储粮害虫图片CNN识别

注： 图片二值化之前必须灰度化

数据组织格式如下：

# -*- coding: utf-8 -*-

import keras
import random
import os 
from PIL import Image
import numpy as np
from keras.models import Sequential  #序贯模型
from keras.layers import Dense    #全连接层
from keras.layers import Dropout  #随机失活层
from keras.layers import Flatten  #展平层，从卷积层到全连接层必须展平
from keras.layers import Conv2D   #二维卷积层，多用于图像
from keras.layers import MaxPooling2D  #最大值池化
from keras import backend as k
from skimage import filters
import matplotlib.pyplot as plt



#分类标签数组
y_lable = []
#分类标签
classes = 0
#图片计数器
number = 0
for dirname in os.listdir(r'储粮害虫图片'):
    print(dirname)
    for filename in os.listdir(r'储粮害虫图片/'+dirname):
        print(r'储粮害虫图片/'+dirname + '/' + filename)
        #========================================================读取图片=====================================================================================
        image = Image.open('储粮害虫图片/'+dirname + '/' + filename)
        #==================================================获取图片二值化阈值===========================================================================
        #标准化图片大小
        image_resize = image.resize((28, 28))
        #转换成灰度值，它的每个像素用8个bit表示，0表示黑，255表示白，其他数字表示不同的灰度。
        image_l = image_resize.convert('L')
        #将图片对象转换成数组
        image_arr = np.array(image_l)
        #自动获得阈值，并返回
        threshold = filters.threshold_otsu(image_arr)
        # 自定义灰度界限，大于这个值为黑色，小于这个值为白色
        #threshold = 100
        #======================================================图片二值化======================================================
        table = []
        for i in range(256):
            if i < threshold:
                table.append(0)
            else:
                table.append(1)
        # 图片二值化
        photo = image_l.point(table, '1')
        #==========================================================图片保存====================================================
        photo.save("Input/" + str(number) + '.png')
        number = number + 1
        y_lable.append(classes)
    classes = classes + 1

#=======================================================================================

arr = []

for filename in os.listdir(r'Input'):
    image = Image.open('Input/' + filename)
    image_arr = np.array(image)
    result = np.array(image_arr)
    result = result.astype('uint8')
    arr.append(result)
    
x_data = np.array(arr)


 

#生成乱序索引
index = []
for i in range(len(y_lable)):
    index.append(random.randint(0, len(y_lable)-1))

#声明训练集和测试集
train_data_x = []
test_data_x = []
train_data_y = []
test_data_y = []

#生成训练集和测试集
for i in range(0, len(index)):
    if i<= len(index)*70/100:
        train_data_x.append(x_data[index[i]])
        train_data_y.append(y_lable[index[i]])
    else:
        test_data_x.append(x_data[index[i]])
        test_data_y.append(y_lable[index[i]])
        
  
x_train = np.array(train_data_x)
y_train = np.array(train_data_y)
y_train = y_train.astype('uint8')
x_test = np.array(test_data_x)
y_test = np.array(test_data_y)
y_test = y_test.astype('uint8')


#=============================================================================================================
#===============================================模型训练=====================================================================    
batch_size = 10  #一批训练样本128张图片
num_classes = 6  #有10个类别
epochs = 12   #一共迭代12轮


img_rows, img_cols = 28, 28  #图片宽，高


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

#后端可以跑在不同的模型上，比如tensorflow， 不同的工具库对数据的组织形式不同。
#=======================================================================

if k.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)
    input_shape = (1, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)
    input_shape = (img_rows, img_cols, 1)

#=================================================================================


x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255


y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)


#写一个LossHistory类，保存loss和acc
class LossHistory(keras.callbacks.Callback):
    def on_train_begin(self, logs={}):
        self.losses = {'batch':[], 'epoch':[]}
        self.accuracy = {'batch':[], 'epoch':[]}
        self.val_loss = {'batch':[], 'epoch':[]}
        self.val_acc = {'batch':[], 'epoch':[]}

    def on_batch_end(self, batch, logs={}):
        self.losses['batch'].append(logs.get('loss'))
        self.accuracy['batch'].append(logs.get('acc'))
        self.val_loss['batch'].append(logs.get('val_loss'))
        self.val_acc['batch'].append(logs.get('val_acc'))

    def on_epoch_end(self, batch, logs={}):
        self.losses['epoch'].append(logs.get('loss'))
        self.accuracy['epoch'].append(logs.get('acc'))
        self.val_loss['epoch'].append(logs.get('val_loss'))
        self.val_acc['epoch'].append(logs.get('val_acc'))

    def loss_plot(self, loss_type):
        iters = range(len(self.losses[loss_type]))
        plt.figure()
        # acc
        plt.plot(iters, self.accuracy[loss_type], 'r', label='train acc')
        # loss
        plt.plot(iters, self.losses[loss_type], 'g', label='train loss')
        if loss_type == 'epoch':
            # val_acc
            plt.plot(iters, self.val_acc[loss_type], 'b', label='val acc')
            # val_loss
            plt.plot(iters, self.val_loss[loss_type], 'k', label='val loss')
        plt.grid(True)
        plt.xlabel(loss_type)
        plt.ylabel('acc-loss')
        plt.legend(loc="upper right")
        plt.show()
        plt.savefig("result.png")


model = Sequential()  #序贯模型，一个架子

model.add(Conv2D(32, kernel_size=(3,3), activation='relu',input_shape=input_shape))  #卷积层， 32个神经元， 卷积核3x3
model.add(Conv2D(64, (3,3), activation='relu'))  #卷积层， 64个神经元， 卷积核3x3
model.add(MaxPooling2D(pool_size=(2, 2))) #池化层
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu')) #全连接层， 128神经元
model.add(Dropout(0.5))
model.add(Dense(num_classes, activation='softmax'))

#编译，损失函数， 优化函数， 评价标注是准确率
model.compile(loss=keras.losses.categorical_crossentropy, optimizer=keras.optimizers.Adadelta(), metrics=['accuracy'])

history = LossHistory()

#运行 ， verbose步长, 注意加入回调函数
model.fit(x_train, y_train, batch_size= batch_size, epochs=epochs, verbose=1, validation_data=(x_test, y_test), callbacks=[history])


score = model.evaluate(x_test, y_test, verbose=0)


print('Test loss:', score[0])
print('Test accuracy:', score[1])

history.loss_plot('epoch')