使用OpenCV和TensorFlow检测实时摄像机上的数字

Question

我尝试了下面提供的代码来检测摄像机中的数字，并在其周围放置轮廓，然后使用H5模型对其进行分类，但它给了我不好的结果，只是相机是打开的，我既看不到检测也看不到分类。我不确定我需要改变或工作的地方。

使用python2.7OpenCV 4.2.0和TensorFlow 1.5.0

我正在使用的代码:

from statistics import mode
import cv2, time
from keras.models import load_model
from keras.datasets import mnist
import tensorflow as tf
import numpy as np
import vision_definitions
from PIL import Image
import numpy as np
import sys, os
from utils.inference import detect_digits
from utils.inference import draw_text
from utils.inference import draw_bounding_box
from utils.inference import apply_offsets
from utils.inference import load_detection_model
from utils.preprocessor import preprocess_input
# parameters for loading data and images
detection_model_path = '../trained_models/detection_models/model.sav'
class_model_path = '../trained_models/class_models/Num.h5'
# hyper-parameters for bounding boxes shape
frame_window = 10
class_offsets = (20, 40)
# loading models
digit_detection = load_detection_model(detection_model_path)
class_classifier = load_model(class_model_path)
# getting input model shapes for inference
class_target_size = class_classifier.input_shape[1:3]
class_window = []
class_window1 = []
# starting video streaming
cameraIndex = 0
resolution = vision_definitions.kVGA
colorSpace = vision_definitions.kRGBColorSpace
resolution = 2
colorSpace = 3
cv2.namedWindow('window_frame')
video_capture = cv2.VideoCapture(0)
if video_capture.isOpened():
 frame = video_capture.read()
else:
 rval = False
while True:
    rval, frame = video_capture.read()
    gray_image = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    rgb_image = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
    digits = detect_digits(digit_detection, gray_image)
    frame = cv2.resize(frame, (640, 480))
    key = cv2.waitKey(1)
    b,g,r = cv2.split(frame) # get b,g,r
    rgb_img = cv2.merge([r,g,b]) # switch it to rgb    
    for digit_coordinates in digits:
        x1, x2, y1, y2 = apply_offsets(digit_coordinates, class_offsets)
        gray_digit = gray_image[y1:y2, x1:x2]
        try:
            gray_digit = cv2.resize(gray_digit, (class_target_size))
        except:
            continue

        gray_digit = preprocess_input(gray_digit, True)
        gray_digit = np.expand_dims(gray_digit, 0)
        gray_digit = np.expand_dims(gray_digit, -1)
        class_prediction = class_classifier.predict(gray_digit)
        class_probability = np.max(class_prediction)
        class_label_arg = np.argmax(class_prediction)
       
        color = color.astype(int)
        color = color.tolist()
        draw_bounding_box(digit_coordinates, rgb_image, color)
        draw_text(digit_coordinates, rgb_image, class_mode,
                  color, 0, -45, 1, 1)
    frame = cv2.cvtColor(rgb_image, cv2.COLOR_RGB2BGR)
    cv2.imshow('window_frame', frame)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

Answer 1

我花了一些时间，因为在Windows上除了c++没有CV2.imshow()，但它是…

[示例]:

import cv2
import matplotlib.pyplot as plt
import matplotlib.animation as animation
import numpy as np
import tensorflow as tf
import os
from os.path import exists
import time
def f1( picture ):
    return np.asarray( picture )
fig = plt.figure()
image = plt.imread( "C:\Users\Jirayu Kaewprateep\Pictures\Cats\samples\03.png" )
im = plt.imshow( image )
global video_capture_0
video_capture_0 = cv2.VideoCapture(0)
video_capture_1 = cv2.VideoCapture(1)
def animate(i ):
    ret0, frame0 = video_capture_0.read()
    if (ret0):
        picture = np.concatenate( ( np.reshape(frame0[:,:,2:3], ( 480, 640, 1 )), 
                                    np.reshape(frame0[:,:,1:2], ( 480, 640, 1 )), 
                                    np.reshape(frame0[:,:,0:1], ( 480, 640, 1 ))),
                                    axis=2 )
        
        im.set_array( f1( picture ) )
    return im,
    
while True:
    # Capture frame-by-frame
    ret0, frame0 = video_capture_0.read()
    ani = animation.FuncAnimation(fig, animate, interval=50, blit=True)
    plt.show()
# When everything is done, release the capture
video_capture_0.release()
cv2.destroyAllWindows()

[Model]:

"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
: Model Initialize
"""""""""""""""""""""""""""""""""""""""""""""""""""""""""
model = tf.keras.models.Sequential([
    tf.keras.layers.InputLayer(input_shape=( 29, 39, 3 )),
    # tf.keras.layers.Reshape(( 29, 39 * 3 )),
    # tf.keras.layers.Bidirectional(tf.keras.layers.LSTM(128, return_sequences=True, return_state=False)),
    
    tf.keras.layers.RandomFlip("horizontal_and_vertical"),
    tf.keras.layers.RandomRotation(0.2),
    tf.keras.layers.RandomZoom(.5, .2),
    
    tf.keras.layers.Conv2D(32, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2, 2)),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.Dense(64),
    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),
    tf.keras.layers.Dense(64),
])
        
model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(64))
model.add(tf.keras.layers.Dense(2))
model.summary()

[Output]:

示例

样本2