213 lines
7.1 KiB
Python
213 lines
7.1 KiB
Python
from PIL import Image
|
||
from PIL.Image import Image
|
||
import cv2
|
||
import numpy as np
|
||
from PIL import Image
|
||
|
||
|
||
def split_image(image_array: np.ndarray, dirt: int) -> (np.ndarray, np.ndarray):
|
||
# 确保图像是二维的灰度图
|
||
if len(image_array.shape) > 2:
|
||
# 如果是彩色图，转换为灰度图 (取平均值或者只取一个通道)
|
||
image_array = image_array.mean(axis=2) # 或者直接取第一个通道：image_array = image_array[:, :, 0]
|
||
|
||
# 将图片转为二值化（假设白色背景值为255，黑色文字值为0）
|
||
# 你可以根据图片实际情况调整阈值
|
||
_, binary_image = cv2.threshold(image_array, 127, 255, cv2.THRESH_BINARY)
|
||
|
||
# 寻找切割线
|
||
split_line = find_split_line(binary_image, dirt)
|
||
|
||
if dirt == 1:
|
||
# 竖着切
|
||
split1 = image_array[:, :split_line]
|
||
split2 = image_array[:, split_line:]
|
||
else:
|
||
# 横着切
|
||
split1 = image_array[:split_line, :]
|
||
split2 = image_array[split_line:, :]
|
||
|
||
return split1, split2
|
||
|
||
|
||
def find_split_line(image_array, dirt):
|
||
height, width = image_array.shape # 现在应该是 (height, width)
|
||
|
||
# 根据dirt值选择切割方向
|
||
if dirt == 1:
|
||
# 竖着切
|
||
middle = width // 2
|
||
for x in range(middle, width):
|
||
# 检查竖直方向的列是否全为空白
|
||
if np.all(image_array[:, x] > 200): # 假设200是空白阈值
|
||
return x
|
||
return middle # 如果找不到合适的切割线，返回中间
|
||
else:
|
||
# 横着切
|
||
middle = height // 2
|
||
for y in range(middle, height):
|
||
# 检查水平方向的行是否全为空白
|
||
if np.all(image_array[y, :] > 200): # 假设200是空白阈值
|
||
return y
|
||
return middle # 如果找不到合适的切割线，返回中间
|
||
|
||
|
||
async def image_split(image: np.ndarray, dirt: int):
|
||
part1, part2 = split_image(image, dirt)
|
||
# 将 NumPy 数组转换为 Pillow 图像对象
|
||
pil_image1 = Image.fromarray(part1)
|
||
pil_image2 = Image.fromarray(part2)
|
||
# 显示图像
|
||
pil_image1.show()
|
||
pil_image2.show()
|
||
return pil_image1, pil_image2
|
||
|
||
|
||
async def get_able_area(image, coords, text):
|
||
"""
|
||
根据给定的文本区域坐标，从图像中截取文本区域。
|
||
|
||
:param text:
|
||
:param image: 原始图像 (使用cv2.imread读取的图像)
|
||
:param coords: 文本区域的四个角坐标，格式为：
|
||
[[x1_top_left, y1_top_left],
|
||
[x2_top_right, y2_top_right],
|
||
[x3_bottom_right, y3_bottom_right],
|
||
[x4_bottom_left, y4_bottom_left]]
|
||
:return: 截取的文本区域图像
|
||
"""
|
||
# 将坐标转换为numpy数组并重新整理为 [[x1, y1], [x2, y2], [x3, y3], [x4, y4]] 的形式
|
||
pts = np.float32([coords[0], coords[1], coords[2], coords[3]])
|
||
|
||
# 计算变换后的目标矩形的宽和高
|
||
top_width = np.linalg.norm(np.array(coords[1]) - np.array(coords[0])) # 顶边长度
|
||
bottom_width = np.linalg.norm(np.array(coords[2]) - np.array(coords[3])) # 底边长度
|
||
height = np.linalg.norm(np.array(coords[2]) - np.array(coords[1])) # 高
|
||
|
||
# 取最大宽度作为目标宽度
|
||
max_width = max(top_width, bottom_width)
|
||
|
||
# 目标矩形的四个角点
|
||
dst = np.float32([[0, 0], [max_width - 1, 0], [max_width - 1, height - 1], [0, height - 1]])
|
||
|
||
# 计算透视变换矩阵
|
||
M = cv2.getPerspectiveTransform(pts, dst)
|
||
|
||
# 进行透视变换，获取裁剪后的图像
|
||
cropped_image = cv2.warpPerspective(image, M, (int(max_width), int(height)))
|
||
await get_box_size(cropped_image, text)
|
||
|
||
|
||
async def get_box_size(image, text):
|
||
# 预处理图像
|
||
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
||
_, binary = cv2.threshold(gray, 128, 255, cv2.THRESH_BINARY_INV)
|
||
|
||
# 查找轮廓
|
||
contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||
|
||
# 存储所有文字大小
|
||
text_sizes = []
|
||
|
||
# 遍历每个轮廓
|
||
for cnt in contours:
|
||
# 获取包围盒的坐标和尺寸
|
||
x, y, w, h = cv2.boundingRect(cnt)
|
||
|
||
# 计算文字区域的面积
|
||
area = cv2.contourArea(cnt)
|
||
|
||
# 假设每个文字区域有一个平均字符数 (可以根据实际情况调整)
|
||
avg_char_width = w // len(text) # 假设每行有10个字符
|
||
avg_char_height = h // 1 # 假设每行有1个字符
|
||
|
||
# 计算字符的大小
|
||
character_size = (avg_char_width, avg_char_height)
|
||
text_sizes.append(character_size)
|
||
|
||
# 可视化结果
|
||
cv2.rectangle(image, (x, y), (x + h, y + h), (0, 255, 0), 2)
|
||
|
||
# 计算平均字符大小
|
||
if len(text_sizes) > 0:
|
||
avg_char_width = sum(size[0] for size in text_sizes) / len(text_sizes)
|
||
avg_char_height = sum(size[1] for size in text_sizes) / len(text_sizes)
|
||
print(f"平均字符宽度: {avg_char_width}, 平均字符高度: {avg_char_height}")
|
||
else:
|
||
print("未检测到文字区域")
|
||
|
||
# 显示结果图像
|
||
im = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
||
il_image1 = Image.fromarray(im)
|
||
il_image1.show()
|
||
|
||
#增强图片
|
||
async def positive_image(image):
|
||
# 1. 灰度化（注意：输入为 RGB，须用 COLOR_RGB2GRAY；误用 BGR 会翻转红蓝通道，彩色文字/背景灰度失真）
|
||
gray_img = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
|
||
|
||
# 2. 对比度增强（CLAHE）
|
||
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
|
||
enhanced = clahe.apply(gray_img)
|
||
|
||
# 3. 锐化（可选）
|
||
blurred = cv2.GaussianBlur(enhanced, (0, 0), 2)
|
||
sharpened = cv2.addWeighted(enhanced, 1.5, blurred, -0.5, 0)
|
||
|
||
return sharpened
|
||
|
||
|
||
def draw_text_box(image, coords):
|
||
pos1 = coords[0]
|
||
pos2 = coords[2]
|
||
x1 = int(pos1[0])
|
||
y1 = int(pos1[1])
|
||
x2 = int(pos2[0])
|
||
y2 = int(pos2[1])
|
||
# 可视化结果
|
||
cv2.rectangle(image, (x1, y1), (x2, y2), (0, 255, 0), 1)
|
||
|
||
|
||
# 倾斜矫正
|
||
async def tilt_correction(image):
|
||
# 转为灰度图
|
||
gray_img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
||
|
||
# 二值化
|
||
_, binary_img = cv2.threshold(gray_img, 128, 255, cv2.THRESH_BINARY)
|
||
|
||
# 边缘检测
|
||
edges = cv2.Canny(binary_img, 50, 150)
|
||
|
||
# 提取轮廓
|
||
contours, _ = cv2.findContours(edges, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
||
|
||
if len(contours) == 0:
|
||
print("No contours found.")
|
||
return image # 没有找到轮廓，返回原图
|
||
|
||
# 找到最大轮廓
|
||
largest_contour = max(contours, key=cv2.contourArea)
|
||
|
||
# 计算最小外接矩形的角度
|
||
rect = cv2.minAreaRect(largest_contour)
|
||
angle = rect[-1]
|
||
|
||
# 修正角度
|
||
if angle < -45:
|
||
angle = -(90 + angle) # 修正角度，使其在 [-90, 90] 范围内
|
||
else:
|
||
angle = -angle # 直接取反号
|
||
|
||
# 如果角度接近0度，则不进行旋转
|
||
if abs(angle) < 0.5:
|
||
return image # 角度非常小，几乎不需要旋转
|
||
|
||
# 旋转图像
|
||
(h, w) = image.shape[:2] # 使用原始图像的形状
|
||
center = (w // 2, h // 2)
|
||
M = cv2.getRotationMatrix2D(center, angle, 1.0)
|
||
rotated_img = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
|
||
|
||
return rotated_img
|