Question

我的目标是找到帧/图像中主要对象的颜色。在我的情况下，图像总是相同的类型。例如，动物农场的森林或新闻记者新闻记者（人）。新闻记者的位置也一样。找出主要对象的主色的简单解决方案是什么（新闻报道））

欢迎任何帮助。谢谢

已添加EDIT代码

import cv2
from collections import namedtuple
from math import sqrt
import random
import webcolors


try:
 import Image
except ImportError:
 from PIL import Image

Point = namedtuple('Point', ('coords', 'n', 'ct'))
Cluster = namedtuple('Cluster', ('points', 'center', 'n'))

def get_points(img):
 points = []
 w, h = img.size
 for count, color in img.getcolors(w * h):
    points.append(Point(color, 3, count))
 return points

 rtoh = lambda rgb: '#%s' % ''.join(('%02x' % p for p in rgb))

def colorz(filename, n=3):
 img = Image.open(filename)
 img.thumbnail((200, 200))
 w, h = img.size

 points = get_points(img)
 clusters = kmeans(points, n, 1)
 rgbs = [map(int, c.center.coords) for c in clusters]
 return map(rtoh, rgbs)

def euclidean(p1, p2):
  return sqrt(sum([
  (p1.coords[i] - p2.coords[i]) ** 2 for i in range(p1.n)
 ]))

 def calculate_center(points, n):
  vals = [0.0 for i in range(n)]
  plen = 0
  for p in points:
    plen += p.ct
    for i in range(n):
        vals[i] += (p.coords[i] * p.ct)
   return Point([(v / plen) for v in vals], n, 1)

def kmeans(points, k, min_diff):
 clusters = [Cluster([p], p, p.n) for p in random.sample(points, k)]

 while 1:
   plists = [[] for i in range(k)]

   for p in points:
        smallest_distance = float('Inf')
        for i in range(k):
            distance = euclidean(p, clusters[i].center)
            if distance < smallest_distance:
                smallest_distance = distance
                idx = i
        plists[idx].append(p)

    diff = 0
    for i in range(k):
        old = clusters[i]
        center = calculate_center(plists[i], old.n)
        new = Cluster(plists[i], center, old.n)
        clusters[i] = new
        diff = max(diff, euclidean(old.center, new.center))

    if diff < min_diff:
        break

 return clusters

def main():

 img = cv2.imread('d:/Emmanu/project-data/b1.jpg')
 res=cv2.resize(img,(400,300))
 crop_img = res[100:200, 150:250]
 cv2.imwrite("d:/Emmanu/project-data/color-test.jpg", crop_img)
 g= colorz('d:/Emmanu/project-data/color-test.jpg',1)
 k=g[0]
 print k
 f=webcolors.hex_to_rgb(k)
 print webcolors.rgb_to_name(f, spec='css3')

if __name__ == '__main__':main()

问题是这会返回整个图像中的主要颜色而不是主要对象

Answer 1

如果你拍摄整个图像的颜色，在大多数情况下你会得到错误的答案，因为背景更多。如果你的图像尺寸是固定的，你确定对象的位置最简单的解决方案是裁剪图像在你期望对象的位置。在大多数情况下它会起作用。

为了裁剪

import cv2
img = cv2.imread("'d:/Emmanu/project-data/b1.jpg'")
crop_img = img[200:400, 100:300] # Crop from x, y, w, h -> 100, 200, 300, 400
# NOTE: its img[y: y + h, x: x + w] and *not* img[x: x + w, y: y + h]
cv2.imshow("cropped", crop_img)
cv2.waitKey(0)

现在把这个crop_image作为你代码的输入。在大多数情况下，它会提供正确的解决方案。没有什么比这更简单了。我认为这会有所帮助。

如何在固定大小的图像中查找主要对象的颜色

1 个答案: