如何将一张图片粘贴到另一张图片上到定义的区域

Question

我有一个简单的 Python 代码，它可以从摄像头捕获视频并预测面部情绪（从here 获取，以防您需要运行它）。

我喜欢将此视频捕获放在此框架内（中心是透明的）并显示所有内容。我该怎么做？

import numpy as np
import argparse
import matplotlib.pyplot as plt
import cv2
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout, Flatten
from tensorflow.keras.layers import Conv2D
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

# command line argument
ap = argparse.ArgumentParser()
ap.add_argument("--mode",help="train/display")
mode = ap.parse_args().mode

# plots accuracy and loss curves
def plot_model_history(model_history):
    """
    Plot Accuracy and Loss curves given the model_history
    """
    fig, axs = plt.subplots(1,2,figsize=(15,5))
    # summarize history for accuracy
    axs[0].plot(range(1,len(model_history.history['accuracy'])+1),model_history.history['accuracy'])
    axs[0].plot(range(1,len(model_history.history['val_accuracy'])+1),model_history.history['val_accuracy'])
    axs[0].set_title('Model Accuracy')
    axs[0].set_ylabel('Accuracy')
    axs[0].set_xlabel('Epoch')
    axs[0].set_xticks(np.arange(1,len(model_history.history['accuracy'])+1),len(model_history.history['accuracy'])/10)
    axs[0].legend(['train', 'val'], loc='best')
    # summarize history for loss
    axs[1].plot(range(1,len(model_history.history['loss'])+1),model_history.history['loss'])
    axs[1].plot(range(1,len(model_history.history['val_loss'])+1),model_history.history['val_loss'])
    axs[1].set_title('Model Loss')
    axs[1].set_ylabel('Loss')
    axs[1].set_xlabel('Epoch')
    axs[1].set_xticks(np.arange(1,len(model_history.history['loss'])+1),len(model_history.history['loss'])/10)
    axs[1].legend(['train', 'val'], loc='best')
    fig.savefig('plot.png')
    plt.show()

# Define data generators
train_dir = 'data/train'
val_dir = 'data/test'

num_train = 28709
num_val = 7178
batch_size = 64
num_epoch = 50

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=batch_size,
        color_mode="grayscale",
        class_mode='categorical')

validation_generator = val_datagen.flow_from_directory(
        val_dir,
        target_size=(48,48),
        batch_size=batch_size,
        color_mode="grayscale",
        class_mode='categorical')

# Create the model
model = Sequential()

model.add(Conv2D(32, kernel_size=(3, 3), activation='relu', input_shape=(48,48,1)))
model.add(Conv2D(64, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, kernel_size=(3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(1024, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(7, activation='softmax'))

# If you want to train the same model or try other models, go for this
if mode == "train":
    model.compile(loss='categorical_crossentropy',optimizer=Adam(lr=0.0001, decay=1e-6),metrics=['accuracy'])
    model_info = model.fit_generator(
            train_generator,
            steps_per_epoch=num_train // batch_size,
            epochs=num_epoch,
            validation_data=validation_generator,
            validation_steps=num_val // batch_size)
    plot_model_history(model_info)
    model.save_weights('model.h5')

# emotions will be displayed on your face from the webcam feed
elif mode == "display":
    model.load_weights('model.h5')

    # prevents openCL usage and unnecessary logging messages
    cv2.ocl.setUseOpenCL(False)

    # dictionary which assigns each label an emotion (alphabetical order)
    emotion_dict = {0: "Angry", 1: "Disgusted", 2: "Fearful", 3: "Happy", 4: "Neutral", 5: "Sad", 6: "Surprised"}

    # start the webcam feed
    cap = cv2.VideoCapture(1)
    while True:
        # Find haar cascade to draw bounding box around face
        ret, frame = cap.read()
        if not ret:
            break
        facecasc = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        faces = facecasc.detectMultiScale(gray,scaleFactor=1.3, minNeighbors=5)

        for (x, y, w, h) in faces:
            cv2.rectangle(frame, (x, y-50), (x+w, y+h+10), (255, 0, 0), 2)
            roi_gray = gray[y:y + h, x:x + w]
            cropped_img = np.expand_dims(np.expand_dims(cv2.resize(roi_gray, (48, 48)), -1), 0)
            prediction = model.predict(cropped_img)
            maxindex = int(np.argmax(prediction))
            text = emotion_dict[maxindex]

            if ("Happy" in text) or ("Sad" in text):
                cv2.putText(frame, text, (x+20, y-60), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2, cv2.LINE_AA)

        cv2.imshow('Video', cv2.resize(frame,(1600,960),interpolation = cv2.INTER_CUBIC))
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

    cap.release()
    cv2.destroyAllWindows()

Answer 1

Christoph 伟大解决方案在 cmets 中的简短实现。

第 1 步： 使用绘图工具提取黑盒区域的坐标。

您可以在图像底部看到 x,y 坐标。

第 2 步：

一个。调整视频的每一帧以适合黑色区域的大小。 宽度 = x1 - x0 和高度 = y1 - y0。

b.用调整大小的帧替换黑色区域像素。

代码：

import cv2

canvasImage = cv2.imread("gift.jpeg")

x0, x1 = 163, 472
y0, y1 = 73, 290

cap = cv2.VideoCapture("desk.mp4")
    
while True:
    isNextFrameAvail, frame = cap.read()
    if not isNextFrameAvail:
        break
    frame_shrunk = cv2.resize(frame, (x1 - x0, y1 - y0))
    canvasImage[y0:y1, x0:x1] = frame_shrunk
    cv2.imshow("Result", canvasImage)
    cv2.waitKey

结果：