工业零件在制造完成的时候，往往需要去检测其完整性和功能性。如下图所示，从左上到右下，分别是擦花、漏底、碰凹、凸粉。本篇博文主要讲解如何去识别这四类图像，所用框架为keras-2.1.6+tensorflow-1.7.0+GTX1060。
所获得的数据不是太多，一共250幅图像，其中擦花图像29幅、漏底图像140幅、碰凹图像20幅、凸粉图像61幅。可以发现，这样的数据对深度卷积网络来说是远远不够的，而且数据分布是极不对称的。而且对特征是否明显来说，擦花特征是最不明显的，在训练的时候更要进行关注。
对每类图像进行增强，使其扩展到300幅左右。这里使用ImageDataGenerator来完成，主要包括图像的旋转、平移、错切等。
from keras.preprocessing.image import ImageDataGenerator
import numpy as np
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.optimizers import SGD
import tensorflow as tf
from PIL import Image
from image_handle import *
import os
import cv2
batch_size=10
epoch_size=50
data = np.empty((250,800, 800,3), dtype="float32")
image_resize=[]
image_vector=[]
image_label=[]
image_label_list=['擦花','漏底','碰凹','凸粉'] #漏底占的比例太大了，导致后面的预测全部都偏向该物体
image_dir='F:/Data/guangdong_round1_train1_20180903/'
j=0
k=0
for fn in os.listdir(image_dir):
image_name=get_image_name(fn)
for i in range(0,4):
if image_label_list[i]==image_name:
image_name=i
image = Image.open(image_dir+fn,'r')#原始图片过大
image_down=image.resize((800, 800), Image.ANTIALIAS)
arr = np.asarray(image_down, dtype="float32")
data[j, :, :, :] = arr
j=j+1
image_label.append(image_name)
#准备好数据和标签送进VGG网络中
x_train=data[231:250]
y_train = keras.utils.to_categorical(image_label,4)[231:250]#转换成one-hot向量
print(len(x_train))
print(len(y_train))
print(image_label)
generator = ImageDataGenerator(
rotation_range=20,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.1,
zoom_range=0.1,
horizontal_flip=True,
)
for batch in generator.flow(x_train,
batch_size=100,
save_to_dir='C:/Users/18301/Desktop/image_data',#生成后的图像保存路径
save_prefix='碰凹2018',
save_format='jpg'):
k += 1
if k > 10: #这个10指出要扩增多少个数据，最终的数据为x_train的大小与10的乘积，可根据要求自行更改
break # otherwise the generator would loop indefinitely
增强后的图像：
主程序，main.py
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import BatchNormalization,Activation
from sklearn.model_selection import train_test_split
from keras.optimizers import SGD
import tensorflow as tf
from PIL import Image
from image_handle import *
from model import BuildModel
import os
import cv2
import keras.backend.tensorflow_backend as KTF
#进行配置，使用60%的GPU,这是为了保护GPU
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 0.6
session = tf.Session(config=config)
# 设置session
KTF.set_session(session )
batch_size=5
epoch_size=50
image_number=1451
resize_width=300
resize_height=300
image_vec=[]
image_resize=[]
image_vector=[]
image_label=[]
image_label_list=['擦花','漏底','碰凹','凸粉'] #漏底占的比例太大了，导致后面的预测全部都偏向该物体
data = np.empty((1429,300, 300,3), dtype="float32")
image_dir='F:/Data/guangdong_round1_train1_20180903/image_data/'
data,image_label,image_vec=get_image_data(image_dir,resize_width,resize_height,data,image_label,image_label_list)
#准备好数据和标签送进VGG网络中
X_train=data
Y_train = keras.utils.to_categorical(image_label,4) #转换成one-hot向量
#划分训练集和测试集
x_train, x_test,y_train, y_test = train_test_split(X_train, Y_train,test_size=0.1, random_state=None)
#开始建立序列模型
model=BuildModel(x_train,y_train,x_test,y_test,batch_size,epoch_size)
model.run_model()
model.py
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten,Input
from keras.layers import Conv2D, MaxPooling2D,merge
from keras.layers import BatchNormalization,Activation
from sklearn.model_selection import train_test_split
from keras.optimizers import SGD
from keras import regularizers
from keras.models import Model
import tensorflow as tf
from PIL import Image
from image_handle import *
import os
import cv2
class BuildModel():
def __init__(self,x_train,y_train,x_test,y_test,batch_size,epoch_size):
self.x_train=x_train
self.y_train = y_train
self.x_test=x_test
self.y_test=y_test
self.batch_size=batch_size
self.epoch_size=epoch_size
def add_layer(self,X,channel_num):
#借鉴残差网络的思想
conv_1=Conv2D(channel_num, (3, 3),padding='same')(X)
conv_1=BatchNormalization()(conv_1)
conv_1= Activation('relu')(conv_1)
# conv_1 = MaxPooling2D(pool_size=(3, 3),strides=(1,1),padding='same')(conv_1)
conv_1 = Conv2D(channel_num, (3, 3),padding='same')(conv_1)
conv_1 = BatchNormalization()(conv_1)
merge_data = merge([conv_1, X], mode='sum')
out = Activation('relu')(merge_data)
return out
def google_layer(self,X):
#借鉴GoogleNet的思想,单层分支
conv_1 = Conv2D(32,(1, 1), padding='same')(X)
conv_1 = BatchNormalization()(conv_1)
conv_1 = Activation('relu')(conv_1)
conv_2 = Conv2D(32,(3, 3), padding='same')(X)
conv_2 = BatchNormalization()(conv_2)
conv_2 = Activation('relu')(conv_2)
conv_3 = Conv2D(32,(5, 5), padding='same')(X)
conv_3 = BatchNormalization()(conv_3)
conv_3 = Activation('relu')(conv_3)
pooling_1 = MaxPooling2D(pool_size=(2, 2), strides=(1, 1), padding='same')(X)
out = merge([conv_1,conv_2,conv_3,pooling_1], mode='concat')
return out
def run_model(self):
# input: 100x100 images with 3 channels -> (100, 100, 3) tensors.
# this applies 32 convolution filters of size 3x3 each.
#在这里采用函数式模型不采用序贯式模型
#发现单纯使用残差网络比使用残差+GoogleNet效果要好，收敛速度更快
inputs=Input(shape=(300,300,3))
X=Conv2D(32, (3, 3))(inputs)
X=BatchNormalization()(X)
X=Activation('relu')(X)
X=self.add_layer(X,32)
# X=self.google_layer(X)
X=MaxPooling2D(pool_size=(2, 2),strides=(2,2))(X)
X=Conv2D(64, (3, 3),kernel_regularizer=regularizers.l2(0.01))(X)
X=BatchNormalization()(X)
X=Activation('relu')(X)
X=self.add_layer(X,64)
# X = self.google_layer(X)
X = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(X)
X=Conv2D(64, (3, 3))(X)
X=BatchNormalization()(X)
X=Activation('relu')(X)
X=MaxPooling2D(pool_size=(2, 2),strides=(2,2))(X)
X = self.add_layer(X, 64)
# X = self.google_layer(X)
X=Conv2D(32, (3, 3),kernel_regularizer=regularizers.l2(0.01))(X)
X=BatchNormalization()(X)
X=Activation('relu')(X)
X=self.add_layer(X,32)
# X = self.google_layer(X)
X = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(X)
X=Conv2D(64, (3, 3))(X)
X=BatchNormalization()(X)
X=Activation('relu')(X)
X=self.add_layer(X,64)
# X = self.google_layer(X)
X=Flatten()(X)
X=Dense(256, activation='relu')(X)
X=Dropout(0.5)(X)
predictions=Dense(4, activation='softmax')(X)
model = Model(inputs=inputs, outputs=predictions)
# sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
model.fit(self.x_train, self.y_train, batch_size=self.batch_size, epochs=self.epoch_size, class_weight = 'auto',validation_split=0.1)
model.save('model_google_layer.h5')
score = model.evaluate(self.x_test, self.y_test, batch_size=self.batch_size)
print(score)
image_handle.py
import numpy as np
from PIL import Image
import random
import re
import os
def get_image_name(image_name):
image_name=re.split('.jpg', image_name)
name=re.split('2018',image_name[0])
return name[0]
def one_hot_vector(image_label,image_label_list):
classes=len(image_label_list)
one_hot_label = np.zeros(shape=(image_label.shape[0], classes+1)) ##生成全0矩阵
one_hot_label[np.arange(0, image_label.shape[0]), image_label] = 1
return one_hot_label
def batch_generate(x_train,y_train,batch_size):
batch_x=[]
batch_y=[]
for i in range(batch_size):
t = random.randint(0, 249)
batch_x.append(x_train[t])
batch_y.append(y_train[t])
return batch_x,batch_y
def get_image_data(image_dir,resize_width,resize_height,data,image_label,image_label_list):
j=0
image_vec=[]
for fn in os.listdir(image_dir):
image_name = get_image_name(fn)
for i in range(0, 4):
if image_label_list[i] == image_name:
image_name = i
image = Image.open(image_dir + fn) # 原始图片过大
image_down = image.resize((resize_width,resize_height), Image.ANTIALIAS)
image_vec.append(image_down)
arr = np.asarray(image_down, dtype="float32")
data[j, :, :, :] = arr
j = j + 1
image_label.append(image_name)
return data,image_label,image_vec
训练中~
model_test.py
import numpy as np
import keras
from keras.models import Sequential,load_model
from keras.layers import Dense, Dropout, Flatten,Input
from keras.layers import Conv2D, MaxPooling2D,merge
from keras.layers import BatchNormalization,Activation
from sklearn.model_selection import train_test_split
from keras.optimizers import SGD
from keras.models import Model
import tensorflow as tf
from PIL import Image,ImageDraw,ImageFont
from image_handle import *
import os
import cv2
from keras import backend as K
K.clear_session()
start=10
end=11
image_number=1451
resize_width=300
resize_height=300
image_resize=[]
image_vector=[]
image_label=[]
image_label_list=['擦花','漏底','碰凹','凸粉'] #漏底占的比例太大了，导致后面的预测全部都偏向该物体
data = np.empty((22,300, 300,3), dtype="float32")
image_dir='C:/Users/18301/Desktop/test_image/'
data,image_label,image_vec=get_image_data(image_dir,resize_width,resize_height,data,image_label,image_label_list)
#准备好数据和标签送进VGG网络中
X_train=data
Y_train = keras.utils.to_categorical(image_label,4) #转换成one-hot向量
# print(X_train)
print(Y_train)
x_train=X_train[start:end]
y_train=Y_train[start:end]
model = load_model('model_google_layer.h5')
preds = model.predict(x_train)
print(preds)
list_pre= preds[0].tolist()
object_index=list_pre.index(max(list_pre))
y_=Y_train[start:end][0]
y_=y_.tolist()
print(y_)
true_object_index=y_.index(max(y_))
print(object_index)
print(true_object_index)
s_pre=image_label_list[object_index]
s_true=image_label_list[true_object_index]
print(s_pre)
print(s_true)
image=image_vec[start]
draw = ImageDraw.Draw(image)
############注意：这里检测出来的物体种类，擦花由于特征不够明显，基本上被判断成凸粉，这一点需要改善#################
s_pre_out='检测出的缺陷种类为：'+s_pre
s_true_out='真实缺陷种类为：'+s_true
print(s_pre_out)
print(s_true_out)
ttfront = ImageFont.truetype('simhei.ttf', 20)#字体大小
draw.text((30,40),str(s_pre_out), fill = (255, 0 ,0), font=ttfront)
draw.text((50,60),str(s_true_out), fill = (255, 0 ,0), font=ttfront)
image.show()
from keras import backend as K
K.clear_session()
最终识别结果：
[[1.4585784e-34 0.0000000e+00 1.0000000e+00 0.0000000e+00]]
[0.0, 0.0, 1.0, 0.0]
检测出的缺陷种类为：碰凹
真实缺陷种类为：碰凹
[[1.3628840e-03 2.3904990e-18 5.2082274e-08 9.9863702e-01]]
[0.0, 0.0, 0.0, 1.0]
检测出的缺陷种类为：凸粉
真实缺陷种类为：凸粉
[[9.3814194e-01 1.4996887e-09 1.5372947e-04 6.1704315e-02]]
[1.0, 0.0, 0.0, 0.0]
检测出的缺陷种类为：擦花
真实缺陷种类为：擦花
[[0. 1. 0. 0.]]
[0.0, 1.0, 0.0, 0.0]
检测出的缺陷种类为：漏底
真实缺陷种类为：漏底
源代码请见：深度学习实现工业零件缺陷检测源代码
训练图像请见：工业零件缺陷图像
最后，欢迎加入3D视觉工坊，一起交流学习~
