【機器學習實戰入門項目】使用Python創建自己的表情符號

在這里插入圖片描述

深度學習項目入門——讓你更接近數據科學的夢想

表情符號或頭像是表示非語言暗示的方式。這些暗示已成為在線聊天、產品評論、品牌情感等的重要組成部分。這也促使數據科學領域越來越多的研究致力于表情驅動的故事講述。

隨著計算機視覺和深度學習的進步，現在可以從圖像中檢測人類情感。在這個深度學習項目中，我們將對人類面部表情進行分類，并過濾和映射相應的表情符號或頭像。

關于數據集

面部表情識別數據集（FER2013）包含48*48像素的灰度人臉圖像。這些圖像中心對齊，并且占據相同的空間。該數據集包含以下類別的面部情緒：

0: 憤怒
1: 厭惡
2: 恐懼
3: 快樂
4: 悲傷
5: 驚訝
6: 自然

下載數據集: 面部表情識別數據集

下載項目代碼: 表情生成器項目源代碼

使用深度學習創建你的表情

我們將構建一個深度學習模型來分類圖像中的面部表情，然后將分類的情緒映射到表情符號或頭像。

使用CNN進行面部情緒識別

在以下步驟中，我們將構建一個卷積神經網絡架構，并在FER2013數據集上訓練模型，以從圖像中識別情緒。

導入庫:

import numpy as np
import cv2
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D
from keras.optimizers import Adam
from keras.layers import MaxPooling2D
from keras.preprocessing.image import ImageDataGenerator

初始化訓練和驗證生成器:

train_dir = 'data/train'
val_dir = 'data/test'
train_datagen = ImageDataGenerator(rescale=1./255)
val_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(train_dir,target_size=(48,48),batch_size=64,color_mode="grayscale",class_mode='categorical')
validation_generator = val_datagen.flow_from_directory(val_dir,target_size=(48,48),batch_size=64,color_mode="grayscale",class_mode='categorical')

構建卷積網絡架構:

emotion_model = Sequential()
emotion_model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(48,48,1)))
emotion_model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
emotion_model.add(MaxPooling2D(pool_size=(2, 2)))
emotion_model.add(Dropout(0.25))
emotion_model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
emotion_model.add(MaxPooling2D(pool_size=(2, 2)))
emotion_model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
emotion_model.add(MaxPooling2D(pool_size=(2, 2)))
emotion_model.add(Dropout(0.25))
emotion_model.add(Flatten())
emotion_model.add(Dense(1024, activation='relu'))
emotion_model.add(Dropout(0.5))
emotion_model.add(Dense(7, activation='softmax'))

編譯和訓練模型:

emotion_model.compile(loss='categorical_crossentropy', optimizer=Adam(lr=0.0001, decay=1e-6), metrics=['accuracy'])
emotion_model_info = emotion_model.fit_generator(train_generator,steps_per_epoch=28709 // 64,epochs=50,validation_data=validation_generator,validation_steps=7178 // 64)

保存模型權重:
```
emotion_model.save_weights('model.h5')
```

使用OpenCV的haarcascade xml檢測網絡攝像頭中人臉的邊界框，并預測情緒:

cv2.ocl.setUseOpenCL(False)
emotion_dict = {0: "Angry", 1: "Disgusted", 2: "Fearful", 3: "Happy", 4: "Neutral", 5: "Sad", 6: "Surprised"}
cap = cv2.VideoCapture(0)
while True:ret, frame = cap.read()if not ret:breakbounding_box = cv2.CascadeClassifier('/home/shivam/.local/lib/python3.6/site-packages/cv2/data/haarcascade_frontalface_default.xml')gray_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)num_faces = bounding_box.detectMultiScale(gray_frame, scaleFactor=1.3, minNeighbors=5)for (x, y, w, h) in num_faces:cv2.rectangle(frame, (x, y-50), (x+w, y+h+10), (255, 0, 0), 2)roi_gray_frame = gray_frame[y:y + h, x:x + w]cropped_img = np.expand_dims(np.expand_dims(cv2.resize(roi_gray_frame, (48, 48)), -1), 0)emotion_prediction = emotion_model.predict(cropped_img)maxindex = int(np.argmax(emotion_prediction))cv2.putText(frame, emotion_dict[maxindex], (x+20, y-60), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)cv2.imshow('Video', cv2.resize(frame, (1200,860), interpolation=cv2.INTER_CUBIC))if cv2.waitKey(1) & 0xFF == ord('q'):break
cap.release()
cv2.destroyAllWindows()

GUI和表情符號映射的代碼

創建一個名為emojis的文件夾，并保存數據集中每種情緒對應的表情符號。

將以下代碼粘貼到gui.py中并運行文件。

import tkinter as tk
from tkinter import *
import cv2
from PIL import Image, ImageTk
import os
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D
from keras.optimizers import Adam
from keras.layers import MaxPooling2Demotion_model = Sequential()
emotion_model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(48,48,1)))
emotion_model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
emotion_model.add(MaxPooling2D(pool_size=(2, 2)))
emotion_model.add(Dropout(0.25))
emotion_model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
emotion_model.add(MaxPooling2D(pool_size=(2, 2)))
emotion_model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
emotion_model.add(MaxPooling2D(pool_size=(2, 2)))
emotion_model.add(Dropout(0.25))
emotion_model.add(Flatten())
emotion_model.add(Dense(1024, activation='relu'))
emotion_model.add(Dropout(0.5))
emotion_model.add(Dense(7, activation='softmax'))
emotion_model.load_weights('model.h5')cv2.ocl.setUseOpenCL(False)
emotion_dict = {0: "   Angry   ", 1: "Disgusted", 2: "  Fearful  ", 3: "   Happy   ", 4: "  Neutral  ", 5: "    Sad    ", 6: "Surprised"}
emoji_dist={0:"./emojis/angry.png", 1:"./emojis/disgusted.png", 2:"./emojis/fearful.png", 3:"./emojis/happy.png", 4:"./emojis/neutral.png", 5:"./emojis/sad.png", 6:"./emojis/surprised.png"}global last_frame1
last_frame1 = np.zeros((480, 640, 3), dtype=np.uint8)
global cap1
show_text=[0]def show_vid():cap1 = cv2.VideoCapture(0)if not cap1.isOpened():print("cant open the camera1")flag1, frame1 = cap1.read()frame1 = cv2.resize(frame1, (600,500))bounding_box = cv2.CascadeClassifier('/home/shivam/.local/lib/python3.6/site-packages/cv2/data/haarcascade_frontalface_default.xml')gray_frame = cv2.cvtColor(frame1, cv2.COLOR_BGR2GRAY)num_faces = bounding_box.detectMultiScale(gray_frame, scaleFactor=1.3, minNeighbors=5)for (x, y, w, h) in num_faces:cv2.rectangle(frame1, (x, y-50), (x+w, y+h+10), (255, 0, 0), 2)roi_gray_frame = gray_frame[y:y + h, x:x + w]cropped_img = np.expand_dims(np.expand_dims(cv2.resize(roi_gray_frame, (48, 48)), -1), 0)prediction = emotion_model.predict(cropped_img)maxindex = int(np.argmax(prediction))cv2.putText(frame1, emotion_dict[maxindex], (x+20, y-60), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)show_text[0]=maxindexif flag1 is None:print("Major error!")elif flag1:global last_frame1last_frame1 = frame1.copy()pic = cv2.cvtColor(last_frame1, cv2.COLOR_BGR2RGB)img = Image.fromarray(pic)imgtk = ImageTk.PhotoImage(image=img)lmain.imgtk = imgtklmain.configure(image=imgtk)lmain.after(10, show_vid)if cv2.waitKey(1) & 0xFF == ord('q'):exit()def show_vid2():frame2 = cv2.imread(emoji_dist[show_text[0]])pic2 = cv2.cvtColor(frame2, cv2.COLOR_BGR2RGB)img2 = Image.fromarray(pic2)imgtk2 = ImageTk.PhotoImage(image=img2)lmain2.imgtk2 = imgtk2lmain3.configure(text=emotion_dict[show_text[0]], font=('arial',45,'bold'))lmain2.configure(image=imgtk2)lmain2.after(10, show_vid2)if __name__ == '__main__':root = tk.Tk()img = ImageTk.PhotoImage(Image.open("logo.png"))heading = Label(root, image=img, bg='black')heading.pack()heading2 = Label(root, text="Photo to Emoji", pady=20, font=('arial',45,'bold'), bg='black', fg='#CDCDCD')heading2.pack()lmain = tk.Label(master=root, padx=50, bd=10)lmain2 = tk.Label(master=root, bd=10)lmain3 = tk.Label(master=root, bd=10, fg="#CDCDCD", bg='black')lmain.pack(side=LEFT)lmain.place(x=50,y=250)lmain3.pack()lmain3.place(x=960,y=250)lmain2.pack(side=RIGHT)lmain2.place(x=900,y=350)root.title("Photo To Emoji")root.geometry("1400x900+100+10")root['bg']='black'exitbutton = Button(root, text='Quit', fg="red", command=root.destroy, font=('arial',25,'bold')).pack(side = BOTTOM)show_vid()show_vid2()root.mainloop()

總結

在這個面向初學者的深度學習項目中，我們構建了一個卷積神經網絡來識別面部情緒。我們在FER2013數據集上訓練了我們的模型，然后將這些情緒映射到相應的情緒符號或頭像。

使用OpenCV的haar cascade xml，我們獲得了網絡攝像頭中人臉的邊界框，然后將這些框輸入到訓練好的模型中進行分類。

DataFlair致力于為用戶提供成為數據科學家所需的所有資源，包括詳細的教程、實踐、用例以及項目源代碼。

參考資料

參考資料名稱	鏈接
FER2013數據集	Kaggle FER2013 Dataset
Keras官方文檔	Keras Official Documentation
OpenCV官方文檔	OpenCV Official Documentation
TensorFlow官方文檔	TensorFlow Official Documentation
數據科學教程	DataFlair Data Science Tutorials
深度學習項目	DataFlair Deep Learning Projects
圖像分類教程	Image Classification Tutorial
CNN架構詳解	CNN Architecture Explained
數據增強技術	Data Augmentation Techniques
GUI編程指南	GUI Programming Guide
表情符號使用指南	Emoji Usage Guide
情感分析研究	Emotion Recognition Research
深度學習框架比較	Deep Learning Framework Comparison
計算機視覺應用	Computer Vision Applications