import numpy as np
import cv2

img = cv2.imread("lena.png")
mask = np.zeros(img.shape[0:2], np.uint8)
green = np.zeros(img.shape, np.uint8)
green[:,:,1] = 255

cv2.circle(mask, center=(300, 300), radius=100, color=255,thickness=-1)

# 透過描画したいマスク領域
mask_area = np.where(mask == 255)

# アルファ値（透過度合い）
alpha = 0.3
img[mask_area] = img[mask_area] * (1-alpha) + green[mask_area] * alpha

cv2.imwrite("lena_converted.png", img)