[英]How to detect emotions from a single image and not a constant camera feed?
我正在嘗試修改此存儲庫。 這個 repo 不斷地從相機中獲取幀,並不斷更新當前的情緒。 我現在要做的是從我的一個文件夾中獲取已經保存的單個圖像,然后在命令行上打印出情緒。
我嘗試為 cv2.VideoCapture 提供圖像的路徑,但它仍然不起作用,我在嘗試時遇到的錯誤之一是
AttributeError: 'cv2.VideoCapture' object has no attribute 'shape'
這是代碼:
from tensorflow.keras.preprocessing.image import img_to_array
import imutils
import cv2
from tensorflow.keras.models import load_model
import numpy as np
# from tensorflow.keras import Sequential
# from tensorflow.keras.layers import Conv2D, Flatten, Dense
# parameters for loading data and images
detection_model_path = 'haarcascade_files/haarcascade_frontalface_default.xml'
emotion_model_path = 'models/_mini_XCEPTION.102-0.66.hdf5'
# hyper-parameters for bounding boxes shape
# loading models
face_detection = cv2.CascadeClassifier(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
EMOTIONS = ["angry" ,"disgust","scared", "happy", "sad", "surprised",
"neutral"]
#feelings_faces = []
#for index, emotion in enumerate(EMOTIONS):
# feelings_faces.append(cv2.imread('emojis/' + emotion + '.png', -1))
# starting video streaming
cv2.namedWindow('your_face')
# camera = cv2.VideoCapture('C:/Users/ajeel/Desktop/Faces/FZKmwbkp.png')
# camera = cv2.VideoCapture('C://Users//ajeel//Desktop//Faces//FZKmwbkp.png')
camera = cv2.VideoCapture('FZKmwbkp.png')
# camera = cv2.VideoCapture()
while True:
# frame = camera.read('C://Users//ajeel//Desktop//Faces//FZKmwbkp.png')[1]
# frame = camera.read('C:/Users/ajeel/Desktop/Faces/FZKmwbkp.png')[1]
ret, frame = camera.read()
# reading the frame
# frame = imutils.resize(frame,width=300)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_detection.detectMultiScale(gray,scaleFactor=1.1,minNeighbors=5,minSize=(30,30),flags=cv2.CASCADE_SCALE_IMAGE)
canvas = np.zeros((250, 300, 3), dtype="uint8")
frameClone = frame.copy()
if len(faces) > 0:
faces = sorted(faces, reverse=True,
key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
(fX, fY, fW, fH) = faces
# Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
# the ROI for classification via the CNN
roi = gray[fY:fY + fH, fX:fX + fW]
roi = cv2.resize(roi, (64, 64))
roi = roi.astype("float") / 255.0
roi = img_to_array(roi)
roi = np.expand_dims(roi, axis=0)
preds = emotion_classifier.predict(roi)[0]
emotion_probability = np.max(preds)
label = EMOTIONS[preds.argmax()]
else: continue
for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
# construct the label text
text = "{}: {:.2f}%".format(emotion, prob * 100)
# draw the label + probability bar on the canvas
# emoji_face = feelings_faces[np.argmax(preds)]
w = int(prob * 300)
cv2.rectangle(canvas, (7, (i * 35) + 5),
(w, (i * 35) + 35), (0, 0, 255), -1)
cv2.putText(canvas, text, (10, (i * 35) + 23),
cv2.FONT_HERSHEY_SIMPLEX, 0.45,
(255, 255, 255), 2)
cv2.putText(frameClone, label, (fX, fY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
(0, 0, 255), 2)
# for c in range(0, 3):
# frame[200:320, 10:130, c] = emoji_face[:, :, c] * \
# (emoji_face[:, :, 3] / 255.0) + frame[200:320,
# 10:130, c] * (1.0 - emoji_face[:, :, 3] / 255.0)
cv2.imshow('your_face', frameClone)
cv2.imshow("Probabilities", canvas)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
camera.release()
cv2.destroyAllWindows()
我找到了解決方案:
我在循環之外刪除了 cv2.VideoCapture,然后將其移交給幀變量,而是直接將 cv2.imread('path-name') 分配給它。
此外,我禁用了 windows 所以現在我只能在命令行上獲得打印語句。
這是代碼:
from tensorflow.keras.preprocessing.image import img_to_array
import imutils
import cv2
from tensorflow.keras.models import load_model
import numpy as np
# from tensorflow.keras import Sequential
# from tensorflow.keras.layers import Conv2D, Flatten, Dense
# parameters for loading data and images
detection_model_path = 'haarcascade_files/haarcascade_frontalface_default.xml'
emotion_model_path = 'models/_mini_XCEPTION.102-0.66.hdf5'
# hyper-parameters for bounding boxes shape
# loading models
face_detection = cv2.CascadeClassifier(detection_model_path)
emotion_classifier = load_model(emotion_model_path, compile=False)
EMOTIONS = ["angry" ,"disgust","scared", "happy", "sad", "surprised",
"neutral"]
#feelings_faces = []
#for index, emotion in enumerate(EMOTIONS):
# feelings_faces.append(cv2.imread('emojis/' + emotion + '.png', -1))
# starting video streaming
# cv2.namedWindow('your_face')
# camera = cv2.VideoCapture('C:/Users/ajeel/Desktop/Faces/FZKmwbkp.png')
# camera = cv2.VideoCapture('C://Users//ajeel//Desktop//Faces//FZKmwbkp.png')
# camera = cv2.VideoCapture('FZKmwbkp.png')
# camera = cv2.imread('C://Users//ajeel//Desktop//Faces//FZKmwbkp.png')
#
while True:
# frame = camera.read('C://Users//ajeel//Desktop//Faces//FZKmwbkp.png')[1]
# frame = camera.read('C:/Users/ajeel/Desktop/Faces/FZKmwbkp.png')[1]
# ret, frame = camera.read()
# frame = camera.read()[1]
frame = cv2.imread('C://Users//ajeel//Desktop//Faces//FZKmwbkp.png')
# reading the frame
frame = imutils.resize(frame,width=300)
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_detection.detectMultiScale(gray,scaleFactor=1.1,minNeighbors=5,minSize=(30,30),flags=cv2.CASCADE_SCALE_IMAGE)
canvas = np.zeros((250, 300, 3), dtype="uint8")
frameClone = frame.copy()
if len(faces) > 0:
faces = sorted(faces, reverse=True,
key=lambda x: (x[2] - x[0]) * (x[3] - x[1]))[0]
(fX, fY, fW, fH) = faces
# Extract the ROI of the face from the grayscale image, resize it to a fixed 28x28 pixels, and then prepare
# the ROI for classification via the CNN
roi = gray[fY:fY + fH, fX:fX + fW]
roi = cv2.resize(roi, (64, 64))
roi = roi.astype("float") / 255.0
roi = img_to_array(roi)
roi = np.expand_dims(roi, axis=0)
preds = emotion_classifier.predict(roi)[0]
# print("this is preds")
# print(preds)
emotion_probability = np.max(preds)
# print("this is emotional probability")
# print(emotion_probability)
label = EMOTIONS[preds.argmax()]
# print("this is label")
print(label)
else: continue
for (i, (emotion, prob)) in enumerate(zip(EMOTIONS, preds)):
# construct the label text
text = "{}: {:.2f}%".format(emotion, prob * 100)
# draw the label + probability bar on the canvas
# emoji_face = feelings_faces[np.argmax(preds)]
w = int(prob * 300)
cv2.rectangle(canvas, (7, (i * 35) + 5),
(w, (i * 35) + 35), (0, 0, 255), -1)
cv2.putText(canvas, text, (10, (i * 35) + 23),
cv2.FONT_HERSHEY_SIMPLEX, 0.45,
(255, 255, 255), 2)
cv2.putText(frameClone, label, (fX, fY - 10),
cv2.FONT_HERSHEY_SIMPLEX, 0.45, (0, 0, 255), 2)
cv2.rectangle(frameClone, (fX, fY), (fX + fW, fY + fH),
(0, 0, 255), 2)
# for c in range(0, 3):
# frame[200:320, 10:130, c] = emoji_face[:, :, c] * \
# (emoji_face[:, :, 3] / 255.0) + frame[200:320,
# 10:130, c] * (1.0 - emoji_face[:, :, 3] / 255.0)
# cv2.imshow('your_face', frameClone)
# cv2.imshow("Probabilities", canvas)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
camera.release()
cv2.destroyAllWindows()
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.