[cv001] python+opencv情緒識別

Let’s code to identify your emotions.
Coding識別你的喜怒哀樂畅哑。
                  ---《python情緒識別》.BY Andy

Emotions.png

一肴楷、原圖

二、情緒識別結(jié)果

三荠呐、代碼實現(xiàn)

'''
@filename:faceEmotions_image.py
'''
import dlib                     #人臉識別的庫dlib
import numpy as np              #數(shù)據(jù)處理的庫numpy
import cv2                      #圖像處理的庫OpenCv
from skimage import io          #>pip install scikit-image,scipy

class face_emotion():
    def __init__(self):
        # 使用特征提取器get_frontal_face_detector
        self.detector = dlib.get_frontal_face_detector()
        # dlib的68點模型赛蔫，使用作者訓練好的特征預測器
        self.predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
    def learning_face(self):
        # 眉毛直線擬合數(shù)據(jù)緩沖
        line_brow_x = []
        line_brow_y = []
        im_rd = cv2.imread("p4.jpg")
        img_gray = cv2.cvtColor(im_rd, cv2.COLOR_RGB2GRAY)
        faces = self.detector(img_gray, 0) # 檢測到的人臉數(shù)
        # 待會要顯示在屏幕上的字體
        font = cv2.FONT_HERSHEY_SIMPLEX
        if(len(faces)!=0):
            # 對每個人臉都標出68個特征點
            for k, d in enumerate(faces):
                cv2.rectangle(im_rd, (d.left(), d.top()),
                              (d.right(), d.bottom()), (0, 0, 255))
                cv2.rectangle(im_rd, (d.left()-10, d.top()-10),
                              (d.right()+10, d.bottom()+10), (0, 255, 0))
                # 用紅色矩形框出人臉
                cv2.rectangle(im_rd, (d.left(), d.top()), (d.right(), d.bottom()), (0, 0, 255))
                # 計算人臉熱別框邊長
                self.face_width = d.right() - d.left()
                # 使用預測器得到68點數(shù)據(jù)的坐標
                shape = self.predictor(im_rd, d)
                # 圓圈顯示每個特征點
                for i in range(68):
                    cv2.circle(im_rd, (shape.part(i).x, shape.part(i).y), 2, (0, 255, 0), -1, 8)
                    #cv2.putText(im_rd, str(i), (shape.part(i).x, shape.part(i).y),
                    #            cv2.FONT_HERSHEY_SIMPLEX, 0.3,(255, 255, 255))   
                # 分析任意n點的位置關系來作為表情識別的依據(jù)
                mouth_width = (shape.part(54).x - shape.part(48).x) / self.face_width  # 嘴巴咧開程度
                mouth_higth = (shape.part(66).y - shape.part(62).y) / self.face_width  # 嘴巴張開程度
                # print("嘴巴寬度與識別框?qū)挾戎龋?,mouth_width_arv)
                # print("嘴巴高度與識別框高度之比：",mouth_higth_arv)
                # 通過兩個眉毛上的10個特征點，分析挑眉程度和皺眉程度
                brow_sum = 0  # 高度之和
                frown_sum = 0  # 兩邊眉毛距離之和
                for j in range(17, 21):
                    brow_sum += (shape.part(j).y - d.top()) + (shape.part(j + 5).y - d.top())
                    frown_sum += shape.part(j + 5).x - shape.part(j).x
                    line_brow_x.append(shape.part(j).x)
                    line_brow_y.append(shape.part(j).y)
                # self.brow_k, self.brow_d = self.fit_slr(line_brow_x, line_brow_y)  # 計算眉毛的傾斜程度
                tempx = np.array(line_brow_x)
                tempy = np.array(line_brow_y)
                z1 = np.polyfit(tempx, tempy, 1)  # 擬合成一次直線
                self.brow_k = -round(z1[0], 3)  # 擬合出曲線的斜率和實際眉毛的傾斜方向是相反的
                brow_hight = (brow_sum / 10) / self.face_width  # 眉毛高度占比
                brow_width = (frown_sum / 5) / self.face_width  # 眉毛距離占比
                # print("眉毛高度與識別框高度之比：",round(brow_arv/self.face_width,3))
                # print("眉毛間距與識別框高度之比：",round(frown_arv/self.face_width,3))
                # 眼睛睜開程度
                eye_sum = (shape.part(41).y - shape.part(37).y + shape.part(40).y - shape.part(38).y +
                           shape.part(47).y - shape.part(43).y + shape.part(46).y - shape.part(44).y)

                eye_hight = (eye_sum / 4) / self.face_width
                # print("眼睛睜開距離與識別框高度之比：",round(eye_open/self.face_width,3))
                # 分情況討論
                # 張嘴泥张，可能是開心或者驚訝
                if round(mouth_higth >= 0.03):
                    if eye_hight >= 0.056:
                        print(f'amazing-->[mouth_higth:{mouth_higth},eye_hight:{eye_hight},self.brow_k:{self.brow_k}]')
                        cv2.putText(im_rd, "amazing", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                    (0, 0, 255), 2, 4)
                    else:
                        print(f'happy-->[mouth_higth:{mouth_higth},eye_hight:{eye_hight},self.brow_k:{self.brow_k}]')
                        cv2.putText(im_rd, "happy", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                                (0, 0, 255), 2, 4)
                # 沒有張嘴呵恢，可能是正常和生氣
                else:
                    if self.brow_k <= -0.2:# modify 0.3 as 0.2 by Andy
                        print(f'angry-->[mouth_higth:{mouth_higth},eye_hight:{eye_hight},self.brow_k:{self.brow_k}]')
                        cv2.putText(im_rd, "angry", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,(0, 0, 255), 2, 4)
                    else:
                        print(f'nature-->[mouth_higth:{mouth_higth},eye_hight:{eye_hight},self.brow_k:{self.brow_k}]')
                        cv2.putText(im_rd, "nature", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                    (0, 0, 255), 2, 4)
            # 標出人臉數(shù)
            cv2.putText(im_rd, "Faces: "+str(len(faces)), (20,50), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
        else:
            # 沒有檢測到人臉
            cv2.putText(im_rd, "No Face", (20, 50), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
        # 窗口顯示
        cv2.imshow("camera", im_rd)
        cv2.imwrite("Andy0"+".jpg", im_rd)
if __name__ == "__main__":
    my_face = face_emotion()
    my_face.learning_face()

#coding: utf-8
'''
@filename:faceEmotions_video.py
'''
import dlib                     #人臉識別的庫dlib
import numpy as np              #數(shù)據(jù)處理的庫numpy
import cv2                      #圖像處理的庫OpenCv
from skimage import io          #>pip install scikit-image,scipy

class face_emotion():
    def __init__(self):
        # 使用特征提取器get_frontal_face_detector
        self.detector = dlib.get_frontal_face_detector()
        # dlib的68點模型，使用作者訓練好的特征預測器
        self.predictor = dlib.shape_predictor("shape_predictor_68_face_landmarks.dat")
        #建cv2攝像頭對象圾结，這里使用電腦自帶攝像頭瑰剃，如果接了外部攝像頭，則自動切換到外部攝像頭
        self.cap = cv2.VideoCapture(0)
        # 設置視頻參數(shù)筝野，propId設置的視頻參數(shù)晌姚，value設置的參數(shù)值
        self.cap.set(3, 480)
        # 截圖screenshoot的計數(shù)器
        self.cnt = 0

    def learning_face(self):

        # 眉毛直線擬合數(shù)據(jù)緩沖
        line_brow_x = []
        line_brow_y = []

        # cap.isOpened（） 返回true/false 檢查初始化是否成功
        while(self.cap.isOpened()):

            # cap.read()
            # 返回兩個值：
            #    一個布爾值true/false，用來判斷讀取視頻是否成功/是否到視頻末尾
            #    圖像對象歇竟，圖像的三維矩陣
            flag, im_rd = self.cap.read()

            # 每幀數(shù)據(jù)延時1ms挥唠，延時為0讀取的是靜態(tài)幀
            k = cv2.waitKey(1)

            # 取灰度
            img_gray = cv2.cvtColor(im_rd, cv2.COLOR_RGB2GRAY)

            # 使用人臉檢測器檢測每一幀圖像中的人臉。并返回人臉數(shù)rects
            faces = self.detector(img_gray, 0)

            # 待會要顯示在屏幕上的字體
            font = cv2.FONT_HERSHEY_SIMPLEX

            # 如果檢測到人臉
            if(len(faces)!=0):

                # 對每個人臉都標出68個特征點
                for i in range(len(faces)):
                    # enumerate方法同時返回數(shù)據(jù)對象的索引和數(shù)據(jù)焕议，k為索引宝磨，d為faces中的對象
                    for k, d in enumerate(faces):
                        # 用紅色矩形框出人臉
                        cv2.rectangle(im_rd, (d.left(), d.top()), (d.right(), d.bottom()), (0, 0, 255))
                        # 計算人臉熱別框邊長
                        self.face_width = d.right() - d.left()

                        # 使用預測器得到68點數(shù)據(jù)的坐標
                        shape = self.predictor(im_rd, d)
                        # 圓圈顯示每個特征點
                        for i in range(68):
                            cv2.circle(im_rd, (shape.part(i).x, shape.part(i).y), 2, (0, 255, 0), -1, 8)
                            cv2.putText(im_rd, str(i), (shape.part(i).x, shape.part(i).y), cv2.FONT_HERSHEY_SIMPLEX, 0.3,
                                        (255, 255, 255))

                        # 分析任意n點的位置關系來作為表情識別的依據(jù)
                        mouth_width = (shape.part(54).x - shape.part(48).x) / self.face_width  # 嘴巴咧開程度
                        mouth_higth = (shape.part(66).y - shape.part(62).y) / self.face_width  # 嘴巴張開程度
                        # print("嘴巴寬度與識別框?qū)挾戎龋?,mouth_width_arv)
                        # print("嘴巴高度與識別框高度之比：",mouth_higth_arv)

                        # 通過兩個眉毛上的10個特征點，分析挑眉程度和皺眉程度
                        brow_sum = 0  # 高度之和
                        frown_sum = 0  # 兩邊眉毛距離之和
                        for j in range(17, 21):
                            brow_sum += (shape.part(j).y - d.top()) + (shape.part(j + 5).y - d.top())
                            frown_sum += shape.part(j + 5).x - shape.part(j).x
                            line_brow_x.append(shape.part(j).x)
                            line_brow_y.append(shape.part(j).y)
                        print("self:"+str(self))
                        # self.brow_k, self.brow_d = self.fit_slr(line_brow_x, line_brow_y)  # 計算眉毛的傾斜程度
                        tempx = np.array(line_brow_x)
                        tempy = np.array(line_brow_y)
                        z1 = np.polyfit(tempx, tempy, 1)  # 擬合成一次直線
                        self.brow_k = -round(z1[0], 3)  # 擬合出曲線的斜率和實際眉毛的傾斜方向是相反的

                        brow_hight = (brow_sum / 10) / self.face_width  # 眉毛高度占比
                        brow_width = (frown_sum / 5) / self.face_width  # 眉毛距離占比
                        # print("眉毛高度與識別框高度之比：",round(brow_arv/self.face_width,3))
                        # print("眉毛間距與識別框高度之比：",round(frown_arv/self.face_width,3))

                        # 眼睛睜開程度
                        eye_sum = (shape.part(41).y - shape.part(37).y + shape.part(40).y - shape.part(38).y +
                                   shape.part(47).y - shape.part(43).y + shape.part(46).y - shape.part(44).y)
                        eye_hight = (eye_sum / 4) / self.face_width
                        # print("眼睛睜開距離與識別框高度之比：",round(eye_open/self.face_width,3))

                        # 分情況討論
                        # 張嘴盅安，可能是開心或者驚訝
                        if round(mouth_higth >= 0.03):
                            if eye_hight >= 0.056:
                                cv2.putText(im_rd, "amazing", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                            (0, 0, 255), 2, 4)
                            else:
                                cv2.putText(im_rd, "happy", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                            (0, 0, 255), 2, 4)

                        # 沒有張嘴唤锉，可能是正常和生氣
                        else:
                            if self.brow_k <= -0.3:
                                cv2.putText(im_rd, "angry", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                            (0, 0, 255), 2, 4)
                            else:
                                cv2.putText(im_rd, "nature", (d.left(), d.bottom() + 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8,
                                            (0, 0, 255), 2, 4)

                # 標出人臉數(shù)
                cv2.putText(im_rd, "Faces: "+str(len(faces)), (20,50), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
            else:
                # 沒有檢測到人臉
                cv2.putText(im_rd, "No Face", (20, 50), font, 1, (0, 0, 255), 1, cv2.LINE_AA)
            # 添加說明
            im_rd = cv2.putText(im_rd, "S: screenshot", (20, 400), font, 0.8, (0, 0, 255), 1, cv2.LINE_AA)
            im_rd = cv2.putText(im_rd, "Q: quit", (20, 450), font, 0.8, (0, 0, 255), 1, cv2.LINE_AA)
            # 按下s鍵截圖保存
            if (k == ord('s')):
                self.cnt+=1
                cv2.imwrite("screenshoot"+str(self.cnt)+".jpg", im_rd)
            # 按下q鍵退出
            if(k == ord('q')):
                break
            # 窗口顯示
            cv2.imshow("camera", im_rd)
        # 釋放攝像頭
        self.cap.release()
        # 刪除建立的窗口
        cv2.destroyAllWindows()

if __name__ == "__main__":
    my_face = face_emotion()
    my_face.learning_face()

四、閑聊

??[1].代碼截止2019-04-21調(diào)試無誤别瞭。
??[2].需要全部代碼及相關文件窿祥，留言郵箱。

[cv001] python+opencv情緒識別

一肴楷、原圖

二、情緒識別結(jié)果

三荠呐、代碼實現(xiàn)

四、閑聊

??讓知識或技術實現(xiàn)其最大的價值蝙寨，歡迎收藏自用晒衩、轉(zhuǎn)載分享，轉(zhuǎn)載請注明原文出處墙歪，謝謝听系！