





来自Github的口红色号宇宙


https://github.com/Ovilia/lipstick

先用番茄做个实验?

提取这张纯色图片的RGB值在技术上是可行的,getcolor.py代码如下:
import colorsys import PIL.Image as Image def get_dominant_color(image): max_score = 0.0001 dominant_color = None for count,(r,g,b) in image.getcolors(image.size[0]*image.size[1]): # 转为HSV标准 saturation = colorsys.rgb_to_hsv(r/255.0, g/255.0, b/255.0)[1] y = min(abs(r*2104+g*4130+b*802+4096+131072)>>13,235) y = (y-16.0)/(235-16) #忽略高亮色 if y > 0.9: continue score = (saturation+0.1)*count if score > max_score: max_score = score dominant_color = (r,g,b) return dominant_color
import os
import getcolor
from os.path import join as pjoin
from scipy import misc
def load_color(color_dir,list):
count = 0
for dir in os.listdir(color_dir):
img_dir = pjoin(color_dir, dir)
image = getcolor.Image.open(img_dir)
image = image.convert('RGB')
get=getcolor.get_dominant_color(image)
list.append(get)
count = count+1
#print(person_dir)
#print(count)
return count
def Mean_color(count,list):
Mean_R=Mean_G=Mean_B=0
for i in range(count):
tuple=list[i]
Mean_R+=tuple[0]
Mean_G+=tuple[1]
Mean_B+=tuple[2]
MeanC=((int)(Mean_R/count),(int)(Mean_G/count),(int)(Mean_B/count))
return Me当然是口红的数据,文摘菌这儿用到了5个品牌,分别是圣罗兰、香奈儿可可小姐、迪奥、美宝莲、纪梵希,共17个系列,271个口红色号,数据集是一个嵌套的字典数据结构,存为json串的形式,里面记录了每个口红品牌系列下不同口红色号的颜色id、名称、和16进制颜色值,lipstick.json部分数据集展示如下:
{"brands":[{"name":"圣罗兰","series":
[{"name":"莹亮纯魅唇膏","lipsticks":
[{"color":"#D62352","id":"49","name":"撩骚"},
{"color":"#DC4B41","id":"14","name":"一见倾心"},
{"color":"#B22146","id":"05","name":"浮生若梦"},数据集中存储的RGB颜色是16进制的字符串形式,需要将其转换成RGB值,比较两个颜色相近与否,实际上是比较RGB三个分量维度上的误差,最小的口红输出对应的品牌、系列、色号和id,代码如下:
import json
import getcolor
import numpy as np
import lipcolor
#filename = 'temp.txt'
##write the temp data to file##
def WtoFile(filename,RGB_temp):
num=len(RGB_temp)
with open(filename,'w') as f:
for i in range(num):
s = str(RGB_temp[i]).replace('[','').replace(']','')
f.write(s)
f.write("\n")
#operate the data #
##save the brand&series&color id&color name to sum_list##
##covert the color #D62352 to RGB_array##
##caculate the RGB difference to RGB_temp and write the value to file##
def data_operate():
with open('lipstick.json', 'r', encoding='utf-8') as f:
ret_dic = json.load(f)
#print(ret_dic['brands'])
#print(type(ret_dic)) #
#print(ret_dic['brands'][0]['name'])
b_num=len(ret_dic['brands'])
#print(b_num)#brands number
s_list=[]
#series brands#
for i in range(len(ret_dic['brands'])):
s_num=len(ret_dic['brands'][i]['series'])
s_list.append(s_num)
#print("{0} has {1} series".format((ret_dic['brands'][i]['name']),(s_list[i])))
#the lipstick color of every brands every series#
#the first loop calculate the total color numbers
sum=0
for b1 in range(b_num):
for s1 in range(s_list[b1]):
brand_name=ret_dic['brands'][b1]['name']
lip_name=ret_dic['brands'][b1]['series'][s1]['name']
color_num=len(ret_dic['brands'][b1]['series'][s1]['lipsticks'])
sum+=color_num#calculate the total color numbers
#the second loop save the message to a list#
sum_list=np.zeros((sum,4), dtype=(str,8))
value_array=np.zeros((sum,6), dtype=int)
i=0
for b2 in range(b_num):
for s2 in range(s_list[b2]):
brand_name=ret_dic['brands'][b2]['name']
#print(type(brand_name))
lip_name=ret_dic['brands'][b2]['series'][s2]['name']
color_num=len(ret_dic['brands'][b2]['series'][s2]['lipsticks'])
for c in range(color_num):
color_value=ret_dic['brands'][b2]['series'][s2]['lipsticks'][c]['color']
color_name=ret_dic['brands'][b2]['series'][s2]['lipsticks'][c]['name']
color_id=ret_dic['brands'][b2]['series'][s2]['lipsticks'][c]['id']
#print("{0} series {1} has {2} colors,color {3}:{4}".format(brand_name,lip_name,color_num,c+1,color_name))
sum_list[i][0]=brand_name
sum_list[i][1]=lip_name
sum_list[i][2]=color_id
sum_list[i][3]=color_name
#value_array[i]=value_array[i][1]
#convert "#D62352" to [13 6 2 3 5 2]#
for l in range(6):
temp=color_value[l+1]
if(temp>='A'and temp<='F'):
temp1=ord(temp)-ord('A')+10
else:
temp1=ord(temp)-ord('0')
value_array[i][l]=temp1
i+=1
#the third loop covert value_array to RGB_array#
RGB_array=np.zeros((sum,3), dtype=int)
for i in range(sum):
RGB_array[i][0]=value_array[i][0]*16+value_array[i][1]
RGB_array[i][1]=value_array[i][2]*16+value_array[i][3]
RGB_array[i][2]=value_array[i][4]*16+value_array[i][5]
#calculate the similar and save to RGB_temp
#RGB_temp=np.zeros((sum,1), dtype=int)
RGB_temp=np.zeros((sum,1), dtype=float)
for i in range(sum):
R=RGB_array[i][0]
G=RGB_array[i][1]
B=RGB_array[i][2]
RGB_temp[i]=abs(get[0]-R)+abs(get[1]*3/4-G)+abs(get[2]-B)
RGB_temp.tolist();#covert array to list
#print(RGB_temp)
filename="temp.txt"
WtoFile(filename,RGB_temp)
#sort the RGB_temp#
result=sorted(range(len(RGB_temp)), key=lambda k: RGB_temp[k])
#print(result)
#output the three max prob of the lipsticks#
print("The first three possible lipstick brand and color id&name are as follows:")
for i in range(3):
idex=result[i]
print(sum_list[idex])
print("The first three possible lipstick brand RGB value are as follows:")
for i in range(3):
idex=result[i]
R=RGB_array[idex][0]
G=RGB_array[idex][1]
B=RGB_array[idex][2]
tuple=(R,G,B)
print(tuple)
if __name__ == '__main__':
#image = getcolor.Image.open(inputpath)
#image = image.convert('RGB')
#get=getcolor.get_dominant_color(image)#tuple #get=(231, 213, 211)
list=[]
color_dir="output"
count=lipcolor.load_color(color_dir,list)
get=lipcolor.Mean_color(count,list)
print("the extracted RGB value of the color is {0}".format(get))
#operate the data#
data_operat 
提取到的番茄颜色:
'迪奥' '烈艳蓝金唇膏' '080' '微笑正红’的颜色:

'圣罗兰' '纯口红' '56' '橙红织锦'的颜色:

'纪梵希' '高定香榭天鹅绒唇' '325' '圣水红'的颜色:

文摘菌已经眼花缭乱,三个颜色……有区别吗?!以后不如准备统一叫它们,番茄色!

不过,这也正说明了,刚刚的提取&对比方法可行!
截取到的嘴唇区域如下:


圣罗兰官网#842C71口红

人脸识别和截取嘴唇区域的代码如下:
import numpy as np
import cv2
import dlib
from PIL import Image
def crop(source,pos):
x1=pos[2][0]
y1=pos[2][1]
x2=pos[1][0]
y2=pos[1][1]
d=abs(x2-x1)
region = source[(int)(y1-d*0.75):y2,x1:x2]
# save the image
cv2.imwrite("output/Mouth1.jpg", region)
x1=pos[1][0]
y1=pos[1][1]
x2=pos[0][0]
y2=pos[0][1]
d=abs(x1-x2)
region = source[y1-d:y2,x1:x2]
# save the image
cv2.imwrite("output/Mouth2.jpg", region)
def detect_mouth(img,pos):
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = cv2.equalizeHist(gray)
detector = dlib.get_frontal_face_detector()
#use the predictor
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
dets = detector(img, 1)
print("Number of faces detected: {}".format(len(dets)))
for a in dets:
cv2.rectangle(img,(a.left(),a.top()),(a.right(),a.bottom()),(255,0,0))
#point_list=[]#save the mouth point to point_list[]#
#Extract 68 feature points of the face and crop the lip image#
for index, face in enumerate(dets):
print('face {}; left {}; top {}; right {}; bottom {}'.format(index, face.left(), face.top(), face.right(), face.bottom()))
shape = predictor(gray, face)
for i, pt in enumerate(shape.parts()):
#print('Part {}: {}'.format(i, pt))
#print(i)
pt_pos = (pt.x, pt.y)
if i>=48 and i<=67:
cv2.circle(img, pt_pos, 2, (255, 0, 0), 1)
if i>=56 and i<=58:
#print(pt_pos)
pos[i-56][0]=pt.x
pos[i-56][1]=pt.y
#cv2.circle(img, pt_pos, 2, (255, 0, 0), 1)
return img
if __name__ == "__main__":
img = cv2.imread("test3.png")
#copy the input image for the later crop#
img_clone = np.copy(img)
cv2.imwrite("input/source.jpg",img_clone)
#save the lip position to pos array#
pos=np.zeros((3,2), dtype=int)
result=detect_mouth(img,pos)
cv2.imwrite("input/source2.jpg",result)
#crop the lip areas#
source = cv2.imread("input/source.jpg")
crop(source,pos)
# show the result
cv2.imshow('FaceDetect',result)
cv2.waitKey(0)
cv2.destroyAllWindow
误差分析

嘴唇区域截取不可避免会截取到皮肤中的一部分颜色,虽然算法已经将那种可能降到最低; 颜色提取上,虽然截取多个嘴唇图片求平均值,但是本身的提取算法还是和实际值稍有偏差; RGB颜色相似度比对的算法也不够精确; 最最重要的是,照片必须是原图,而且光线要自然,加了滤镜的图是怎么也不可能识别出来的。
文末福利:实时人像口红色号预测

#coding=utf8
import cv2
import time
print('Press Esc to exit')
imgWindow = cv2.namedWindow('FaceDetect', cv2.WINDOW_NORMAL)
import sys
import os
import dlib
import glob
import numpy
from skimage import io
def detect_face():
capInput = cv2.VideoCapture(0)
#nextCaptureTime = time.time()
faces = []
feas = []
if not capInput.isOpened(): print('Capture failed because of camera')
while 1:
ret, img = capInput.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
gray = cv2.equalizeHist(gray)
time=0
eTime = time.time() + 0.1
detector = dlib.get_frontal_face_detector()
predictor = dlib.shape_predictor('shape_predictor_68_face_landmarks.dat')
dets = detector(gray, 1)
print("Number of faces detected: {}".format(len(dets)))
for a in dets:
cv2.rectangle(img,(a.left(),a.top()),(a.right(),a.bottom()),(255,0,0))
for index, face in enumerate(dets):
print('face {}; left {}; top {}; right {}; bottom {}'.format(index, face.left(), face.top(), face.right(), face.bottom()))
shape = predictor(gray, face)
for i, pt in enumerate(shape.parts()):
#print('Part {}: {}'.format(i, pt))
pt_pos = (pt.x, pt.y)
cv2.circle(img, pt_pos, 2, (255, 0, 0), 1)
cv2.imshow('FaceDetect',img)
if cv2.waitKey(1) & 0xFF == 27: break
capInput.release()
cv2.destroyAllWindows()
if __name__ == "__main__":
detect_face()好啦,佳期如梦,双星良夜,在这个充满爱意的日子里,定位好女神常用的口红色号,和那个她来场华丽的邂逅吧!