# -*- coding: utf-8 -*-
# @Time    : 2024/4/15 9:39
# @Author  : len
# @File    : 感兴趣区域提取2.py
# @Software: PyCharm 
# @Comment :
import os

import cv2
import numpy as np
from matplotlib import pyplot as plt
plt.rcParams['font.sans-serif'] = ['SimHei']

# 定义一个调整后的图像处理函数来改善屏幕检测
def process_image_adjusted(image_path):
    # 加载图片
    image = cv2.imread(image_path)

    # 将图片转换成灰度图
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # 应用高斯模糊，减少噪点，提升边缘检测效果
    blurred = cv2.GaussianBlur(gray, (5, 5), 0)

    # 自适应阈值化创建二值图像
    threshold = cv2.adaptiveThreshold(blurred, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
                                      cv2.THRESH_BINARY_INV, 11, 2)

    # 从阈值化的图像中找轮廓
    contours, _ = cv2.findContours(threshold, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

    # 根据轮廓面积排序，并移除面积较小的轮廓
    contours = sorted(contours, key=cv2.contourArea, reverse=True)
    large_contours = [cnt for cnt in contours if cv2.contourArea(cnt) > 1000]

    screen_contour = None
    for contour in large_contours:
        # 将轮廓近似为多边形
        perimeter = cv2.arcLength(contour, True)
        approximation = cv2.approxPolyDP(contour, 0.02 * perimeter, True)

        # 如果多边形有4条边，我们假设它是屏幕
        if len(approximation) == 4:
            screen_contour = approximation
            break

    # 在图片上绘制轮廓
    if screen_contour is not None:
        cv2.drawContours(image, [screen_contour], -1, (0, 255, 0), 3)
        screen_image = cv2.polylines(image, [screen_contour], True, (0, 255, 0), 3)
    else:
        screen_image = image

    # 展示结果
    plt.imshow(cv2.cvtColor(screen_image, cv2.COLOR_BGR2RGB))
    plt.title('调整后的屏幕检测')
    plt.axis('off')  # 关闭坐标轴显示
    plt.show()


# 设置文件夹路径
folder_path = './data/pingmu'  # 将此路径替换为你的图片文件夹路径

# 遍历文件夹中的所有文件
for filename in os.listdir(folder_path):
    if filename.lower().endswith(('.png', '.jpg', '.jpeg')):  # 检查文件扩展名
        file_path = os.path.join(folder_path, filename)  # 获取文件完整路径
        process_image_adjusted(file_path)