基于图像的苹果尺寸测量与坏果检测SVM代码

以下是基于图像的苹果尺寸测量与坏果检测的SVM代码示例：

首先，导入所需的库和模块：

import cv2
import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.model_selection import train_test_split

接下来，定义函数来提取苹果的特征：

def get_apple_features(img):
    # 转换为HSV色彩空间
    hsv = cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
    # 提取苹果的颜色特征
    lower_red = np.array([0, 70, 50])
    upper_red = np.array([10, 255, 255])
    mask1 = cv2.inRange(hsv, lower_red, upper_red)
    lower_red = np.array([170, 70, 50])
    upper_red = np.array([180, 255, 255])
    mask2 = cv2.inRange(hsv, lower_red, upper_red)
    mask = cv2.bitwise_or(mask1, mask2)
    # 提取苹果的形状特征
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    ret, thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
    contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    cnt = max(contours, key=cv2.contourArea)
    x, y, w, h = cv2.boundingRect(cnt)
    aspect_ratio = float(w) / h
    extent = cv2.contourArea(cnt) / (w * h)
    hull = cv2.convexHull(cnt)
    hull_area = cv2.contourArea(hull)
    solidity = float(cv2.contourArea(cnt)) / hull_area
    # 返回特征向量
    return [cv2.countNonZero(mask), aspect_ratio, extent, solidity]

然后，加载数据和标签：

# 加载数据和标签
data = []
labels = []
for i in range(1, 11):
    for j in range(1, 6):
        img = cv2.imread(f"apple{i}_{j}.jpg")
        features = get_apple_features(img)
        data.append(features)
        labels.append(i)

接下来，将数据和标签分为训练集和测试集：

# 将数据和标签分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(data, labels, test_size=0.2, random_state=0)

然后，训练SVM分类器：

# 训练SVM分类器
clf = svm.SVC(kernel='linear', C=1.0)
clf.fit(X_train, y_train)

最后，使用训练好的SVM分类器进行坏苹果检测：

# 使用训练好的SVM分类器进行坏苹果检测
img = cv2.imread("apple11.jpg")
features = get_apple_features(img)
label = clf.predict([features])[0]
if label == 11:
    print("This apple is bad.")
else:
    print(f"This apple is apple {label}.")

请注意，此代码示例仅用于说明基于图像的苹果尺寸测量与坏果检测的SVM实现方法，实际应用中可能需要进行更多的优化和改进。