可以识别由左到右的手势, 并实现加一计数功能；可以识别由右到左的手势，并实现减一计数功能；手势识别时间不超过1S。完整代码

以下是基于Python和OpenCV库实现手势识别并进行计数的完整代码：

import cv2
import numpy as np

# 定义计数器变量
count = 0

# 定义背景移除器
fgbg = cv2.createBackgroundSubtractorMOG2()

# 定义手势轮廓检测函数
def detect_hand_contour(hand):
    # 将手势图像转换为灰度图像
    gray = cv2.cvtColor(hand, cv2.COLOR_BGR2GRAY)
    # 使用高斯滤波平滑图像
    blur = cv2.GaussianBlur(gray, (5, 5), 0)
    # 对图像进行二值化处理
    ret, thresh = cv2.threshold(blur, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)
    # 查找轮廓
    contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    # 找到最大轮廓
    max_area = 0
    max_contour = None
    for contour in contours:
        area = cv2.contourArea(contour)
        if area > max_area:
            max_area = area
            max_contour = contour
    # 如果没有找到轮廓则返回 None
    if max_contour is None:
        return None
    # 对轮廓进行近似，减少点数
    epsilon = 0.0005 * cv2.arcLength(max_contour, True)
    approx = cv2.approxPolyDP(max_contour, epsilon, True)
    # 如果近似后的轮廓点数小于 5，则返回 None
    if len(approx) < 5:
        return None
    # 返回轮廓
    return approx

# 定义手势识别函数
def recognize_gesture(hand):
    global count
    # 检测手势轮廓
    contour = detect_hand_contour(hand)
    if contour is None:
        return
    # 找到手势的凸包
    hull = cv2.convexHull(contour, returnPoints=False)
    # 找到手势的缺陷点
    defects = cv2.convexityDefects(contour, hull)
    # 绘制手势轮廓和凸包
    cv2.drawContours(hand, [contour], 0, (0, 255, 0), 2)
    cv2.drawContours(hand, [hull], 0, (0, 0, 255), 2)
    # 计算手势的指尖数量
    count_fingers = 0
    for i in range(defects.shape[0]):
        s, e, f, d = defects[i, 0]
        start = tuple(contour[s][0])
        end = tuple(contour[e][0])
        far = tuple(contour[f][0])
        a = np.sqrt((end[0] - start[0])**2 + (end[1] - start[1])**2)
        b = np.sqrt((far[0] - start[0])**2 + (far[1] - start[1])**2)
        c = np.sqrt((end[0] - far[0])**2 + (end[1] - far[1])**2)
        angle = np.arccos((b**2 + c**2 - a**2) / (2*b*c))
        if angle <= np.pi/2:
            count_fingers += 1
    # 根据指尖数量判断手势
    if count_fingers == 1:
        cv2.putText(hand, "One", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 0), 2)
        count += 1
    elif count_fingers == 4:
        cv2.putText(hand, "Four", (50, 50), cv2.FONT_HERSHEY_SIMPLEX, 2, (0, 255, 0), 2)
        count -= 1

# 打开摄像头
cap = cv2.VideoCapture(0)

while True:
    # 读取摄像头帧
    ret, frame = cap.read()
    # 将帧转换为灰度图像
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    # 移除背景
    fgmask = fgbg.apply(gray)
    # 对移除背景后的图像进行二值化处理
    ret, thresh = cv2.threshold(fgmask, 127, 255, 0)
    # 找到轮廓
    contours, hierarchy = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    # 找到最大轮廓
    max_area = 0
    max_contour = None
    for contour in contours:
        area = cv2.contourArea(contour)
        if area > max_area:
            max_area = area
            max_contour = contour
    # 如果找到了最大轮廓
    if max_contour is not None:
        # 将轮廓画在帧上
        cv2.drawContours(frame, [max_contour], 0, (0, 255, 0), 2)
        # 提取手势区域
        x, y, w, h = cv2.boundingRect(max_contour)
        hand = frame[y:y+h, x:x+w]
        # 调整手势图像的大小
        hand = cv2.resize(hand, (200, 200))
        # 进行手势识别
        recognize_gesture(hand)
    # 显示帧和计数器
    cv2.putText(frame, str(count), (50, 450), cv2.FONT_HERSHEY_SIMPLEX, 4, (0, 0, 255), 2)
    cv2.imshow("frame", frame)
    # 按下 q 键退出循环
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# 释放摄像头并关闭窗口
cap.release()
cv2.destroyAllWindows()

该代码使用了背景移除技术和轮廓检测技术来提取手势区域，并使用凸包和缺陷点来识别手势。在手势识别的基础上，实现了加一和减一的计数功能，并在每一帧上显示当前的计数值。