第七节筛选和聚类

2023-09-23 23:38:27

一、哈希算法筛选图片，在网页展示

from flask import Flask,render_template
import cv2
import os
 
app=Flask(__name__)
 
def aHash(img):
    # 缩放为8*8
    img = cv2.resize(img, (8, 8))
 
    # 转化为灰度图
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    # s为像素和初值为0，hash_str为hash值初值为''
    s = 0
    hash_str = ''
    # 遍历累加求像素和
    for i in range(8):
        for j in range(8):
            s = s + gray[i, j]
    # 求平均灰度
    avg = s / 64
    # 灰度大于平均值为1相反为0生成图片的hash值
    for i in range(8):
        for j in range(8):
            if gray[i, j] > avg:
                hash_str = hash_str + '1'
            else:
                hash_str = hash_str + '0'
    return hash_str
 
# Hash值对比
def cmpHash(hash1, hash2):
    n = 0
    print(hash1)
    print(hash2)
    # hash长度不同则返回-1代表传参出错
    if len(hash1) != len(hash2):
        return -1
    # 遍历判断
    for i in range(len(hash1)):
        # 不相等则n计数+1，n最终为相似度
        if hash1[i] != hash2[i]:
            n = n + 1
    sim=1-n/64
    return sim
 
def genFrame():
    v_path='static/video.mp4'
    image_save='static/pic'
 
    if not(os.path.exists(image_save)):
        os.mkdir(image_save)
 
    cap=cv2.VideoCapture(v_path)
    fc=cap.get(cv2.CAP_PROP_FRAME_COUNT)
 
    _,img1=cap.read()
    cv2.imwrite('static/Hash2021/image{}.jpg'.format(0),img1)
 
    for i in range(int(fc-1)):
        _,img2=cap.read()
        hash1=aHash(img1)
        hash2=aHash(img2)
        n=cmpHash(hash1,hash2)
        if n<0.6:
 
            cv2.imwrite('static/Hash2021/image{}.jpg'.format(i),img2)
            img1=img2
 
genFrame()

htlml中写

<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <title>Title</title>
</head>
<body>
<br>
均值哈希帧数:{{framecount}}<br>
{% for i in range(framecount)%}
<img height="40" src="static/Hash2021/{{filename[i]}}"/>
{{filename[i]}}
{% endfor%}
</body>
</html>

为加入一个路由器程序，在main加上

@app.route('/shot')
def shot():
    path='static/Hash2021'
    filename=os.listdir(path)
    framecount=len(filename)
 
    print(filename)
    print(type(filename))
 
    print(filename)
 
    return render_template('hash.html',filename=filename,framecount=framecount)

得到

二、聚类

1、通过颜色聚类

import numpy as np
import os
from PIL import Image
import matplotlib.pyplot as plt
 
im=np.array(Image.open('IMG_7433.JPG'))
 
def colorz(filename,n=3):
    img=Image.open(filename)
    img=img.rotate(-90)
    img.thumbnail((200,200))
    w,h=img.size
    print(w,h)
    print('w*h=',w*h)
    plt.axis('off')
    plt.imshow(img)
    plt.show()
    points=[]
    for count,color in img.getcolors(w*h):
        points.append(color)
    return points
colorz('IMG_7433.JPG',3)

2、通过缩略聚类

import os
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
 
im=np.array(Image.open('hk7.jpg'))
 
#用缩略图聚类
def colorz(filename,n=3):
    img=Image.open(filename)
    img=img.rotate(-90)
    img.thumbnail((200,200))
    w,h=img.size
    print(w,h)
    print('w*h=',w*h)
    plt.axis('off')
    plt.imshow(img)
    plt.show()
    points=[]
    for count,color in img.getcolors(w*h):
        points.append(color)
    return points
 
colorz('hk7.jpg',3)

码农公寓

相关文章