Opencv项目实战：15 手势缩放图片

 0、项目介绍

        本篇将会以HandTrackingModule为模块，这里的模块与之前的有所不同，请按照本篇为准，前面的HandTrackingModule不足以完成本项目，本篇将会通过手势对本人的博客海报进行缩放，具体效果可以看下面的效果展示。

1、项目展示

2、项目搭建

首先在一个文件夹下建立HandTrackingModule.py文件以及gesture_zoom.py，以及一张图片，你可以按照你的喜好选择，建议尺寸不要过大。

在这里用到了食指的索引8，可以完成左右手食指的手势进行缩放。

3、项目的代码与讲解

HandTrackingModule.py：

import cv2
import mediapipe as mp
import math


class handDetector:

    def __init__(self, mode=False, maxHands=2, detectionCon=0.5, minTrackCon=0.5):
        self.mode = mode
        self.maxHands = maxHands
        self.detectionCon = detectionCon
        self.minTrackCon = minTrackCon

        self.mpHands = mp.solutions.hands
        self.hands = self.mpHands.Hands(static_image_mode=self.mode, max_num_hands=self.maxHands,
                                        min_detection_confidence=self.detectionCon,
                                        min_tracking_confidence=self.minTrackCon)
        self.mpDraw = mp.solutions.drawing_utils
        self.tipIds = [4, 8, 12, 16, 20]
        self.fingers = []
        self.lmList = []

    def findHands(self, img, draw=True, flipType=True):
        imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        self.results = self.hands.process(imgRGB)
        allHands = []
        h, w, c = img.shape
        if self.results.multi_hand_landmarks:
            for handType, handLms in zip(self.results.multi_handedness, self.results.multi_hand_landmarks):
                myHand = {}
                ## lmList
                mylmList = []
                xList = []
                yList = []
                for id, lm in enumerate(handLms.landmark):
                    px, py, pz = int(lm.x * w), int(lm.y * h), int(lm.z * w)
                    mylmList.append([px, py])
                    xList.append(px)
                    yList.append(py)

                ## bbox
                xmin, xmax = min(xList), max(xList)
                ymin, ymax = min(yList), max(yList)
                boxW, boxH = xmax - xmin, ymax - ymin
                bbox = xmin, ymin, boxW, boxH
                cx, cy = bbox[0] + (bbox[2] // 2), \
                         bbox[1] + (bbox[3] // 2)

                myHand["lmList"] = mylmList
                myHand["bbox"] = bbox
                myHand["center"] = (cx, cy)

                if flipType:
                    if handType.classification[0].label == "Right":
                        myHand["type"] = "Left"
                    else:
                        myHand["type"] = "Right"
                else:
                    myHand["type"] = handType.classification[0].label
                allHands.append(myHand)

                ## draw
                if draw:
                    self.mpDraw.draw_landmarks(img, handLms,
                                               self.mpHands.HAND_CONNECTIONS)
                    cv2.rectangle(img, (bbox[0] - 20, bbox[1] - 20),
                                  (bbox[0] + bbox[2] + 20, bbox[1] + bbox[3] + 20),
                                  (255, 0, 255), 2)
                    cv2.putText(img, myHand["type"], (bbox[0] - 30, bbox[1] - 30), cv2.FONT_HERSHEY_PLAIN,
                                2, (255, 0, 255), 2)
        if draw:
            return allHands, img
        else:
            return allHands

    def fingersUp(self, myHand):
        myHandType = myHand["type"]
        myLmList = myHand["lmList"]
        if self.results.multi_hand_landmarks:
            fingers = []
            # Thumb
            if myHandType == "Right":
                if myLmList[self.tipIds[0]][0] > myLmList[self.tipIds[0] - 1][0]:
                    fingers.append(1)
                else:
                    fingers.append(0)
            else:
                if myLmList[self.tipIds[0]][0] < myLmList[self.tipIds[0] - 1][0]:
                    fingers.append(1)
                else:
                    fingers.append(0)

            # 4 Fingers
            for id in range(1, 5):
                if myLmList[self.tipIds[id]][1] < myLmList[self.tipIds[id] - 2][1]:
                    fingers.append(1)
                else:
                    fingers.append(0)
        return fingers

    def findDistance(self, p1, p2, img=None):
        x1, y1 = p1
        x2, y2 = p2
        cx, cy = (x1 + x2) // 2, (y1 + y2) // 2
        length = math.hypot(x2 - x1, y2 - y1)
        info = (x1, y1, x2, y2, cx, cy)
        if img is not None:
            cv2.circle(img, (x1, y1), 15, (255, 0, 255), cv2.FILLED)
            cv2.circle(img, (x2, y2), 15, (255, 0, 255), cv2.FILLED)
            cv2.line(img, (x1, y1), (x2, y2), (255, 0, 255), 3)
            cv2.circle(img, (cx, cy), 15, (255, 0, 255), cv2.FILLED)
            return length, info, img
        else:
            return length, info


def main():
    cap = cv2.VideoCapture(0)
    detector = handDetector(detectionCon=0.8, maxHands=2)
    while True:
        # Get image frame
        success, img = cap.read()
        # Find the hand and its landmarks
        hands, img = detector.findHands(img)  # with draw
        # hands = detector.findHands(img, draw=False)  # without draw

        if hands:
            # Hand 1
            hand1 = hands[0]
            lmList1 = hand1["lmList"]  # List of 21 Landmark points
            bbox1 = hand1["bbox"]  # Bounding box info x,y,w,h
            centerPoint1 = hand1['center']  # center of the hand cx,cy
            handType1 = hand1["type"]  # Handtype Left or Right

            fingers1 = detector.fingersUp(hand1)

            if len(hands) == 2:
                # Hand 2
                hand2 = hands[1]
                lmList2 = hand2["lmList"]  # List of 21 Landmark points
                bbox2 = hand2["bbox"]  # Bounding box info x,y,w,h
                centerPoint2 = hand2['center']  # center of the hand cx,cy
                handType2 = hand2["type"]  # Hand Type "Left" or "Right"

                fingers2 = detector.fingersUp(hand2)

                # Find Distance between two Landmarks. Could be same hand or different hands
                length, info, img = detector.findDistance(lmList1[8][0:2], lmList2[8][0:2], img)  # with draw
                # length, info = detector.findDistance(lmList1[8], lmList2[8])  # with draw
        # Display
        cv2.imshow("Image", img)
        cv2.waitKey(1)


if __name__ == "__main__":
    main()

gesture_zoom.py 

import cv2
import mediapipe as mp
import time
import HandTrackingModule as htm

startDist = None
scale = 0
cx, cy = 500,200
wCam, hCam = 1280,720
pTime = 0

cap = cv2.VideoCapture(0)
cap.set(3, wCam)
cap.set(4, hCam)
cap.set(10,150)

detector = htm.handDetector(detectionCon=0.75)

while 1:
    success, img = cap.read()
    handsimformation,img=detector.findHands(img)

    img1 = cv2.imread("1.png")
    # img[0:360, 0:260] = img1
    if len(handsimformation)==2:

        # print(detector.fingersUp(handsimformation[0]),detector.fingersUp(handsimformation[1]))
        #detector.fingersUp(handimformation[0]右手
        if detector.fingersUp(handsimformation[0]) == [1, 1, 1, 0, 0] and \
                detector.fingersUp(handsimformation[1]) == [1, 1, 1 ,0, 0]:
            lmList1 = handsimformation[0]['lmList']
            lmList2 = handsimformation[1]['lmList']
            if startDist is None:
                #lmList1[8],lmList2[8]右、左手指尖

                # length,info,img=detector.findDistance(lmList1[8],lmList2[8], img)
                length, info, img = detector.findDistance(handsimformation[0]["center"], handsimformation[1]["center"], img)
                startDist=length
            length, info, img = detector.findDistance(handsimformation[0]["center"], handsimformation[1]["center"], img)
            # length, info, img = detector.findDistance(lmList1[8], lmList2[8], img)
            scale=int((length-startDist)//2)
            cx, cy=info[4:]
            print(scale)
    else:
        startDist=None
    try:
        h1, w1, _ = img1.shape
        newH, newW = ((h1 + scale) // 2) * 2, ((w1 + scale) // 2) * 2
        img1 = cv2.resize(img1, (newW, newH))

        img[cy-newH//2:cy+ newH//2, cx-newW//2:cx+newW//2] = img1
    except:
        pass
    #################打印帧率#####################
    cTime = time.time()
    fps = 1 / (cTime - pTime)
    pTime = cTime
    cv2.putText(img, f'FPS: {int(fps)}', (40, 50), cv2.FONT_HERSHEY_COMPLEX,
                1, (100, 0, 255), 3)

    cv2.imshow("image",img)
    k=cv2.waitKey(1)
    if k==27:
        break

前面的类模块，我不做过多的讲解，它的新添加功能，我会在讲解主文件的时候提到。

• 首先，导入我们需要的模块，第一步先编写打开摄像头的代码，确保摄像头的正常，并调节好窗口的设置——长、宽、亮度，并且用htm(HandTrackingModule的缩写，后面都是此意)handDetector调整置信度，让我们检测到手更准确。
• 其次，用findHands的得到手的landmark，我所设定的手势是左右手的大拇指、食指、中指高于其他四指，也就是这六根手指竖起，我们按照[1, 1, 1, 0, 0]，[1, 1, 1, 0, 0]来设定，如果你不能确定，请解除这里的代码;

#print(detector.fingersUp(handsimformation[0]),detector.fingersUp(handsimformation[1]))

• 然后，在这里有两个handsimformation[0]['lmList']，handsimformation[0]["center"]，分别代表我要取食指，和手掌中心点，那么展示的时候是用的中心点，可以按照个人的喜好去选择手掌的索引，startDist=None表示为没有检测到的手时的起始长度，而经过每次迭代后，获得的距离length-起始长度，如果我增大手的距离，我就能得到一个较大的scale，由于打印的scale太大，我不希望它变化太快，所以做了二分后取整，如果得到的是一个负值，那么就缩小图片，那么我们没有检测到手时，就要令startDist=None。
• 之后来看，info = (x1, y1, x2, y2, cx, cy)，根据索引得到中心值，然后，我们来获取现在海报的大小，然后加上我们scale，实现动态的缩放，但在这里要注意，这里进行了整出2，在乘以2的操作，如果是参数是偶数，我们无需理会，但如果遇到了奇数就会出现少一个像素点的问题，比如，值为9，整除2后得到的为4，4+4=8<9，所以为了确保正确，加了这一步。加入try...except语句是因为图像超出窗口时发出会发出警告，起到超出时此代码将不起作用，回到窗口时，可以继续操作。
• 最后，打印出我们的帧率

4、项目资源

GitHub:https://github.com/Auorui/Opencv-project-training/tree/main/Opencv%20project%20training/15%20Gesture%20Zoom%20Picture

5、项目总结

本次项目完成了手势图片的虚拟缩放，如果你喜欢的话可以关注点赞加收藏。如果你们对于其他项目感兴趣，可以进入GitHub中，点击收藏。

 感谢大家的关注，如果你对于本项目较为喜欢，那么我会在评论中看到你哦。