0、项目介绍

今天要做的是单手识别数字0到5，通过在窗口展示，实时的展示相应的图片以及文字。

在网上找了很久的手势表示数字的图片，当然为了本项目的简洁，我只展示了0到5，感兴趣的可以自己添加后面的，原理很简单。

1、效果展示

成功的实现了单手识别数字0到5，实时展现也很不错。

2、项目搭建

在文件image_figures中，我将"完整图片.png"手动裁剪成0到5的图片，大小为220 $\times$ 300，当然你可以不用想我这样裁成统一大小，后面有解决的方法。

3、项目代码展示

HandTrackingModule.py

import cv2
import mediapipe as mp
import math
import timeclass handDetector:def __init__(self, mode=False, maxHands=2, detectionCon=0.5, minTrackCon=0.5):self.mode = modeself.maxHands = maxHandsself.detectionCon = detectionConself.minTrackCon = minTrackConself.mpHands = mp.solutions.handsself.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_utilsself.tipIds = [4, 8, 12, 16, 20]self.fingers = []self.lmList = []def findHands(self, img, draw=True):imgRGB = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)self.results = self.hands.process(imgRGB)# print(results.multi_hand_landmarks)if self.results.multi_hand_landmarks:for handLms in self.results.multi_hand_landmarks:if draw:self.mpDraw.draw_landmarks(img, handLms,self.mpHands.HAND_CONNECTIONS)return imgdef findPosition(self, img, handNo=0, draw=True):self.lmList=[]bbox = 0if self.results.multi_hand_landmarks:myHand = self.results.multi_hand_landmarks[handNo]xList = []yList = []for id, lm in enumerate(myHand.landmark):# print(id, lm)h, w, c = img.shapecx, cy = int(lm.x * w), int(lm.y * h)xList.append(cx)yList.append(cy)# print(id, cx, cy)self.lmList.append([id, cx, cy])if draw:cv2.circle(img, (cx, cy), 5, (255, 0, 255), cv2.FILLED)xmin, xmax = min(xList), max(xList)ymin, ymax = min(yList), max(yList)bbox = xmin, ymin, xmax, ymaxif draw:cv2.rectangle(img, (xmin - 20, ymin - 20), (xmax + 20, ymax + 20),(0, 255, 0), 2)return self.lmList, bboxdef fingersUp(self):fingers = []# Thumbif self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0] - 1][1]:fingers.append(1)else:fingers.append(0)# Fingersfor id in range(1, 5):if self.lmList[self.tipIds[id]][2] < self.lmList[self.tipIds[id] - 2][2]:fingers.append(1)else:fingers.append(0)# totalFingers = fingers.count(1)return fingersdef findDistance(self, p1, p2, img=None):x1, y1 = self.lmList[p1][1:]x2, y2 = self.lmList[p2][1:]cx, cy = (x1 + x2) // 2, (y1 + y2) // 2length = 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, imgelse:return length, infodef main():pTime = 0cTime = 0cap = cv2.VideoCapture(0)detector = handDetector()while True:success, img = cap.read()img = detector.findHands(img)lmList, bbox = detector.findPosition(img)if len(lmList) != 0:print(lmList[4])cTime = time.time()fps = 1 / (cTime - pTime)pTime = cTimecv2.putText(img, str(int(fps)), (10, 70), cv2.FONT_HERSHEY_PLAIN, 3,(255, 0, 255), 3)cv2.imshow("Image", img)k=cv2.waitKey(1)if k==27:breakif __name__ == "__main__":main()

Figures_counter.py

import os
import cv2
import mediapipe as mp
import time
import HandTrackingModule as htmclass fpsReader():def __init__(self):self.pTime = time.time()def FPS(self,img=None,pos=(20, 50), color=(255, 255, 0), scale=3, thickness=3):cTime = time.time()try:fps = 1 / (cTime - self.pTime)self.pTime = cTimeif img is None:return fpselse:cv2.putText(img, f'FPS: {int(fps)}', pos, cv2.FONT_HERSHEY_PLAIN,scale, color, thickness)return fps, imgexcept:return 0
fpsReader = fpsReader()
cap=cv2.VideoCapture(0)Wcam, Hcam = 980, 980
cap.set(3, Wcam)
cap.set(4, Hcam)
cap.set(10,150)img_path="image_figures"
mulu=os.listdir(img_path)
print(mulu)
Laylist=[]
for path in mulu:image=cv2.imread(f"{img_path}/{path}")Laylist.append(image)detector = htm.handDetector(detectionCon=0.75)while 1:_, img = cap.read()detector.findHands(img)lmList,_= detector.findPosition(img, draw=False)if len(lmList) != 0:fingerup=detector.fingersUp()print(fingerup)all_figures=fingerup.count(1)print(all_figures)h, w, _ = Laylist[all_figures].shapeimg[0:h, 0:w] = Laylist[all_figures]# img[0:300,0:220]=Laylist[0]cv2.rectangle(img,(0,350),(220,550),(0,255,0),cv2.FILLED)cv2.putText(img,str(all_figures),(45,510),cv2.FONT_HERSHEY_COMPLEX,6,(0,0,255),25)#################打印帧率#####################fps, img = fpsReader.FPS(img,pos=(880,50))cv2.imshow("image",img)k=cv2.waitKey(1)if k==27:break

这里的HandTrackingModule.py文件与上一节相同，不用更改什么。

由于我裁剪的时候是按照0-5的顺序命名，Laylist的索引刚好与其对应，所以不用在进行多的修改，而且这里的图片大小其实是可以根据其shape直接得到的，但当时我没有想到，所以就把所有的图片裁剪成统一大小了。

4、项目资源

GitHub:Opencv项目实战：20 单手识别数字0到5

5、项目总结

在这里，我提供一下识别更多数字的方法（0-10）。首先最简便的是双手识别，完全不用更改代码，把图片处理好就行了；其次，就是按照最上面的那张图片，参数figureup是一个长度为5的列表[0,0,0,0,0]，你可以参照着手势将其打印出来，然后将其用if条件判断。当然，在我们这边最常见的还是华北手势表示数字，大家按照自己的习惯来就行。