasets_dir)
-    solution.gesture_recognition()
+    dir_video = "C:/Users/Liar/Pictures/Camera Roll/WIN_20220630_20_11_47_Pro.mp4"
+    dir_img = "C:/Users/Liar/Pictures/Camera Roll/WIN_20220630_20_01_22_Pro.jpg"
+    # solution.gesture_recognition_camera()
+    # solution.gesture_recognition_video(dir_video)
+    # solution.gesture_recognition_img(dir_img)

ai_UI.py

@@ -1,476 +0,0 @@
-# -*- coding:utf-8 -*-
-
-"""
-信号设计课程小组设计
-
-@ by: Leaf
-@ date: 2022-05-28
-"""
-import tkinter as tk
-import cv2
-import mediapipe as mp
-import torch
-import torch.nn as nn
-import numpy as np
-import shutil
-import math
-from scipy import stats
-from os.path import exists
-from os import mkdir
-from pathlib import Path
-from torch.utils.data import DataLoader, TensorDataset
-
-
-# 旋转函数
-def rotate(angle, x, y, point_x, point_y):
-    px = (x - point_x) * math.cos(angle) - (y - point_y) * math.sin(angle) + point_x
-    py = (x - point_x) * math.sin(angle) + (y - point_y) * math.cos(angle) + point_y
-    return px, py
-
-
-# 归一化
-def normalize(x):
-    max_x = np.max(x)
-    min_x = np.min(x)
-    return (x - min_x) / (max_x - min_x)
-
-
-class CNN(nn.Module):
-    def __init__(self, m):
-        super(CNN, self).__init__()
-        self.out_label = []
-        self.conv1 = nn.Sequential(
-            nn.Conv2d(
-                in_channels=1,
-                out_channels=16,
-                kernel_size=5,
-                stride=1,
-                padding=2,
-            ),
-            nn.ReLU(),
-            nn.MaxPool2d(kernel_size=1),
-        )
-        self.conv2 = nn.Sequential(
-            nn.Conv2d(16, 32, 5, 1, 2),
-            nn.ReLU(),
-            nn.MaxPool2d(2),
-        )
-        self.med = nn.Linear(32 * 11 * 2, 500)
-        self.med2 = nn.Linear(1 * 21 * 3, 100)
-        self.med3 = nn.Linear(100, 500)
-        self.out = nn.Linear(500, m)  # fully connected layer, output 10 classes
-
-    def forward(self, x):
-        x = self.conv1(x)
-        x = self.conv2(x)
-        x = x.view(x.size(0), -1)  # 展平多维的卷积图成 (batch_size, 32 * 7 * 7)
-        x = self.med(x)
-        # x = self.med2(x)
-        # x = self.med3(x)
-        output = self.out(x)
-        return output
-
-
-class HandDetector:
-    """
-    使用mediapipe库查找手。导出地标像素格式。添加了额外的功能。
-    如查找方式，许多手指向上或两个手指之间的距离。而且提供找到的手的边界框信息。
-    """
-
-    def __init__(self, mode=False, max_hands=2, detection_con=0.5, min_track_con=0.5):
-        """
-        :param mode: 在静态模式下，对每个图像进行检测
-        :param max_hands: 要检测的最大手数
-        :param detection_con: 最小检测置信度
-        :param min_track_con: 最小跟踪置信度
-        """
-        self.results = None
-        self.mode = mode
-        self.max_hands = max_hands
-        self.modelComplex = 1
-        self.detection_con = detection_con
-        self.min_track_con = min_track_con
-
-        # 初始化手部的识别模型
-        self.mpHands = mp.solutions.hands
-        self.hands = self.mpHands.Hands(static_image_mode=self.mode,
-                                        max_num_hands=self.max_hands,
-                                        min_detection_confidence=self.detection_con,
-                                        min_tracking_confidence=self.min_track_con)
-        self.mpDraw = mp.solutions.drawing_utils  # 初始化绘图器
-        self.tipIds = [4, 8, 12, 16, 20]  # 指尖列表
-        self.fingers = []
-        self.lmList = []
-        self.re_lmList = []
-
-    def find_hands(self, img, draw=True):
-        """
-        从图像(BRG)中找到手部。
-        :param img: 用于查找手的图像。
-        :param draw: 在图像上绘制输出的标志。
-        :return: 带或不带图形的图像
-        """
-        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)  # 将传入的图像由BGR模式转标准的Opencv模式——RGB模式，
-        self.results = self.hands.process(img_rgb)
-
-        if self.results.multi_hand_landmarks:
-            for handLms in self.results.multi_hand_landmarks:
-                if draw:
-                    self.mpDraw.draw_landmarks(img, handLms,
-                                               self.mpHands.HAND_CONNECTIONS)
-        return img
-
-    def find_position(self, img, hand_no=0, draw=True):
-        """
-        查找单手的地标并将其放入列表中像素格式。还可以返回手部的周围的边界框。
-        :param img: 要查找的主图像
-        :param hand_no: 如果检测到多只手，则为手部id
-        :param draw: 在图像上绘制输出的标志。(默认绘制矩形框)
-        :return: 像素格式的手部关节位置列表；手部边界框
-        """
-        x_list = []
-        y_list = []
-        bbox_info = []
-        self.lmList = []
-        h, w, c = img.shape
-        if self.results.multi_hand_landmarks:
-            my_hand = self.results.multi_hand_landmarks[hand_no]
-            for i, lm in enumerate(my_hand.landmark):
-                px, py = int(lm.x * w), int(lm.y * h)
-                x_list.append(px)
-                y_list.append(py)
-                self.lmList.append([lm.x, lm.y, 0])
-                if draw:
-                    cv2.circle(img, (px, py), 5, (255, 0, 255), cv2.FILLED)
-            x_min, x_max = min(x_list), max(x_list)
-            y_min, y_max = min(y_list), max(y_list)
-            box_w, box_h = x_max - x_min, y_max - y_min
-            bbox = x_min, y_min, box_w, box_h
-            cx, cy = bbox[0] + (bbox[2] // 2), bbox[1] + (bbox[3] // 2)
-            bbox_info = {"id": hand_no, "bbox": bbox, "center": (cx, cy), "shape": (h, w)}
-
-            if draw:
-                cv2.rectangle(img, (bbox[0] - 20, bbox[1] - 20),
-                              (bbox[0] + bbox[2] + 20, bbox[1] + bbox[3] + 20),
-                              (0, 255, 0), 2)
-
-        self.revolve(img)
-        self.re_lmList = np.array(self.re_lmList)
-        if self.re_lmList.any():
-            self.re_lmList = np.concatenate((np.zeros((21, 1)), self.re_lmList), axis=1)
-            self.re_lmList = np.concatenate((self.re_lmList, np.zeros((1, 4))), axis=0)
-
-        return self.re_lmList, bbox_info
-
-    def revolve(self, img, draw=True):
-        """
-            旋转手势识别点
-            :param img: 要查找的主图像
-            :param draw: 在图像上绘制输出的标志。(默认绘制矩形框)
-            :return: 像素格式的手部关节位置列表
-        """
-        h, w, c = img.shape
-        if len(self.lmList) >= 21:
-            # print(self.lmList)
-            self.re_lmList = []
-            point_x = self.lmList[0][0]
-            point_y = self.lmList[0][1]
-            delta_x = self.lmList[13][0] - point_x
-            delta_y = self.lmList[13][1] - point_y
-            if delta_y == 0:
-                if delta_x < 0:
-                    theta = math.pi / 2
-                else:
-                    theta = -math.pi / 2
-            else:
-                theta = math.atan(delta_x / delta_y)
-                if delta_y > 0:
-                    theta = theta + math.pi
-            # print(theta*180/math.pi)
-            for i in self.lmList:
-                px, py = rotate(theta, i[0] * w, i[1] * h, point_x * w, point_y * h)
-                self.re_lmList.append([px, py, 0])
-                if draw:
-                    cv2.circle(img, (int(px), int(py)), 5, (0, 0, 255), cv2.FILLED)
-            # 归一化
-            x_array = normalize(np.array(self.re_lmList)[:, 0])
-            # print(x_array)
-            for i in range(len(x_array)):
-                self.re_lmList[i][0] = x_array[i]
-            y_array = normalize(np.array(self.re_lmList)[:, 1])
-            for i in range(len(y_array)):
-                self.re_lmList[i][1] = x_array[i]
-        else:
-            self.re_lmList = self.lmList
-        return self.re_lmList
-
-    def hand_type(self):
-        """
-        检查传入的手部 是左还是右
-        :return: 1 或 0
-        """
-        if self.results.multi_hand_landmarks:
-            if self.lmList[17][0] < self.lmList[5][0]:
-                return 1
-            else:
-                return 0
-
-
-class AI:
-    def __init__(self, datasets_dir):
-        self.EPOCH = 20
-        self.BATCH_SIZE = 2
-        self.LR = 10e-5
-        self.DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-        self.datasets_dir = datasets_dir
-        self.train_loader = None
-        self.m = 0
-        self.out_label = []  # CNN网络输出后数字标签转和字符串标签的映射关系
-
-    def load_datasets(self):
-        train_data = []
-        train_label = []
-        self.m = 0
-        for file in Path(self.datasets_dir).rglob("*.npz"):
-            data = np.load(str(file))
-            train_data.append(data["data"])
-            label_number = np.ones(len(data["data"])) * len(self.out_label)
-            train_label.append(label_number)
-            self.out_label.append(data["label"])
-            self.m += 1
-        train_data = torch.Tensor(np.concatenate(train_data, axis=0))
-        train_data = train_data.unsqueeze(1)
-        train_label = torch.tensor(np.concatenate(train_label, axis=0)).long()
-
-        dataset = TensorDataset(train_data, train_label)
-        self.train_loader = DataLoader(dataset, batch_size=self.BATCH_SIZE, shuffle=True)
-        return self.m
-
-    def train_cnn(self):
-        cnn = CNN(self.m).to(self.DEVICE)
-        optimizer = torch.optim.Adam(cnn.parameters(), self.LR)  # optimize all cnn parameters
-        loss_func = nn.CrossEntropyLoss()  # the target label is not one-hotted
-
-        for epoch in range(self.EPOCH):
-            for step, (data, target) in enumerate(self.train_loader):
-                # 分配 batch data, normalize x when iterate train_loader
-                data, target = data.to(self.DEVICE), target.to(self.DEVICE)
-                output = cnn(data)  # cnn output
-                loss = loss_func(output, target)  # cross entropy loss
-                optimizer.zero_grad()  # clear gradients for this training step
-                loss.backward()  # backpropagation, compute gradients
-                optimizer.step()  # apply gradients
-                if (step + 1) % 50 == 0:  # 输出结果
-                    print(
-                        "\r[Epoch: %d] [%d/%d (%0.f %%)][Loss: %f]"
-                        % (
-                            epoch + 1,
-                            (step + 1) * len(data),
-                            len(self.train_loader.dataset),
-                            100. * (step + 1) / len(self.train_loader),
-                            loss.item()
-                        ), end="")
-
-        cnn.out_label = self.out_label
-        torch.save(cnn, 'CNN.pkl')
-        print("训练结束")
-
-
-class Main:
-    def __init__(self):
-        self.camera = None
-        self.detector = HandDetector()
-        self.default_datasets = "Datasets"
-        self.len_x = 22
-        self.len_y = 4
-        self.label = ''
-        self.top1 = tk.Tk()
-        self.top1.geometry('300x50')
-        self.top1.title('请输入标签')
-        tk.Label(self.top1, text='Label:').place(x=27, y=10)
-        self.entry = tk.Entry(self.top1, width=15)
-        self.entry.place(x=80, y=10)
-        tk.Button(self.top1, text='确定', command=self.change_state).place(x=235, y=5)
-
-    def change_state(self):
-        self.label = self.entry.get()  # 调用get()方法，将Entry中的内容获取出来
-        self.top1.quit()
-        if self.label == "":
-            self.top1.destroy()
-
-    def make_datasets(self, datasets_dir="default", n=100):
-        if datasets_dir == "default":
-            return
-        if exists(datasets_dir):
-            shutil.rmtree(datasets_dir)
-        mkdir(datasets_dir)
-        if self.camera is None:
-            self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
-            self.camera.set(3, 1280)
-            self.camera.set(4, 720)
-        self.top1.mainloop()
-        while not self.label == "":
-            data = np.zeros([n, self.len_x, self.len_y])
-            shape_list = np.zeros([n, 2], dtype=np.int16)
-            hand_type = np.zeros(n, dtype=np.int8)
-
-            count = 0
-            cv2.startWindowThread()
-            while True:
-                frame, img = self.camera.read()
-                img = self.detector.find_hands(img)
-                result = np.zeros((self.len_x, self.len_y))
-
-                lm_list, bbox = self.detector.find_position(img)
-                for i in range(len(lm_list)):
-                    result[i] = np.array(lm_list[i])
-                if result.sum() > 0:  # 假设矩阵不为0，即捕捉到手部时
-
-                    shape = bbox["shape"]
-                    x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
-                    data[count] = result
-                    hand_type[count] = self.detector.hand_type()
-                    shape_list[count] = np.array(shape)
-                    count += 1
-                    cv2.putText(img, str("{}/{}".format(count, n)), (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 255, 0), 3)
-
-                cv2.imshow("camera", img)
-                key = cv2.waitKey(100)
-                if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
-                    break
-                elif key == 27:
-                    break
-                elif count == n - 1:
-                    break
-            cv2.destroyAllWindows()
-
-            open(datasets_dir + "/" + self.label + ".npz", "w")
-            np.savez(datasets_dir + "/" + self.label + ".npz", label=self.label, data=data,
-                     handtype=hand_type, shape=shape_list)
-            self.top1.mainloop()
-
-    def train(self, datasets_dir="default"):
-        if datasets_dir == "default":
-            datasets_dir = self.default_datasets
-        ai = AI(datasets_dir)
-        ai.load_datasets()
-        ai.train_cnn()
-
-    def gesture_recognition_camera(self):
-        if self.camera is None:
-            self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
-            self.camera.set(3, 1280)
-            self.camera.set(4, 720)
-        self.detector = HandDetector()
-        cnn = torch.load("CNN.pkl")
-        out_label = cnn.out_label
-        result = []
-        disp = ""
-        while True:
-            frame, img = self.camera.read()
-            img = self.detector.find_hands(img)
-            lm_list, bbox = self.detector.find_position(img)
-
-            if lm_list.any():
-                x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
-                data = torch.Tensor(lm_list)
-                data = data.unsqueeze(0)
-                data = data.unsqueeze(0)
-
-                test_output = cnn(data)
-                result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
-                if len(result) > 5:
-                    disp = str(out_label[stats.mode(result)[0][0]])
-                    result = []
-
-                cv2.putText(img, disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                            (0, 0, 255), 3)
-
-            cv2.imshow("camera", img)
-            key = cv2.waitKey(1)
-            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
-                break
-            elif key == 27:
-                break
-
-    def gesture_recognition_video(self, filedir):
-        self.detector = HandDetector()
-        cnn = torch.load("CNN.pkl")
-        out_label = cnn.out_label
-        result = []
-        disp = ""
-        cap = cv2.VideoCapture(filedir)
-        while True:
-            ret, img = cap.read()
-            img = self.detector.find_hands(img)
-            lm_list, bbox = self.detector.find_position(img)
-
-            if lm_list.any():
-                x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
-                data = torch.Tensor(lm_list)
-                data = data.unsqueeze(0)
-                data = data.unsqueeze(0)
-
-                test_output = cnn(data)
-                result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
-                if len(result) > 5:
-                    disp = str(out_label[stats.mode(result)[0][0]])
-                    result = []
-
-                cv2.putText(img, disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                            (0, 0, 255), 3)
-
-            cv2.imshow("camera", img)
-            key = cv2.waitKey(1)
-            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
-                break
-            elif key == 27:
-                break
-        cap.release()
-
-
-    def gesture_recognition_img(self, filedir):
-        self.detector = HandDetector()
-        cnn = torch.load("CNN.pkl")
-        out_label = cnn.out_label
-        result = []
-        disp = ""
-        img = cv2.imread(filedir)
-        img = self.detector.find_hands(img)
-        while True:
-
-            lm_list, bbox = self.detector.find_position(img)
-
-            if lm_list.any():
-                x_1, y_1 = bbox["bbox"][0], bbox["bbox"][1]
-                data = torch.Tensor(lm_list)
-                data = data.unsqueeze(0)
-                data = data.unsqueeze(0)
-
-                test_output = cnn(data)
-                result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
-                if len(result) > 5:
-                    disp = str(out_label[stats.mode(result)[0][0]])
-                    result = []
-
-                cv2.putText(img, disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                            (0, 0, 255), 3)
-
-            cv2.imshow("camera", img)
-            key = cv2.waitKey(1)
-            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
-                break
-            elif key == 27:
-                break
-
-if __name__ == '__main__':
-    solution = Main()
-    my_datasets_dir = "test"
-    # solution.make_datasets(my_datasets_dir, 100)
-    # solution.train(my_datasets_dir)
-    dir_video = "C:/Users/Liar/Pictures/Camera Roll/WIN_20220630_20_11_47_Pro.mp4"
-    dir_img = "C:/Users/Liar/Pictures/Camera Roll/WIN_20220630_20_01_22_Pro.jpg"
-    solution.gesture_recognition_camera()
-    # solution.gesture_recognition_video(dir_video)
-    # solution.gesture_recognition_img(dir_img)

ai_two.py

@@ -36,9 +36,9 @@ def normalize(x):
     return (x-min_x)/(max_x-min_x)
 
 
-class CNN(nn.Module):
+class CNNTwo(nn.Module):
     def __init__(self, m):
-        super(CNN, self).__init__()
+        super(CNNTwo, self).__init__()
         self.out_label = []
         self.conv1 = nn.Sequential(
             nn.Conv2d(
@@ -250,7 +250,7 @@ class AI:
         return self.m
 
     def train_cnn(self):
-        cnn = CNN(self.m).to(self.DEVICE)
+        cnn = CNNTwo(self.m).to(self.DEVICE)
         optimizer = torch.optim.Adam(cnn.parameters(), self.LR)  # optimize all cnn parameters
         loss_func = nn.CrossEntropyLoss()  # the target label is not one-hotted
 
@@ -275,7 +275,7 @@ class AI:
                         ), end="")
 
         cnn.out_label = self.out_label
-        torch.save(cnn, 'CNN.pkl')
+        torch.save(cnn, 'CNN_two.pkl')
         print("训练结束")
 
 
@@ -287,13 +287,9 @@ class Main:
         self.len_x = 44
         self.len_y = 4
         self.label = ''
-        self.top1 = tk.Tk()
+
-        self.top1.geometry('300x50')
+        self.result = []
-        self.top1.title('请输入标签')
+        self.disp = ""
-        tk.Label(self.top1, text='Label:').place(x=27, y=10)
-        self.entry = tk.Entry(self.top1, width=15)
-        self.entry.place(x=80, y=10)
-        tk.Button(self.top1, text='确定', command=self.change_state).place(x=235, y=5)
 
     def change_state(self):
         self.label = self.entry.get()  # 调用get()方法，将Entry中的内容获取出来
@@ -301,16 +297,27 @@ class Main:
         if self.label == "":
             self.top1.destroy()
 
-    def make_datasets(self, datasets_dir="default", n=100):
+    def on_closing(self):
+        self.label = ""
+        self.top1.destroy()
+
+    def make_datasets(self, camera, datasets_dir="default", n=100):
         if datasets_dir == "default":
             return
         if exists(datasets_dir):
             shutil.rmtree(datasets_dir)
         mkdir(datasets_dir)
-        if self.camera is None:
+        self.camera = camera
-            self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
+
-            self.camera.set(3, 1280)
+        self.top1 = tk.Tk()
-            self.camera.set(4, 720)
+        self.top1.geometry('300x50')
+        self.top1.title('请输入标签')
+        self.top1.protocol("WM_DELETE_WINDOW", self.on_closing)
+        tk.Label(self.top1, text='Label:').place(x=27, y=10)
+        self.entry = tk.Entry(self.top1, width=15)
+        self.entry.place(x=80, y=10)
+        tk.Button(self.top1, text='确定', command=self.change_state).place(x=235, y=5)
+
         self.top1.mainloop()
         while not self.label == "":
             data = np.zeros([n, self.len_x, self.len_y])
@@ -369,47 +376,34 @@ class Main:
         ai.load_datasets()
         ai.train_cnn()
 
-    def gesture_recognition(self):
+    def gesture_recognition(self, detector, img, cnn):
-        if self.camera is None:
+        self.detector = detector
-            self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
-            self.camera.set(3, 1280)
-            self.camera.set(4, 720)
-        self.detector = HandDetector()
-        cnn = torch.load("CNN.pkl")
         out_label = cnn.out_label
-        result = []
+        img, is_two_hand = self.detector.find_hands(img)
-        disp = ""
+        if is_two_hand:
-        while True:
+            lm_list1, bbox1 = self.detector.find_position(img, 0)
-            frame, img = self.camera.read()
+            lm_list2, bbox2 = self.detector.find_position(img, 1)
-            img, is_two_hand = self.detector.find_hands(img)
+            if lm_list1.any() and lm_list2.any():
-            if is_two_hand:
+                x_1, y_1 = bbox1["bbox"][0], bbox1["bbox"][1]
-                lm_list1, bbox1 = self.detector.find_position(img, 0)
+                x_2, y_2 = bbox2["bbox"][0], bbox2["bbox"][1]
-                lm_list2, bbox2 = self.detector.find_position(img, 1)
+                lm_list = np.concatenate((lm_list1, lm_list2), axis=0)
-                if lm_list1.any() and lm_list2.any():
+                data = torch.Tensor(lm_list)
-                    x_1, y_1 = bbox1["bbox"][0], bbox1["bbox"][1]
+                data = data.unsqueeze(0)
-                    x_2, y_2 = bbox2["bbox"][0], bbox2["bbox"][1]
+                data = data.unsqueeze(0)
-                    lm_list = np.concatenate((lm_list1, lm_list2), axis=0)
-                    data = torch.Tensor(lm_list)
-                    data = data.unsqueeze(0)
-                    data = data.unsqueeze(0)
 
-                    test_output = cnn(data)
+                test_output = cnn(data)
-                    result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
+                self.result.append(torch.max(test_output, 1)[1].data.cpu().numpy()[0])
-                    if len(result) > 4:
+                if len(self.result) > 4:
-                        disp = str(out_label[stats.mode(result)[0][0]])
+                    self.disp = str(out_label[stats.mode(self.result)[0][0]])
-                        result = []
+                    self.result = []
 
-                    cv2.putText(img, disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, self.disp, (x_1, y_1), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-                    cv2.putText(img, disp, (x_2, y_2), cv2.FONT_HERSHEY_PLAIN, 3,
+                cv2.putText(img, self.disp, (x_2, y_2), cv2.FONT_HERSHEY_PLAIN, 3,
-                                (0, 0, 255), 3)
+                            (0, 0, 255), 3)
-
+        else:
-            cv2.imshow("camera", img)
+            return 1
-            key = cv2.waitKey(1)
+        return 0
-            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
-                break
-            elif key == 27:
-                break
 
 
 if __name__ == '__main__':

gr.py

@@ -0,0 +1,165 @@
+import TM
+import ai
+import ai_two
+import cv2
+import torch
+import torch.nn as nn
+
+
+class CNN(nn.Module):
+    def __init__(self, m):
+        super(CNN, self).__init__()
+        self.out_label = []
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=1,
+                out_channels=16,
+                kernel_size=5,
+                stride=1,
+                padding=2,
+            ),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=1),
+        )
+        self.conv2 = nn.Sequential(
+            nn.Conv2d(16, 32, 5, 1, 2),
+            nn.ReLU(),
+            nn.MaxPool2d(2),
+        )
+        self.med = nn.Linear(32 * 11 * 2, 500)
+        self.med2 = nn.Linear(1 * 21 * 3, 100)
+        self.med3 = nn.Linear(100, 500)
+        self.out = nn.Linear(500, m)  # fully connected layer, output 10 classes
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.conv2(x)
+        x = x.view(x.size(0), -1)  # 展平多维的卷积图成 (batch_size, 32 * 7 * 7)
+        x = self.med(x)
+        # x = self.med2(x)
+        # x = self.med3(x)
+        output = self.out(x)
+        return output
+
+
+class CNNTwo(nn.Module):
+    def __init__(self, m):
+        super(CNNTwo, self).__init__()
+        self.out_label = []
+        self.conv1 = nn.Sequential(
+            nn.Conv2d(
+                in_channels=1,
+                out_channels=16,
+                kernel_size=5,
+                stride=1,
+                padding=2,
+            ),
+            nn.ReLU(),
+            nn.MaxPool2d(kernel_size=2),
+        )
+        self.conv2 = nn.Sequential(
+            nn.Conv2d(16, 32, 5, 1, 2),
+            nn.ReLU(),
+            nn.MaxPool2d(2),
+        )
+        self.med = nn.Linear(32 * 11 * 1, 500)
+        self.med2 = nn.Linear(1*21*3, 100)
+        self.med3 = nn.Linear(100, 500)
+        self.out = nn.Linear(500, m)  # fully connected layer, output 10 classes
+
+    def forward(self, x):
+        x = self.conv1(x)
+        x = self.conv2(x)
+        x = x.view(x.size(0), -1)  # 展平多维的卷积图成 (batch_size, 32 * 7 * 7)
+        x = self.med(x)
+        # x = self.med2(x)
+        # x = self.med3(x)
+        output = self.out(x)
+        return output
+
+
+class Main:
+    def __init__(self):
+        self.camera = cv2.VideoCapture(0, cv2.CAP_DSHOW)
+        self.camera.set(3, 1280)
+        self.camera.set(4, 720)
+
+        self.tm_detector = TM.HandDetector()
+        self.ai_detector = ai.HandDetector()
+        self.at_detector = ai_two.HandDetector()
+
+        self.tm_main = TM.Main()
+        self.ai_main = ai.Main()
+        self.at_main = ai_two.Main()
+
+    def gr_img(self, filedir, diy):
+        print(filedir)
+        img = cv2.imread(filedir)
+        if diy:
+            cnn = torch.load("CNN.pkl")
+            cnn_two = torch.load("CNN_two.pkl")
+        tm_img = self.tm_detector.find_hands(img)
+        while True:
+            is_one_hand = self.at_main.gesture_recognition(self.at_detector, img, cnn_two)
+            if is_one_hand:
+                not_match = self.ai_main.gesture_recognition_camera(self.ai_detector, img, cnn)
+                if not_match:
+                    self.tm_main.gesture_recognition(tm_img, self.tm_detector)
+
+            cv2.imshow("camera", img)
+            key = cv2.waitKey(1)
+            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
+                break
+            elif key == 27:
+                break
+
+    def gr_video(self, filedir, diy):
+        cap = cv2.VideoCapture(filedir)
+        if diy:
+            cnn = torch.load("CNN.pkl")
+            cnn_two = torch.load("CNN_two.pkl")
+        while True:
+            ret, img = cap.read()
+            tm_status = self.tm_main.gesture_recognition(self.tm_detector.find_hands(img), self.tm_detector)
+            if tm_status and diy:
+                is_one_hand = self.at_main.gesture_recognition(self.at_detector, img, cnn_two)
+                if is_one_hand:
+                    self.ai_main.gesture_recognition_camera(self.ai_detector, img, cnn)
+
+            cv2.imshow("camera", img)
+            key = cv2.waitKey(1)
+            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
+                break
+            elif key == 27:
+                break
+        cap.release()
+
+    def gr_realtime(self, diy):
+        if diy:
+            cnn = torch.load("CNN.pkl")
+            cnn_two = torch.load("CNN_two.pkl")
+        while True:
+            frame, img = self.camera.read()
+            tm_status = self.tm_main.gesture_recognition(self.tm_detector.find_hands(img), self.tm_detector)
+            if tm_status and diy:
+                is_one_hand = self.at_main.gesture_recognition(self.at_detector, img, cnn_two)
+                if is_one_hand:
+                    self.ai_main.gesture_recognition_camera(self.ai_detector, img, cnn)
+
+            cv2.imshow("camera", img)
+            key = cv2.waitKey(1)
+            if cv2.getWindowProperty('camera', cv2.WND_PROP_VISIBLE) < 1:
+                break
+            elif key == 27:
+                break
+
+    def ai_input(self):
+        self.ai_main.make_datasets(self.camera, "ai_datasets", 100)
+        self.ai_main.train("ai_datasets")
+        self.at_main.make_datasets(self.camera, "ai_two_datasets", 100)
+        self.at_main.train("ai_two_datasets")
+
+
+if __name__ == '__main__':
+    main = Main()
+    main.gr_img("C:/Users/leafl/Pictures/图片1.png", 0)

main.py

@@ -0,0 +1,112 @@
+# -*- coding:utf-8 -*-
+
+"""
+信号设计课程小组设计
+
+@ by: Leaf
+@ date: 2022-05-28
+"""
+import gr
+
+import tkinter as tk
+from tkinter import filedialog, Button, Label, Frame, ACTIVE, LEFT
+from PIL import Image, ImageTk
+
+
+class DisplayImage:
+    """用于展示选择的图片"""
+    def __init__(self, master):
+        self.master = master
+        master.title("GUI")
+        self.Text_lab0 = Label(master, text='已加载图像/视频')
+        self.Text_lab0.pack(pady=10)
+        self.image_frame = Frame(master, bd=0, height=300, width=300, bg='white', highlightthickness=2,
+                                 highlightbackground='gray', highlightcolor='black')
+        self.image_frame.pack()
+
+        self.Text_label = Label(master, text='加载待识别影像/视频')
+        self.Text_label.place(x=60, y=410)
+        self.Choose_image = Button(master, command=self.choose_img, text="图像",
+                                   width=7, default=ACTIVE, borderwidth=0)
+        self.Choose_image.place(x=50, y=450)
+        self.Choose_image = Button(master, command=self.choose_video, text="视频",
+                                   width=7, default=ACTIVE, borderwidth=0)
+        self.Choose_image.place(x=120, y=450)
+        self.Text_label2 = Label(master, text='运行手势识别程序')
+        self.Text_label2.place(x=60, y=500)
+        self.image_mosaic = Button(master, command=self.gesture_recognition, text="Gesture recognition",
+                                   width=17, default=ACTIVE, borderwidth=0)
+        self.image_mosaic.place(x=50, y=540)
+        self.Text_label3 = Label(master, text='运行实时手势识别程序')
+        self.Text_label3.place(x=300, y=410)
+        self.realtime = Button(master, command=self.realtime_gr, text="Realtime\n gesture recognition",
+                               width=17, height=6, default=ACTIVE, borderwidth=0)
+        self.realtime.place(x=300, y=450)
+        self.Text_label4 = Label(master, text='录入自定义手势')
+        self.Text_label4.place(x=180, y=610)
+        self.input = Button(master, command=self.input_image, text="Input gesture",
+                            width=42, default=ACTIVE, borderwidth=0)
+        self.input.place(x=60, y=650)
+
+        self.gr = gr.Main()
+        self.temp_dir = "temp"
+        self.mode = 0
+        self.directory = ""
+        self.diy = 1
+
+    def choose_img(self):
+        self.mode = 1
+        # 清空框架中的内容
+        for widget in self.image_frame.winfo_children():
+            widget.destroy()
+
+        self.directory = filedialog.askopenfilename()
+
+        # 布局所选图片
+        img = Image.open(self.directory).resize((300, 300))
+        img.save(self.temp_dir + "/photo.png")
+        image = ImageTk.PhotoImage(image=img)
+        label = Label(self.image_frame, highlightthickness=0, borderwidth=0)
+        label.configure(image=image)
+        label.pack(side=LEFT, expand=True)
+
+    def choose_video(self):
+        # 清空框架中的内容
+        self.mode = 2
+        for widget in self.image_frame.winfo_children():
+            widget.destroy()
+
+        self.directory = filedialog.askopenfilename()
+
+        # 布局所选图片
+        img = Image.open(self.temp_dir+"/video.jpg").resize((300, 300))
+        img.save(self.temp_dir + "/photo.png")
+        image = ImageTk.PhotoImage(image=img)
+        label = Label(self.image_frame, highlightthickness=0, borderwidth=0)
+        label.configure(image=image)
+        label.pack(side=LEFT, expand=True)
+
+    def gesture_recognition(self):
+        if self.mode == 1:
+            self.gr.gr_img(self.directory, self.diy)
+        elif self.mode == 2:
+            self.gr.gr_video(self.directory, self.diy)
+
+    def realtime_gr(self):
+        self.gr.gr_realtime(self.diy)
+
+    def input_image(self):
+        self.diy = 1
+        self.gr.ai_input()
+
+
+def main():
+    window = tk.Tk()
+    DisplayImage(window)
+    window.title('手势识别')
+    window.geometry('500x720')
+    window.mainloop()
+
+
+if __name__ == '__main__':
+    main()