用Python和OpenCV提取顏色直方圖特徵
阿新 • • 發佈：2019-01-27
用OpenCV中自帶的cv2.calHist()函式求影象的顏色直方圖特徵
import cv2
import numpy
image = cv2.imread("D:/lena.jpg", 0)
hist = cv2.calcHist([image], [0], None, [256], [0.0,255.0])
上面程式是以灰度圖的方式計算顏色直方圖特徵，cv2.calcHist()函式的引數
第一個引數[image]，必須帶[]， 是讀入後的影象
第二個引數[0]，必須帶[]，指定通道,若為灰度圖則為[0]，若彩色圖，則[0]、[1]、[2]分別對應於B、G、R通道
第三個引數是掩膜Mask，指定ROI區域，若對整張影象取特徵，則置為None
第四個引數是bins的個數，必須帶[]
第五個引數是畫素值範圍
來看一下hist的內容：
>>> hist array([[ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 1.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 1.00000000e+00], [ 2.00000000e+00], [ 5.00000000e+00], [ 8.00000000e+00], [ 1.70000000e+01], [ 2.40000000e+01], [ 5.50000000e+01], [ 8.30000000e+01], [ 1.12000000e+02], [ 1.60000000e+02], [ 2.02000000e+02], [ 2.81000000e+02], [ 3.41000000e+02], [ 4.20000000e+02], [ 5.28000000e+02], [ 6.11000000e+02], [ 7.09000000e+02], [ 8.85000000e+02], [ 1.03200000e+03], [ 1.28200000e+03], [ 1.44100000e+03], [ 1.61700000e+03], [ 1.68600000e+03], [ 1.90500000e+03], [ 1.88700000e+03], [ 2.00000000e+03], [ 2.00000000e+03], [ 2.07200000e+03], [ 2.01000000e+03], [ 2.02500000e+03], [ 1.89100000e+03], [ 1.88400000e+03], [ 1.76200000e+03], [ 1.71400000e+03], [ 1.53300000e+03], [ 1.44200000e+03], [ 1.26100000e+03], [ 1.26800000e+03], [ 1.18500000e+03], [ 1.09800000e+03], [ 9.70000000e+02], [ 9.78000000e+02], [ 9.10000000e+02], [ 8.83000000e+02], [ 8.23000000e+02], [ 8.02000000e+02], [ 7.42000000e+02], [ 8.03000000e+02], [ 8.42000000e+02], [ 8.16000000e+02], [ 7.85000000e+02], [ 8.78000000e+02], [ 8.59000000e+02], [ 8.70000000e+02], [ 8.72000000e+02], [ 8.67000000e+02], [ 9.57000000e+02], [ 8.88000000e+02], [ 9.79000000e+02], [ 9.06000000e+02], [ 8.35000000e+02], [ 9.76000000e+02], [ 9.40000000e+02], [ 9.53000000e+02], [ 9.58000000e+02], [ 9.96000000e+02], [ 1.06100000e+03], [ 1.15800000e+03], [ 1.14400000e+03], [ 1.16600000e+03], [ 1.22200000e+03], [ 1.25300000e+03], [ 1.44600000e+03], [ 1.46600000e+03], [ 1.59400000e+03], [ 1.85500000e+03], [ 1.81000000e+03], [ 1.93400000e+03], [ 1.96400000e+03], [ 1.89900000e+03], [ 2.00200000e+03], [ 1.87200000e+03], [ 1.82300000e+03], [ 1.68900000e+03], [ 1.59800000e+03], [ 1.53900000e+03], [ 1.39800000e+03], [ 1.44100000e+03], [ 1.37500000e+03], [ 1.33400000e+03], [ 1.38900000e+03], [ 1.37600000e+03], [ 1.38000000e+03], [ 1.41300000e+03], [ 1.40200000e+03], [ 1.45500000e+03], [ 1.46400000e+03], [ 1.62700000e+03], [ 1.62600000e+03], [ 1.60400000e+03], [ 1.80800000e+03], [ 1.82700000e+03], [ 2.03400000e+03], [ 2.09700000e+03], [ 2.21300000e+03], [ 2.35200000e+03], [ 2.43300000e+03], [ 2.36800000e+03], [ 2.46700000e+03], [ 2.30400000e+03], [ 2.27600000e+03], [ 2.05000000e+03], [ 1.96000000e+03], [ 1.91000000e+03], [ 1.88900000e+03], [ 1.92500000e+03], [ 2.05800000e+03], [ 2.04300000e+03], [ 2.33100000e+03], [ 2.30200000e+03], [ 2.34000000e+03], [ 2.39100000e+03], [ 2.47500000e+03], [ 2.43100000e+03], [ 2.25300000e+03], [ 2.27100000e+03], [ 2.23300000e+03], [ 2.19300000e+03], [ 2.27900000e+03], [ 2.30300000e+03], [ 2.42600000e+03], [ 2.67100000e+03], [ 2.64700000e+03], [ 2.71900000e+03], [ 2.73300000e+03], [ 2.58300000e+03], [ 2.43700000e+03], [ 2.25600000e+03], [ 2.07600000e+03], [ 1.91100000e+03], [ 1.74400000e+03], [ 1.64400000e+03], [ 1.47100000e+03], [ 1.43000000e+03], [ 1.39500000e+03], [ 1.28800000e+03], [ 1.23000000e+03], [ 1.19300000e+03], [ 1.17000000e+03], [ 1.24400000e+03], [ 1.26800000e+03], [ 1.22900000e+03], [ 1.23700000e+03], [ 1.26300000e+03], [ 1.24200000e+03], [ 1.16400000e+03], [ 1.11500000e+03], [ 1.03900000e+03], [ 9.53000000e+02], [ 8.19000000e+02], [ 7.48000000e+02], [ 6.62000000e+02], [ 6.37000000e+02], [ 6.41000000e+02], [ 5.97000000e+02], [ 6.63000000e+02], [ 6.25000000e+02], [ 7.11000000e+02], [ 7.87000000e+02], [ 7.77000000e+02], [ 8.10000000e+02], [ 8.73000000e+02], [ 9.09000000e+02], [ 9.61000000e+02], [ 9.53000000e+02], [ 8.37000000e+02], [ 8.52000000e+02], [ 8.67000000e+02], [ 8.39000000e+02], [ 9.10000000e+02], [ 8.33000000e+02], [ 9.02000000e+02], [ 9.20000000e+02], [ 9.46000000e+02], [ 9.68000000e+02], [ 1.01000000e+03], [ 1.09300000e+03], [ 1.08000000e+03], [ 9.57000000e+02], [ 9.67000000e+02], [ 1.02200000e+03], [ 8.74000000e+02], [ 7.03000000e+02], [ 5.66000000e+02], [ 4.62000000e+02], [ 3.97000000e+02], [ 3.65000000e+02], [ 3.35000000e+02], [ 2.54000000e+02], [ 2.07000000e+02], [ 2.13000000e+02], [ 1.76000000e+02], [ 1.20000000e+02], [ 1.06000000e+02], [ 7.70000000e+01], [ 6.50000000e+01], [ 3.60000000e+01], [ 3.50000000e+01], [ 2.50000000e+01], [ 1.80000000e+01], [ 1.00000000e+01], [ 9.00000000e+00], [ 3.00000000e+00], [ 4.00000000e+00], [ 1.00000000e+00], [ 2.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 1.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 1.00000000e+00], [ 0.00000000e+00], [ 1.00000000e+00], [ 0.00000000e+00], [ 1.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00], [ 0.00000000e+00]], dtype=float32) >>>