利用OpenCV+Tensorflow实现的手势识别

pip install -r environment.txt -i https://pypi.tuna.tsinghua.edu.cn/simple

import cv2
from cvzone.HandTrackingModule import HandDetector
from cvzone.ClassificationModule import Classifier
from PIL import Image, ImageDraw, ImageFont
import numpy as np
import math
import time
# import speech
 
cap = cv2.VideoCapture(0)
cap.set(3, 1280)
cap.set(4, 720)
 
detector = HandDetector(maxHands=1)
classifile = Classifier("./model/keras_model.h5", "./model/labels.txt")
 
offset = 20
imgSize = 300
counter = 0
labels = ['666', '鄙视', 'Good', '比心', '击掌', '握拳']
 
# folder = r"F:\opencv_game\HandSignDetection\Data\Love"
 
while True:
    success, img = cap.read()
    img = cv2.flip(img, 1)
    imgOutput = img.copy()
    hands, img = detector.findHands(img)
    if hands:
        hand = hands[0]
        x, y, w, h = hand['bbox']
        imgWhite = np.ones((imgSize, imgSize, 3), np.uint8)*255
        imgCrop = img[y - offset:y + h + offset, x - offset:x + w + offset]
 
        imgCropShape = imgCrop.shape
 
        aspectRatio = h/w
 
        if aspectRatio > 1:
            k = imgSize/h
            wCal = math.ceil(k*w)
            imgResize = cv2.resize(imgCrop, (wCal, imgSize))
            imgResizeShape = imgResize.shape
            wGap = math.ceil((imgSize - wCal)/2)
            imgWhite[:, wGap:wCal+wGap] = imgResize
            prediction, index = classifile.getPrediction(imgWhite)
            print(prediction, index)
 
 
        else:
            k = imgSize / w
            hCal = math.ceil(k * h)
            imgResize = cv2.resize(imgCrop, (imgSize, hCal))
            imgResizeShape = imgResize.shape
            hGap = math.ceil((imgSize - hCal) / 2)
            imgWhite[hGap:hCal + hGap,:] = imgResize
            prediction, index = classifile.getPrediction(imgWhite)
 
 
        # 解决cv2.putText绘制中文乱码
        def cv2AddChineseText(img, text, position, textColor=(255, 255, 255), textSize=50):
            if (isinstance(img, np.ndarray)):  # 判断是否OpenCV图片类型
                img = Image.fromarray(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
            # 创建一个可以在给定图像上绘图的对象
            draw = ImageDraw.Draw(img)
            # 字体的格式
            fontStyle = ImageFont.truetype(
                "simsun.ttc", textSize, encoding="utf-8")
            # 绘制文本
            draw.text(position, text, textColor, font=fontStyle)
            # 转换回OpenCV格式
            return cv2.cvtColor(np.asarray(img), cv2.COLOR_RGB2BGR)
 
 
        cv2.rectangle(imgOutput, (x - offset, y - offset - 50),
                      (x-offset+130, y-offset), (255, 0, 255), cv2.FILLED)
        # cv2.putText(imgOutput, labels[index], (x,y-24),
        #             cv2.FONT_HERSHEY_COMPLEX, 1.5, (255, 255, 255), 2)
        # 中文
        img = cv2AddChineseText(imgOutput, labels[index], (x - offset, y - offset - 50))
        cv2.rectangle(img, (x-offset, y-offset),
                      (x+w+offset, y+h+offset), (255,0,255),4)
 
        # speech.say(labels[index])
 
        # cv2.imshow('ImageCrop', imgCrop)
        # cv2.imshow('ImageWhite', imgWhite)
 
    cv2.imshow('Image', img)
    key = cv2.waitKey(1)
    if key == ord('s'):
        pass
    elif key == 27:
        break