您好,登錄后才能下訂單哦!
這篇文章主要為大家展示了“Python如何實(shí)現(xiàn)對照片中的人臉進(jìn)行顏值預(yù)測”,內(nèi)容簡而易懂,條理清晰,希望能夠幫助大家解決疑惑,下面讓小編帶領(lǐng)大家一起研究并學(xué)習(xí)一下“Python如何實(shí)現(xiàn)對照片中的人臉進(jìn)行顏值預(yù)測”這篇文章吧。
**Python版本:**3.5.4(64bit)
opencv_python模塊
sklearn模塊
numpy模塊
dlib模塊
一些Python自帶的模塊。
(1)安裝相應(yīng)版本的Python并添加到環(huán)境變量中;
(2)pip安裝相關(guān)模塊中提到的模塊。
例如:
若pip安裝報(bào)錯(cuò),請自行到:
http://www.lfd.uci.edu/~gohlke/pythonlibs/
下載pip安裝報(bào)錯(cuò)模塊的whl文件,并使用:
pip install whl文件路徑+whl文件名安裝。
例如:
(已在相關(guān)文件中提供了編譯好的用于dlib庫安裝的whl文件——>因?yàn)檫@個(gè)庫最不好裝)
參考文獻(xiàn)鏈接
【1】xxxPh.D.的博客
http://www.learnopencv.com/computer-vision-for-predicting-facial-attractiveness/
【2】華南理工大學(xué)某實(shí)驗(yàn)室
http://www.hcii-lab.net/data/SCUT-FBP/EN/introduce.html
(1)模型訓(xùn)練
用了PCA算法對特征進(jìn)行了壓縮降維;
然后用隨機(jī)森林訓(xùn)練模型。
數(shù)據(jù)源于網(wǎng)絡(luò),據(jù)說數(shù)據(jù)“發(fā)源地”就是華南理工大學(xué)某實(shí)驗(yàn)室,因此我在參考文獻(xiàn)上才加上了這個(gè)實(shí)驗(yàn)室的鏈接。
(2)提取人臉關(guān)鍵點(diǎn)
主要使用了dlib庫。
使用官方提供的模型構(gòu)建特征提取器。
(3)特征生成
完全參考了xxxPh.D.的博客。
(4)顏值預(yù)測
利用之前的數(shù)據(jù)和模型進(jìn)行顏值預(yù)測。
使用方式
有特殊疾病者請慎重嘗試預(yù)測自己的顏值,本人不對顏值預(yù)測的結(jié)果和帶來的所有負(fù)面影響負(fù)責(zé)?。?!
言歸正傳。
環(huán)境搭建完成后,解壓相關(guān)文件中的Face_Value.rar文件,cmd窗口切換到解壓后的*.py文件所在目錄。
例如:
打開test_img文件夾,將需要預(yù)測顏值的照片放入并重命名為test.jpg。
例如:
若嫌麻煩或者有其他需求,請自行修改:
getLandmarks.py文件中第13行。
最后依次運(yùn)行:
train_model.py(想直接用我模型的請忽略此步)
# 模型訓(xùn)練腳本 import numpy as np from sklearn import decomposition from sklearn.ensemble import RandomForestRegressor from sklearn.externals import joblib # 特征和對應(yīng)的分?jǐn)?shù)路徑 features_path = './data/features_ALL.txt' ratings_path = './data/ratings.txt' # 載入數(shù)據(jù) # 共500組數(shù)據(jù) # 其中前480組數(shù)據(jù)作為訓(xùn)練集,后20組數(shù)據(jù)作為測試集 features = np.loadtxt(features_path, delimiter=',') features_train = features[0: -20] features_test = features[-20: ] ratings = np.loadtxt(ratings_path, delimiter=',') ratings_train = ratings[0: -20] ratings_test = ratings[-20: ] # 訓(xùn)練模型 # 這里用PCA算法對特征進(jìn)行了壓縮和降維。 # 降維之后特征變成了20維,也就是說特征一共有500行,每行是一個(gè)人的特征向量,每個(gè)特征向量有20個(gè)元素。 # 用隨機(jī)森林訓(xùn)練模型 pca = decomposition.PCA(n_components=20) pca.fit(features_train) features_train = pca.transform(features_train) features_test = pca.transform(features_test) regr = RandomForestRegressor(n_estimators=50, max_depth=None, min_samples_split=10, random_state=0) regr = regr.fit(features_train, ratings_train) joblib.dump(regr, './model/face_rating.pkl', compress=1) # 訓(xùn)練完之后提示訓(xùn)練結(jié)束 print('Generate Model Successfully!')
getLandmarks.py
# 人臉關(guān)鍵點(diǎn)提取腳本 import cv2 import dlib import numpy # 模型路徑 PREDICTOR_PATH = './model/shape_predictor_68_face_landmarks.dat' # 使用dlib自帶的frontal_face_detector作為人臉提取器 detector = dlib.get_frontal_face_detector() # 使用官方提供的模型構(gòu)建特征提取器 predictor = dlib.shape_predictor(PREDICTOR_PATH) face_img = cv2.imread("test_img/test.jpg") # 使用detector進(jìn)行人臉檢測,rects為返回的結(jié)果 rects = detector(face_img, 1) # 如果檢測到人臉 if len(rects) >= 1: print("{} faces detected".format(len(rects))) else: print('No faces detected') exit() with open('./results/landmarks.txt', 'w') as f: f.truncate() for faces in range(len(rects)): # 使用predictor進(jìn)行人臉關(guān)鍵點(diǎn)識別 landmarks = numpy.matrix([[p.x, p.y] for p in predictor(face_img, rects[faces]).parts()]) face_img = face_img.copy() # 使用enumerate函數(shù)遍歷序列中的元素以及它們的下標(biāo) for idx, point in enumerate(landmarks): pos = (point[0, 0], point[0, 1]) f.write(str(point[0, 0])) f.write(',') f.write(str(point[0, 1])) f.write(',') f.write('\n') f.close() # 成功后提示 print('Get landmarks successfully')
getFeatures.py
# 特征生成腳本 # 具體原理請參見參考論文 import math import numpy import itertools def facialRatio(points): x1 = points[0] y1 = points[1] x2 = points[2] y2 = points[3] x3 = points[4] y3 = points[5] x4 = points[6] y4 = points[7] dist1 = math.sqrt((x1-x2)**2 + (y1-y2)**2) dist2 = math.sqrt((x3-x4)**2 + (y3-y4)**2) ratio = dist1/dist2 return ratio def generateFeatures(pointIndices1, pointIndices2, pointIndices3, pointIndices4, allLandmarkCoordinates): size = allLandmarkCoordinates.shape if len(size) > 1: allFeatures = numpy.zeros((size[0], len(pointIndices1))) for x in range(0, size[0]): landmarkCoordinates = allLandmarkCoordinates[x, :] ratios = [] for i in range(0, len(pointIndices1)): x1 = landmarkCoordinates[2*(pointIndices1[i]-1)] y1 = landmarkCoordinates[2*pointIndices1[i] - 1] x2 = landmarkCoordinates[2*(pointIndices2[i]-1)] y2 = landmarkCoordinates[2*pointIndices2[i] - 1] x3 = landmarkCoordinates[2*(pointIndices3[i]-1)] y3 = landmarkCoordinates[2*pointIndices3[i] - 1] x4 = landmarkCoordinates[2*(pointIndices4[i]-1)] y4 = landmarkCoordinates[2*pointIndices4[i] - 1] points = [x1, y1, x2, y2, x3, y3, x4, y4] ratios.append(facialRatio(points)) allFeatures[x, :] = numpy.asarray(ratios) else: allFeatures = numpy.zeros((1, len(pointIndices1))) landmarkCoordinates = allLandmarkCoordinates ratios = [] for i in range(0, len(pointIndices1)): x1 = landmarkCoordinates[2*(pointIndices1[i]-1)] y1 = landmarkCoordinates[2*pointIndices1[i] - 1] x2 = landmarkCoordinates[2*(pointIndices2[i]-1)] y2 = landmarkCoordinates[2*pointIndices2[i] - 1] x3 = landmarkCoordinates[2*(pointIndices3[i]-1)] y3 = landmarkCoordinates[2*pointIndices3[i] - 1] x4 = landmarkCoordinates[2*(pointIndices4[i]-1)] y4 = landmarkCoordinates[2*pointIndices4[i] - 1] points = [x1, y1, x2, y2, x3, y3, x4, y4] ratios.append(facialRatio(points)) allFeatures[0, :] = numpy.asarray(ratios) return allFeatures def generateAllFeatures(allLandmarkCoordinates): a = [18, 22, 23, 27, 37, 40, 43, 46, 28, 32, 34, 36, 5, 9, 13, 49, 55, 52, 58] combinations = itertools.combinations(a, 4) i = 0 pointIndices1 = [] pointIndices2 = [] pointIndices3 = [] pointIndices4 = [] for combination in combinations: pointIndices1.append(combination[0]) pointIndices2.append(combination[1]) pointIndices3.append(combination[2]) pointIndices4.append(combination[3]) i = i+1 pointIndices1.append(combination[0]) pointIndices2.append(combination[2]) pointIndices3.append(combination[1]) pointIndices4.append(combination[3]) i = i+1 pointIndices1.append(combination[0]) pointIndices2.append(combination[3]) pointIndices3.append(combination[1]) pointIndices4.append(combination[2]) i = i+1 return generateFeatures(pointIndices1, pointIndices2, pointIndices3, pointIndices4, allLandmarkCoordinates) landmarks = numpy.loadtxt("./results/landmarks.txt", delimiter=',', usecols=range(136)) featuresALL = generateAllFeatures(landmarks) numpy.savetxt("./results/my_features.txt", featuresALL, delimiter=',', fmt = '%.04f') print("Generate Feature Successfully!")
Predict.py
# 顏值預(yù)測腳本 from sklearn.externals import joblib import numpy as np from sklearn import decomposition pre_model = joblib.load('./model/face_rating.pkl') features = np.loadtxt('./data/features_ALL.txt', delimiter=',') my_features = np.loadtxt('./results/my_features.txt', delimiter=',') pca = decomposition.PCA(n_components=20) pca.fit(features) predictions = [] if len(my_features.shape) > 1: for i in range(len(my_features)): feature = my_features[i, :] feature_transfer = pca.transform(feature.reshape(1, -1)) predictions.append(pre_model.predict(feature_transfer)) print('照片中的人顏值得分依次為(滿分為5分):') k = 1 for pre in predictions: print('第%d個(gè)人:' % k, end='') print(str(pre)+'分') k += 1 else: feature = my_features feature_transfer = pca.transform(feature.reshape(1, -1)) predictions.append(pre_model.predict(feature_transfer)) print('照片中的人顏值得分為(滿分為5分):') k = 1 for pre in predictions: print(str(pre)+'分') k += 1
以上是“Python如何實(shí)現(xiàn)對照片中的人臉進(jìn)行顏值預(yù)測”這篇文章的所有內(nèi)容,感謝各位的閱讀!相信大家都有了一定的了解,希望分享的內(nèi)容對大家有所幫助,如果還想學(xué)習(xí)更多知識,歡迎關(guān)注億速云行業(yè)資訊頻道!
免責(zé)聲明:本站發(fā)布的內(nèi)容(圖片、視頻和文字)以原創(chuàng)、轉(zhuǎn)載和分享為主,文章觀點(diǎn)不代表本網(wǎng)站立場,如果涉及侵權(quán)請聯(lián)系站長郵箱:is@yisu.com進(jìn)行舉報(bào),并提供相關(guān)證據(jù),一經(jīng)查實(shí),將立刻刪除涉嫌侵權(quán)內(nèi)容。