154 lines
5.7 KiB
Python
154 lines
5.7 KiB
Python
|
|
# coding=utf-8
|
|||
|
|
import cv2
|
|||
|
|
import numpy as np
|
|||
|
|
import os
|
|||
|
|
|
|||
|
|
def analyze_chat_image(image_path, output_path):
|
|||
|
|
print(f"正在读取图片: {image_path}")
|
|||
|
|
|
|||
|
|
# 读取图片
|
|||
|
|
# 注意:cv2.imread 不支持中文路径,需要用 np.fromfile 读取
|
|||
|
|
try:
|
|||
|
|
img_data = np.fromfile(image_path, dtype=np.uint8)
|
|||
|
|
img = cv2.imdecode(img_data, cv2.IMREAD_COLOR)
|
|||
|
|
except Exception as e:
|
|||
|
|
print(f"读取图片失败: {e}")
|
|||
|
|
return
|
|||
|
|
|
|||
|
|
if img is None:
|
|||
|
|
print("图片读取为空")
|
|||
|
|
return
|
|||
|
|
|
|||
|
|
height, width = img.shape[:2]
|
|||
|
|
print(f"图片尺寸: {width}x{height}")
|
|||
|
|
|
|||
|
|
# 1. 预处理
|
|||
|
|
# 转为灰度图
|
|||
|
|
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
|
|||
|
|
|
|||
|
|
# 使用自适应阈值二值化
|
|||
|
|
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
|
|||
|
|
cv2.THRESH_BINARY_INV, 11, 2)
|
|||
|
|
|
|||
|
|
# 形态学操作:闭运算,填充内部空洞
|
|||
|
|
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
|
|||
|
|
closed = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel)
|
|||
|
|
|
|||
|
|
# 2. 轮廓查找
|
|||
|
|
contours, _ = cv2.findContours(closed, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
|||
|
|
|
|||
|
|
print(f"检测到轮廓数量: {len(contours)}")
|
|||
|
|
|
|||
|
|
# 收集所有符合条件的头像
|
|||
|
|
avatars = []
|
|||
|
|
|
|||
|
|
# 3. 筛选轮廓
|
|||
|
|
for contour in contours:
|
|||
|
|
# 获取外接矩形
|
|||
|
|
x, y, w, h = cv2.boundingRect(contour)
|
|||
|
|
|
|||
|
|
# 筛选条件优化:
|
|||
|
|
# 1. 形状接近正方形 (放宽宽高比限制: 0.8 ~ 1.2)
|
|||
|
|
aspect_ratio = float(w) / h
|
|||
|
|
|
|||
|
|
# 2. 尺寸适中
|
|||
|
|
# 假设头像宽度在屏幕宽度的 6% 到 15% 之间
|
|||
|
|
min_w = width * 0.06
|
|||
|
|
max_w = width * 0.15
|
|||
|
|
|
|||
|
|
# 3. 位置筛选
|
|||
|
|
# 排除底部输入框区域 (假设底部 10% 为输入区域)
|
|||
|
|
if y > height * 0.9:
|
|||
|
|
continue
|
|||
|
|
|
|||
|
|
# 左侧头像:靠左边 (x < width * 0.18)
|
|||
|
|
# 右侧头像:靠右边 (x > width * 0.82)
|
|||
|
|
is_left = x < width * 0.18
|
|||
|
|
is_right = x > width * 0.82
|
|||
|
|
|
|||
|
|
if 0.8 <= aspect_ratio <= 1.2 and min_w < w < max_w:
|
|||
|
|
if is_left or is_right:
|
|||
|
|
side = "Left" if is_left else "Right"
|
|||
|
|
avatars.append({
|
|||
|
|
'x': x, 'y': y, 'w': w, 'h': h,
|
|||
|
|
'side': side
|
|||
|
|
})
|
|||
|
|
|
|||
|
|
# 按 y 坐标排序
|
|||
|
|
avatars.sort(key=lambda a: a['y'])
|
|||
|
|
|
|||
|
|
print(f"找到有效头像数量: {len(avatars)}")
|
|||
|
|
|
|||
|
|
# 4. 绘制对话内容框 (Green/Red Boxes)
|
|||
|
|
# 策略:按顺序遍历头像,如果发现同侧连续,则视为一组。
|
|||
|
|
# 从当前组的第一个头像上方开始,直到下一个不同侧的头像上方(或底部)。
|
|||
|
|
|
|||
|
|
if avatars:
|
|||
|
|
i = 0
|
|||
|
|
while i < len(avatars):
|
|||
|
|
current_group_start = i
|
|||
|
|
current_side = avatars[i]['side']
|
|||
|
|
|
|||
|
|
# 找到当前组的结束位置 (即下一个不同侧头像的索引)
|
|||
|
|
j = i + 1
|
|||
|
|
while j < len(avatars) and avatars[j]['side'] == current_side:
|
|||
|
|
j += 1
|
|||
|
|
|
|||
|
|
# 当前组范围: avatars[i] ... avatars[j-1]
|
|||
|
|
# 确定绘制区域的 Y 轴范围
|
|||
|
|
|
|||
|
|
# Start Y: 当前组第一个头像的上方 (例如 -10px)
|
|||
|
|
start_y = max(0, avatars[i]['y'] - 10)
|
|||
|
|
|
|||
|
|
# End Y: 下一组第一个头像的上方 (减去较大间距,例如 -30px),或者当前组最后一个头像的底部加上边距
|
|||
|
|
# 为了让框之间有明显间隔,我们采取策略:
|
|||
|
|
# 如果有下一组,End Y = 下一组第一个头像的 y - 30 (留出间隙)
|
|||
|
|
# 如果没有下一组,End Y = 屏幕底部区域上方
|
|||
|
|
|
|||
|
|
if j < len(avatars):
|
|||
|
|
end_y = max(start_y + 10, avatars[j]['y'] - 30)
|
|||
|
|
else:
|
|||
|
|
end_y = int(height * 0.9) # 到底部输入框上方
|
|||
|
|
|
|||
|
|
# 绘制大框
|
|||
|
|
# 左侧 (Left) -> 对方 -> 绿色 (0, 255, 0)
|
|||
|
|
# 右侧 (Right) -> 我 -> 红色 (0, 0, 255)
|
|||
|
|
# 注意 OpenCV 颜色是 BGR
|
|||
|
|
box_color = (0, 255, 0) if current_side == "Left" else (0, 0, 255)
|
|||
|
|
|
|||
|
|
# 绘制矩形 (空心,线宽 5)
|
|||
|
|
# X 轴范围:0 到 width
|
|||
|
|
cv2.rectangle(img, (0, start_y), (width, end_y), box_color, 5)
|
|||
|
|
|
|||
|
|
print(f"绘制内容框: 侧别={current_side}, 范围 Y={start_y} to {end_y}")
|
|||
|
|
|
|||
|
|
# 移动到下一组
|
|||
|
|
i = j
|
|||
|
|
|
|||
|
|
# 5. 绘制头像框 (Blue/Yellow Boxes) - 画在内容框之上
|
|||
|
|
for av in avatars:
|
|||
|
|
x, y, w, h = av['x'], av['y'], av['w'], av['h']
|
|||
|
|
# 左侧:蓝色 (BGR: 255, 0, 0)
|
|||
|
|
# 右侧:黄色 (BGR: 0, 255, 255)
|
|||
|
|
color = (255, 0, 0) if av['side'] == "Left" else (0, 255, 255)
|
|||
|
|
|
|||
|
|
cv2.rectangle(img, (x, y), (x + w, y + h), color, 10)
|
|||
|
|
print(f"绘制头像: 位置=({x},{y}), 侧别={av['side']}")
|
|||
|
|
|
|||
|
|
# 6. 保存结果
|
|||
|
|
try:
|
|||
|
|
# cv2.imwrite 不支持中文路径,使用 imencode + tofile
|
|||
|
|
ext = os.path.splitext(output_path)[1]
|
|||
|
|
cv2.imencode(ext, img)[1].tofile(output_path)
|
|||
|
|
print(f"结果已保存至: {output_path}")
|
|||
|
|
except Exception as e:
|
|||
|
|
print(f"保存图片失败: {e}")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
# 输入文件路径
|
|||
|
|
input_file = r"d:\dsWork\aiData\Test\Screenshots\chat_result_20260121_113553.jpg"
|
|||
|
|
# 输出文件路径
|
|||
|
|
output_file = r"d:\dsWork\aiData\Test\Screenshots\chat_result_analyzed.jpg"
|
|||
|
|
|
|||
|
|
analyze_chat_image(input_file, output_file)
|