Kaggle-Plant Seedlings Classification-(多分类+CNN+图形处理)

Plant Seedlings Classification

题意：

就是给出很多图片，预测出图片中的小草是什么类型的。

数据处理：

1.去除图片背景，只保留物体。
2.图片数据加强。

建立模型：

1.CNN的Sequential()，多层卷积块和全连接层。
2.学习率降低回调函数。
3.查看混淆矩阵进一步考虑优化。

代码：

import cv2
from glob import glob
import numpy as np
from matplotlib import pyplot as plt
import math
import pandas as pd# 设置图像缩放尺寸和随机种子
ScaleTo = 70  # 图像缩放尺寸
seed = 7  # 随机种子，保证结果可复现print("读取训练图片" + "/"*70 + "\n")
path = '/kaggle/input/plant-seedlings-classification/train/*/*.png'  # 训练集路径
files = glob(path)  # 获取所有图像文件路径trainImg = []  # 存储训练图像
trainLabel = []  # 存储训练标签
j = 1
num = len(files)# 读取图像并调整大小，同时获取标签
for img in files:print(str(j) + "/" + str(num), end="\r")trainImg.append(cv2.resize(cv2.imread(img), (ScaleTo, ScaleTo)))  # 读取图像并调整大小trainLabel.append(img.split('/')[-2])  # 从路径中提取标签（文件夹名）j += 1trainImg = np.asarray(trainImg)  # 转换为numpy数组
trainLabel = pd.DataFrame(trainLabel)  # 转换为DataFrame# 显示前8张训练图像
for i in range(8):plt.subplot(2, 4, i + 1)plt.imshow(trainImg[i])print("去掉图片背景，只保留物体本身" + "/"*70 + "\n")
clearTrainImg = []  # 存储去背景后的图像
examples = []
getEx = True# 对每张图像进行背景去除处理
for img in trainImg:# 使用高斯模糊减少噪声blurImg = cv2.GaussianBlur(img, (5, 5), 0)# 转换为HSV颜色空间，便于颜色分割hsvImg = cv2.cvtColor(blurImg, cv2.COLOR_BGR2HSV)# 创建掩码，提取绿色植物区域lower_green = (25, 40, 50)  # 绿色下界upper_green = (75, 255, 255)  # 绿色上界mask = cv2.inRange(hsvImg, lower_green, upper_green)  # 创建二值掩码kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (11, 11))  # 定义结构元素mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)  # 闭运算填充空洞# 创建布尔掩码bMask = mask > 0# 应用掩码，提取植物区域clear = np.zeros_like(img, np.uint8)  # 创建空白图像clear[bMask] = img[bMask]  # 仅保留掩码区域的像素clearTrainImg.append(clear)  # 保存去背景后的图像# 显示处理过程示例if getEx:plt.subplot(2, 3, 1); plt.imshow(img)  # 原始图像plt.subplot(2, 3, 2); plt.imshow(blurImg)  # 模糊图像plt.subplot(2, 3, 3); plt.imshow(hsvImg)  # HSV图像plt.subplot(2, 3, 4); plt.imshow(mask)  # 掩码plt.subplot(2, 3, 5); plt.imshow(bMask)  # 布尔掩码plt.subplot(2, 3, 6); plt.imshow(clear)  # 去背景图像getEx = FalseclearTrainImg = np.asarray(clearTrainImg)  # 转换为numpy数组# 显示前8张去背景后的图像
for i in range(8):plt.subplot(2, 4, i + 1)plt.imshow(clearTrainImg[i])clearTrainImg = clearTrainImg / 255  # 归一化处理print("处理训练数据集的label" + "/"*70 + "\n")
from tensorflow.keras.utils import to_categorical
from sklearn import preprocessing
import matplotlib.pyplot as plt# 标签编码
le = preprocessing.LabelEncoder()
le.fit(trainLabel[0])
print("类别: " + str(le.classes_))  # 显示所有类别
encodeTrainLabels = le.transform(trainLabel[0])  # 将标签转换为数字# 转换为one-hot编码
clearTrainLabel = to_categorical(encodeTrainLabels)
num_clases = clearTrainLabel.shape[1]
print("类别数量: " + str(num_clases))# 可视化各类别样本数量分布
trainLabel[0].value_counts().plot(kind='bar')print("分离训练和验证集" + "/"*70 + "\n")
from sklearn.model_selection import train_test_split# 划分训练集和验证集，保持类别平衡
trainX, testX, trainY, testY = train_test_split(clearTrainImg, clearTrainLabel,test_size=0.1, random_state=seed,stratify = clearTrainLabel)print("数据集加强" + "/"*70 + "\n")
from tensorflow.keras.preprocessing.image import ImageDataGenerator# 创建数据增强器，增加训练样本多样性
datagen = ImageDataGenerator(rotation_range=180,  # 随机旋转角度范围zoom_range = 0.1,    # 随机缩放范围width_shift_range=0.1,  # 水平平移范围height_shift_range=0.1,  # 垂直平移范围horizontal_flip=True,  # 随机水平翻转vertical_flip=True  # 随机垂直翻转)
datagen.fit(trainX)  # 应用数据增强器print("构造神经网络CNN model" + "/"*70 + "\n")
import numpy
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D, BatchNormalizationnumpy.random.seed(seed)  # 固定随机种子# 构建CNN模型
model = Sequential()# 第一层卷积块
model.add(Conv2D(filters=64, kernel_size=(5, 5), input_shape=(ScaleTo, ScaleTo, 3), activation='relu'))
model.add(BatchNormalization(axis=3))  # 批量归一化
model.add(Conv2D(filters=64, kernel_size=(5, 5), activation='relu'))
model.add(MaxPooling2D((2, 2)))  # 最大池化
model.add(BatchNormalization(axis=3))
model.add(Dropout(0.1))  # Dropout正则化# 第二层卷积块
model.add(Conv2D(filters=128, kernel_size=(5, 5), activation='relu'))
model.add(BatchNormalization(axis=3))
model.add(Conv2D(filters=128, kernel_size=(5, 5), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(BatchNormalization(axis=3))
model.add(Dropout(0.1))# 第三层卷积块
model.add(Conv2D(filters=256, kernel_size=(5, 5), activation='relu'))
model.add(BatchNormalization(axis=3))
model.add(Conv2D(filters=256, kernel_size=(5, 5), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(BatchNormalization(axis=3))
model.add(Dropout(0.1))# 全连接层
model.add(Flatten())  # 展平多维数据
model.add(Dense(256, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5))  # 较高的Dropout率防止过拟合model.add(Dense(256, activation='relu'))
model.add(BatchNormalization())
model.add(Dropout(0.5))model.add(Dense(num_clases, activation='softmax'))  # 输出层，使用softmax激活函数model.summary()  # 显示模型结构# 编译模型
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])print("训练model" + "/"*70 + "\n")from keras.callbacks import ModelCheckpoint, ReduceLROnPlateau, CSVLogger# 学习率降低回调函数
learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc',patience=3,  # 等待3个epoch没有改善verbose=1,   # 显示更新信息factor=0.4,  # 学习率降低因子min_lr=0.00001)  # 最小学习率callbacks_list = [learning_rate_reduction]  # 回调函数列表# 训练模型
hist = model.fit(datagen.flow(trainX, trainY, batch_size=75),epochs=35, validation_data=(testX, testY),steps_per_epoch=trainX.shape[0], callbacks=callbacks_list)print("混淆矩阵" + "/"*70 + "\n")
from sklearn.metrics import confusion_matrix
import itertools# 绘制混淆矩阵函数
def plot_confusion_matrix(cm, classes,normalize=False,title='Confusion matrix',cmap=plt.cm.Blues):fig = plt.figure(figsize=(10, 10))plt.imshow(cm, interpolation='nearest', cmap=cmap)plt.title(title)plt.colorbar()tick_marks = np.arange(len(classes))plt.xticks(tick_marks, classes, rotation=90)plt.yticks(tick_marks, classes)if normalize:cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]thresh = cm.max() / 2.for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):plt.text(j, i, cm[i, j],horizontalalignment="center",color="white" if cm[i, j] > thresh else "black")plt.tight_layout()plt.ylabel('真实标签')plt.xlabel('预测标签')# 预测验证集
predY = model.predict(testX)
predYClasses = np.argmax(predY, axis=1)
trueY = np.argmax(testY, axis=1)# 计算混淆矩阵
confusionMTX = confusion_matrix(trueY, predYClasses)# 绘制混淆矩阵
plot_confusion_matrix(confusionMTX, classes=le.classes_)print("处理测试集" + "/"*70 + "\n")
path = '/kaggle/input/plant-seedlings-classification/test/*.png'  # 测试集路径
files = glob(path)testImg = []  # 存储测试图像
testId = []  # 存储测试图像ID
j = 1
num = len(files)# 读取测试图像
for img in files:print("读取图像: " + str(j) + "/" + str(num), end='\r')testId.append(img.split('/')[-1])  # 提取图像IDtestImg.append(cv2.resize(cv2.imread(img), (ScaleTo, ScaleTo)))  # 调整图像大小j += 1testImg = np.asarray(testImg)  # 转换为numpy数组# 显示前8张测试图像
for i in range(8):plt.subplot(2, 4, i + 1)plt.imshow(testImg[i])# 对测试图像进行背景去除处理（与训练集相同）
clearTestImg = []
examples = []
getEx = Truefor img in testImg:# 使用高斯模糊blurImg = cv2.GaussianBlur(img, (5, 5), 0)# 转换为HSV颜色空间hsvImg = cv2.cvtColor(blurImg, cv2.COLOR_BGR2HSV)# 创建掩码（绿色植物区域）lower_green = (25, 40, 50)upper_green = (75, 255, 255)mask = cv2.inRange(hsvImg, lower_green, upper_green)kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (11, 11))mask = cv2.morphologyEx(mask, cv2.MORPH_CLOSE, kernel)# 创建布尔掩码bMask = mask > 0# 应用掩码，提取植物区域clear = np.zeros_like(img, np.uint8)clear[bMask] = img[bMask]clearTestImg.append(clear)  # 保存去背景后的图像# 显示处理示例if getEx:plt.subplot(2, 3, 1); plt.imshow(img)  # 原始图像plt.subplot(2, 3, 2); plt.imshow(blurImg)  # 模糊图像plt.subplot(2, 3, 3); plt.imshow(hsvImg)  # HSV图像plt.subplot(2, 3, 4); plt.imshow(mask)  # 掩码plt.subplot(2, 3, 5); plt.imshow(bMask)  # 布尔掩码plt.subplot(2, 3, 6); plt.imshow(clear)  # 去背景图像getEx = FalseclearTestImg = np.asarray(clearTestImg)  # 转换为numpy数组# 显示前8张去背景后的测试图像
for i in range(8):plt.subplot(2, 4, i + 1)plt.imshow(clearTestImg[i])clearTestImg = clearTestImg / 255  # 归一化处理# 预测测试集
pred = model.predict(clearTestImg)# 处理预测结果
predNum = np.argmax(pred, axis=1)  # 获取最大概率的类别索引
predStr = le.classes_[predNum]  # 将索引转换为类别名称# 保存结果到CSV文件
res = {'file': testId, 'species': predStr}
res = pd.DataFrame(res)
res.to_csv("/kaggle/working/res.csv", index=False)