目录
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220300,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 time
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):
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 img
def findPosition(self, img, handNo=0, draw=True):
self.lmList=[]
bbox = 0
if 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.shape
cx, 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, ymax
if draw:
cv2.rectangle(img, (xmin - 20, ymin - 20), (xmax + 20, ymax + 20),
(0, 255, 0), 2)
return self.lmList, bbox
def fingersUp(self):
fingers = []
# Thumb
if self.lmList[self.tipIds[0]][1] > self.lmList[self.tipIds[0] - 1][1]:
fingers.append(1)
else:
fingers.append(0)
# Fingers
for 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 fingers
def 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) // 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():
pTime = 0
cTime = 0
cap = 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 = cTime
cv2.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:
break
if __name__ == "__main__":
main()
Figures_counter.py
import os
import cv2
import mediapipe as mp
import time
import HandTrackingModule as htm
class 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 = cTime
if img is None:
return fps
else:
cv2.putText(img, f'FPS: {int(fps)}', pos, cv2.FONT_HERSHEY_PLAIN,
scale, color, thickness)
return fps, img
except:
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].shape
img[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。