Python 摄像头实时识别数字

2021.7.9 

原标题：基于 TensorFlow 和 OpenCV 实现摄像头实时识别数字

最初写这篇的时候完全没有 ML 基础，代码都是直接 copy，这两天留了个相关的作业，翻出来发现升级到 tf2 之后很多写法也变了。查了一下 keras 对新手比较友好，于是瞎搭了一个。

后面摄像头识别应该也不会更新了，目测就是把识别部分换成 keras 的 predict。

# nn5hsun@akane

from keras.datasets import mnist
from tensorflow.keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import Dense, Convolution2D, MaxPooling2D, Flatten, Dropout
from sklearn.model_selection import train_test_split
from keras.callbacks import EarlyStopping

(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_train = x_train.reshape(-1, 28, 28, 1)
x_test = x_test.reshape(-1, 28, 28, 1)

x_train = x_train / 255
x_test = x_test / 255

y_train = to_categorical(y_train, num_classes=10)
y_test = to_categorical(y_test, num_classes=10)

x_train, x_validation, y_train, y_validation = train_test_split(x_train, y_train, train_size=50000)

model = Sequential()

model.add(
    Convolution2D(input_shape=(28, 28, 1),
                  filters=16,
                  kernel_size=5,
                  strides=2,
                  padding='valid',
                  activation='relu'))

model.add(Convolution2D(filters=32, kernel_size=3, strides=1, padding='same', activation='relu'))

model.add(MaxPooling2D(pool_size=2, strides=1, padding='same'))

model.add(Flatten())

model.add(Dropout(0.4))

model.add(Dense(10, activation='softmax'))

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

model.summary()

es_callback = EarlyStopping(monitor='val_loss', patience=5)

model.fit(x_train,
          y_train,
          batch_size=64,
          epochs=20,
          validation_data=(x_validation, y_validation),
          callbacks=es_callback)

loss, acc = model.evaluate(x_test, y_test, batch_size=64)
print(f"Test accuracy: {acc}\nTest loss: {loss}")

model.save(filepath='./cnn_keras_mnist')

输出

---

以下原文

---

做大创需要用到数字识别，之前用 Mathematica 效果不佳，打算换成 TensorFlow 试试，这几天现学了一下 Python 和 TensorFlow 。

下面的代码参考了很多资料（前两个是直接照搬的），我自己用起来识别正确率很低，不知道哪里出了问题，感觉没救了。

放出来供参考，如果有大佬知道怎么修改还请不吝赐教。;w;

先下载 MNIST 数据集 

input_data 

# Copyright 2015 Google Inc. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================

"""Functions for downloading and reading MNIST data."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip
import os

import tensorflow.python.platform

import numpy
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf

SOURCE_URL = 'http://yann.lecun.com/exdb/mnist/'


def maybe_download(filename, work_directory):
  """Download the data from Yann's website, unless it's already here."""
  if not os.path.exists(work_directory):
    os.mkdir(work_directory)
  filepath = os.path.join(work_directory, filename)
  if not os.path.exists(filepath):
    filepath, _ = urllib.request.urlretrieve(SOURCE_URL + filename, filepath)
    statinfo = os.stat(filepath)
    print('Successfully downloaded', filename, statinfo.st_size, 'bytes.')
  return filepath


def _read32(bytestream):
  dt = numpy.dtype(numpy.uint32).newbyteorder('>')
  return numpy.frombuffer(bytestream.read(4), dtype=dt)[0]


def extract_images(filename):
  """Extract the images into a 4D uint8 numpy array [index, y, x, depth]."""
  print('Extracting', filename)
  with gzip.open(filename) as bytestream:
    magic = _read32(bytestream)
    if magic != 2051:
      raise ValueError(
          'Invalid magic number %d in MNIST image file: %s' %
          (magic, filename))
    num_images = _read32(bytestream)
    rows = _read32(bytestream)
    cols = _read32(bytestream)
    buf = bytestream.read(rows * cols * num_images)
    data = numpy.frombuffer(buf, dtype=numpy.uint8)
    data = data.reshape(num_images, rows, cols, 1)
    return data


def dense_to_one_hot(labels_dense, num_classes=10):
  """Convert class labels from scalars to one-hot vectors."""
  num_labels = labels_dense.shape[0]
  index_offset = numpy.arange(num_labels) * num_classes
  labels_one_hot = numpy.zeros((num_labels, num_classes))
  labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1
  return labels_one_hot


def extract_labels(filename, one_hot=False):
  """Extract the labels into a 1D uint8 numpy array [index]."""
  print('Extracting', filename)
  with gzip.open(filename) as bytestream:
    magic = _read32(bytestream)
    if magic != 2049:
      raise ValueError(
          'Invalid magic number %d in MNIST label file: %s' %
          (magic, filename))
    num_items = _read32(bytestream)
    buf = bytestream.read(num_items)
    labels = numpy.frombuffer(buf, dtype=numpy.uint8)
    if one_hot:
      return dense_to_one_hot(labels)
    return labels


class DataSet(object):

  def __init__(self, images, labels, fake_data=False, one_hot=False,
               dtype=tf.float32):
    """Construct a DataSet.

    one_hot arg is used only if fake_data is true.  `dtype` can be either
    `uint8` to leave the input as `[0, 255]`, or `float32` to rescale into
    `[0, 1]`.
    """
    dtype = tf.as_dtype(dtype).base_dtype
    if dtype not in (tf.uint8, tf.float32):
      raise TypeError('Invalid image dtype %r, expected uint8 or float32' %
                      dtype)
    if fake_data:
      self._num_examples = 10000
      self.one_hot = one_hot
    else:
      assert images.shape[0] == labels.shape[0], (
          'images.shape: %s labels.shape: %s' % (images.shape,
                                                 labels.shape))
      self._num_examples = images.shape[0]

      # Convert shape from [num examples, rows, columns, depth]
      # to [num examples, rows*columns] (assuming depth == 1)
      assert images.shape[3] == 1
      images = images.reshape(images.shape[0],
                              images.shape[1] * images.shape[2])
      if dtype == tf.float32:
        # Convert from [0, 255] -> [0.0, 1.0].
        images = images.astype(numpy.float32)
        images = numpy.multiply(images, 1.0 / 255.0)
    self._images = images
    self._labels = labels
    self._epochs_completed = 0
    self._index_in_epoch = 0

  @property
  def images(self):
    return self._images

  @property
  def labels(self):
    return self._labels

  @property
  def num_examples(self):
    return self._num_examples

  @property
  def epochs_completed(self):
    return self._epochs_completed

  def next_batch(self, batch_size, fake_data=False):
    """Return the next `batch_size` examples from this data set."""
    if fake_data:
      fake_image = [1] * 784
      if self.one_hot:
        fake_label = [1] + [0] * 9
      else:
        fake_label = 0
      return [fake_image for _ in xrange(batch_size)], [
          fake_label for _ in xrange(batch_size)]
    start = self._index_in_epoch
    self._index_in_epoch += batch_size
    if self._index_in_epoch > self._num_examples:
      # Finished epoch
      self._epochs_completed += 1
      # Shuffle the data
      perm = numpy.arange(self._num_examples)
      numpy.random.shuffle(perm)
      self._images = self._images[perm]
      self._labels = self._labels[perm]
      # Start next epoch
      start = 0
      self._index_in_epoch = batch_size
      assert batch_size <= self._num_examples
    end = self._index_in_epoch
    return self._images[start:end], self._labels[start:end]


def read_data_sets(train_dir, fake_data=False, one_hot=False, dtype=tf.float32):
  class DataSets(object):
    pass
  data_sets = DataSets()

  if fake_data:
    def fake():
      return DataSet([], [], fake_data=True, one_hot=one_hot, dtype=dtype)
    data_sets.train = fake()
    data_sets.validation = fake()
    data_sets.test = fake()
    return data_sets

  TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
  TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
  TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
  TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
  VALIDATION_SIZE = 5000

  local_file = maybe_download(TRAIN_IMAGES, train_dir)
  train_images = extract_images(local_file)

  local_file = maybe_download(TRAIN_LABELS, train_dir)
  train_labels = extract_labels(local_file, one_hot=one_hot)

  local_file = maybe_download(TEST_IMAGES, train_dir)
  test_images = extract_images(local_file)

  local_file = maybe_download(TEST_LABELS, train_dir)
  test_labels = extract_labels(local_file, one_hot=one_hot)

  validation_images = train_images[:VALIDATION_SIZE]
  validation_labels = train_labels[:VALIDATION_SIZE]
  train_images = train_images[VALIDATION_SIZE:]
  train_labels = train_labels[VALIDATION_SIZE:]

  data_sets.train = DataSet(train_images, train_labels, dtype=dtype)
  data_sets.validation = DataSet(validation_images, validation_labels,
                                 dtype=dtype)
  data_sets.test = DataSet(test_images, test_labels, dtype=dtype)

  return data_sets

训练模型

multilayer_convolutional_network

import input_data
import tensorflow as tf

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
sess = tf.InteractiveSession()

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')
  
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

x_image = tf.reshape(x, [-1,28,28,1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

cross_entropy = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver = tf.train.Saver()# defaults to saving all variables

sess.run(tf.global_variables_initializer())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))
  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
saver.save(sess, 'C:/Users/vzrxs/Desktop/TF Project/model.ckpt')#保存模型参数

print("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

主程序

main_program

import cv2
import tensorflow as tf
from PIL import Image

#############################################################################################################

#模型调用部分
tf.reset_default_graph()


x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
sess = tf.Session()

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')
  
W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])

x_image = tf.reshape(x, [-1,28,28,1])

h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])

h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)

keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2

init_op = tf.global_variables_initializer()

saver = tf.train.Saver()

saver.restore(sess, 'C:/Users/vzrxs/Desktop/TF Project/model.ckpt')

#############################################################################################################

#摄像头调用部分
cap = cv2.VideoCapture(1)#创建一个 VideoCapture 对象, 1: 后置镜头

cap.set(3,640)
cap.set(4,480)

#############################################################################################################  
    
#图像处理部分  
i = 0
compare = [0 for i in range(10)]

while(cap.isOpened()):#循环读取每一帧

    ret, frame = cap.read()
    cv2.rectangle(frame,(240,200),(340,300),(0,0,255),2)

    cv2.imshow('Capture',frame)  #窗口显示，显示名为 Capture

  
    roiImg = frame[200:300,240:340]
    
    im_gray = cv2.cvtColor(roiImg, cv2.COLOR_BGR2GRAY)   #灰度化

    retval, im_at_fixed = cv2.threshold(im_gray, 80, 255, cv2.THRESH_BINARY)#二值化
    img = cv2.resize(im_at_fixed,(28,28))

    cv2.imwrite('C:/Users/vzrxs/Desktop/TF Project/Temp/temp.png', img)#保存图片
    file_name='C:/Users/vzrxs/Desktop/TF Project/Temp/temp.png'
    im = Image.open(file_name)

    tv = list(im.getdata()) #get pixel values

    #normalize pixels to 0 and 1. 0 is pure white, 1 is pure black.
    tva = [ (255-x)*1.0/255.0 for x in tv] 
    
#############################################################################################################    

#图像识别部分
    with tf.Session() as sess:
        sess.run(init_op)
    
        prediction=tf.argmax(y_conv,1)
        predint=prediction.eval(feed_dict={x: [tva],keep_prob: 1.0}, session=sess)
        
        compare[i]=predint[0]
        i+=1
        if i%5==0:
            result=max(set(compare), key=compare.count)
            print('result:',result)
            #print(compare)

        if i==10:
            i=0


#############################################################################################################

#摄像头关闭部分
    if cv2.waitKey(1) & 0xFF == ord('0'):
        break
cap.release() #释放摄像头
cv2.destroyAllWindows()#删除建立的全部窗口

测试识别Ariel字体数字和某手写字体效果奇差，后来考虑设置一个数组(compare)，结果(result)取数组中出现次数最多的数字，识别十次输出两次，但是并没有什么卵用。

如果可以改得能用了的话下一步考虑整个取景框内识别所有数字（形态学？），有进展的话会继续更新。如果有dalao有什么建议的话请务必告诉我，欢迎交流。_(:з」∠)_