LBP图像特征提取分类python

LBP（Local Binary Pattern）是一种用于图像纹理分析的局部特征描述符。LBP算法可以用于图像分类、人脸识别等领域。下面是一个简单的LBP图像特征提取和分类的python代码示例：

import numpy as np
import cv2
from sklearn.svm import LinearSVC
from sklearn.metrics import accuracy_score

# 计算LBP特征
def calc_lbp_feature(img):
    rows, cols = img.shape
    lbp_feature = np.zeros((rows-2, cols-2))

    for i in range(1, rows-1):
        for j in range(1, cols-1):
            center = img[i, j]
            code = 0
            code |= (img[i-1, j-1] > center) << 7
            code |= (img[i-1, j] > center) << 6
            code |= (img[i-1, j+1] > center) << 5
            code |= (img[i, j+1] > center) << 4
            code |= (img[i+1, j+1] > center) << 3
            code |= (img[i+1, j] > center) << 2
            code |= (img[i+1, j-1] > center) << 1
            code |= (img[i, j-1] > center) << 0
            lbp_feature[i-1, j-1] = code

    return lbp_feature.flatten()

# 加载数据集
def load_dataset():
    images = []
    labels = []

    for i in range(1, 41): # 40个人
        for j in range(1, 11): # 每个人10张图片
            img = cv2.imread(f"att_faces/s{i}/{j}.pgm", cv2.IMREAD_GRAYSCALE)
            images.append(img)
            labels.append(i)

    return images, labels

# 提取LBP特征并训练分类器
def train_lbp_classifier(images, labels):
    data = []
    for img in images:
        feature = calc_lbp_feature(img)
        data.append(feature)

    clf = LinearSVC()
    clf.fit(data, labels)

    return clf

# 测试分类器
def test_lbp_classifier(clf, images, labels):
    pred_labels = []
    for img in images:
        feature = calc_lbp_feature(img)
        pred_label = clf.predict([feature])[0]
        pred_labels.append(pred_label)

    acc = accuracy_score(labels, pred_labels)
    print(f"Accuracy: {acc}")

if __name__ == "__main__":
    images, labels = load_dataset()
    clf = train_lbp_classifier(images, labels)
    test_lbp_classifier(clf, images, labels)

在这个示例中，我们使用了AT&T人脸数据集中的图像进行训练和测试。在训练过程中，我们提取了每个图像的LBP特征，并使用LinearSVC（线性支持向量机）训练了一个分类器。在测试过程中，我们使用相同的LBP特征来对测试图像进行分类，并计算了分类器的准确率。