Opencv k-平均聚类算法第三步

k-平均聚类算法(k -means Clustering)第三步:调整初期类别。

使用k-平均聚类算法将8张train@@@.jpg完美地聚类吧!

在这里,通过变更np.random.seed()的值和np.random.random() < th中分割类别的阈值th来更好地预测图片的类别吧!由于train@@@.jpg的图像数量是问题89​的两倍,因此可以更容易地聚类。

这只能通过反复试验来完成。

python实现:

import cv2
import numpy as np
import matplotlib.pyplot as plt
from glob import glob

# Dicrease color
def dic_color(img):
    img //= 63
    img = img * 64 + 32
    return img


# Database
def get_DB():
    # get training image path
    train = glob("dataset/train_*")
    train.sort()

    # prepare database
    db = np.zeros((len(train), 13), dtype=np.int32)
    pdb = []

    # each train
    for i, path in enumerate(train):
        # read image
        img = dic_color(cv2.imread(path))
        # histogram
        for j in range(4):
            db[i, j] = len(np.where(img[..., 0] == (64 * j + 32))[0])
            db[i, j+4] = len(np.where(img[..., 1] == (64 * j + 32))[0])
            db[i, j+8] = len(np.where(img[..., 2] == (64 * j + 32))[0])

        # get class
        if 'akahara' in path:
            cls = 0
        elif 'madara' in path:
            cls = 1

        # store class label
        db[i, -1] = cls

        # add image path
        pdb.append(path)

    return db, pdb

# k-Means
def k_means(db, pdb, Class=2, th=0.5):
    # copy database
    feats = db.copy()

    # initiate random seed
    np.random.seed(4)

    # assign random class 
    for i in range(len(feats)):
        if np.random.random() < th:
            feats[i, -1] = 0
        else:
            feats[i, -1] = 1

    while True:
        # prepare greavity
        gs = np.zeros((Class, 12), dtype=np.float32)
        change_count = 0

        # compute gravity
        for i in range(Class):
            gs[i] = np.mean(feats[np.where(feats[..., -1] == i)[0], :12], axis=0)

        # re-labeling
        for i in range(len(feats)):
            # get distance each nearest graviry
            dis = np.sqrt(np.sum(np.square(np.abs(gs - feats[i, :12])), axis=1))

            # get new label
            pred = np.argmin(dis, axis=0)

            # if label is difference from old label
            if int(feats[i, -1]) != pred:
                change_count += 1
                feats[i, -1] = pred

        if change_count < 1:
            break

    for i in range(db.shape[0]):
        print(pdb[i], " Pred:", feats[i, -1])


db, pdb = get_DB()
k_means(db, pdb, th=0.3)


答案:

train_akahara_1.jpg  Pred: 1
train_akahara_2.jpg  Pred: 1
train_akahara_3.jpg  Pred: 1
train_akahara_4.jpg  Pred: 1
train_akahara_5.jpg  Pred: 1
train_madara_1.jpg  Pred: 0
train_madara_2.jpg  Pred: 0
train_madara_3.jpg  Pred: 0
train_madara_4.jpg  Pred: 0
train_madara_5.jpg  Pred: 0

Python教程

Java教程

Web教程

数据库教程

图形图像教程

大数据教程

开发工具教程

计算机教程