239 lines
7.9 KiB
Python
239 lines
7.9 KiB
Python
|
import cv2
|
|||
|
|
import numpy as np
|
|||
|
|
import os
|
|||
|
|
from pathlib import Path
|
|||
|
|
|
|||
|
|
def detect_white_paper(image):
|
|||
|
|
"""
|
|||
|
|
检测图像中的白色纸张区域
|
|||
|
|
"""
|
|||
|
|
# 转换为HSV色彩空间
|
|||
|
|
hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
|
|||
|
|
|
|||
|
|
# 更严格的白色检测阈值
|
|||
|
|
lower_white = np.array([0, 0, 230]) # 高亮度，低饱和度
|
|||
|
|
upper_white = np.array([180, 20, 255])
|
|||
|
|
|
|||
|
|
# 创建白色掩码
|
|||
|
|
white_mask = cv2.inRange(hsv, lower_white, upper_white)
|
|||
|
|
|
|||
|
|
# 形态学操作：去除噪点
|
|||
|
|
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 5))
|
|||
|
|
white_mask = cv2.morphologyEx(white_mask, cv2.MORPH_OPEN, kernel)
|
|||
|
|
|
|||
|
|
# 查找轮廓
|
|||
|
|
contours, _ = cv2.findContours(white_mask, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
|||
|
|
|
|||
|
|
# 筛选合适的白色区域（基于面积和形状）
|
|||
|
|
paper_regions = []
|
|||
|
|
for contour in contours:
|
|||
|
|
area = cv2.contourArea(contour)
|
|||
|
|
if area > 5000: # 过滤太小的区域
|
|||
|
|
x, y, w, h = cv2.boundingRect(contour)
|
|||
|
|
aspect_ratio = w / h
|
|||
|
|
# 纸张通常是横向的
|
|||
|
|
if 1.0 < aspect_ratio < 3.0:
|
|||
|
|
paper_regions.append((x, y, w, h))
|
|||
|
|
|
|||
|
|
return paper_regions, white_mask
|
|||
|
|
|
|||
|
|
def find_text_regions(roi):
|
|||
|
|
"""
|
|||
|
|
在ROI中查找文字区域
|
|||
|
|
"""
|
|||
|
|
# 转换为灰度图
|
|||
|
|
gray = cv2.cvtColor(roi, cv2.COLOR_BGR2GRAY)
|
|||
|
|
|
|||
|
|
# 自适应二值化，更好地处理不同光照条件
|
|||
|
|
binary = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
|
|||
|
|
cv2.THRESH_BINARY_INV, 11, 2)
|
|||
|
|
|
|||
|
|
# 形态学操作：连接文字笔画
|
|||
|
|
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (2, 2))
|
|||
|
|
binary = cv2.morphologyEx(binary, cv2.MORPH_CLOSE, kernel)
|
|||
|
|
|
|||
|
|
# 查找轮廓
|
|||
|
|
contours, _ = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
|||
|
|
|
|||
|
|
# 筛选文字轮廓
|
|||
|
|
text_regions = []
|
|||
|
|
for contour in contours:
|
|||
|
|
area = cv2.contourArea(contour)
|
|||
|
|
if 200 < area < 10000: # 合理的文字面积范围
|
|||
|
|
x, y, w, h = cv2.boundingRect(contour)
|
|||
|
|
aspect_ratio = w / h
|
|||
|
|
# 文字通常有合理的宽高比
|
|||
|
|
if 0.3 < aspect_ratio < 4.0:
|
|||
|
|
text_regions.append((x, y, w, h))
|
|||
|
|
|
|||
|
|
return text_regions, binary
|
|||
|
|
|
|||
|
|
def classify_digit(roi, region):
|
|||
|
|
"""
|
|||
|
|
分类数字1或2
|
|||
|
|
"""
|
|||
|
|
x, y, w, h = region
|
|||
|
|
|
|||
|
|
# 提取字符ROI
|
|||
|
|
char_roi = roi[y:y+h, x:x+w]
|
|||
|
|
|
|||
|
|
# 转换为灰度并二值化
|
|||
|
|
gray_char = cv2.cvtColor(char_roi, cv2.COLOR_BGR2GRAY)
|
|||
|
|
_, binary_char = cv2.threshold(gray_char, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)
|
|||
|
|
|
|||
|
|
# 调整大小到统一尺寸
|
|||
|
|
char_resized = cv2.resize(binary_char, (20, 20))
|
|||
|
|
|
|||
|
|
# 计算特征
|
|||
|
|
total_pixels = char_resized.shape[0] * char_resized.shape[1]
|
|||
|
|
black_pixels = np.sum(char_resized == 255)
|
|||
|
|
density = black_pixels / total_pixels
|
|||
|
|
|
|||
|
|
# 计算水平和垂直投影
|
|||
|
|
horizontal_proj = np.sum(char_resized == 255, axis=1)
|
|||
|
|
vertical_proj = np.sum(char_resized == 255, axis=0)
|
|||
|
|
|
|||
|
|
# 计算投影的方差
|
|||
|
|
h_variance = np.var(horizontal_proj)
|
|||
|
|
v_variance = np.var(vertical_proj)
|
|||
|
|
|
|||
|
|
# 计算中心区域密度
|
|||
|
|
center_region = char_resized[6:14, 6:14]
|
|||
|
|
center_density = np.sum(center_region == 255) / (8 * 8)
|
|||
|
|
|
|||
|
|
# 基于特征分类
|
|||
|
|
if density < 0.2:
|
|||
|
|
return "unknown"
|
|||
|
|
|
|||
|
|
# 数字1的特征：垂直投影方差小，中心密度低
|
|||
|
|
if v_variance < 8 and center_density < 0.4 and density < 0.5:
|
|||
|
|
return "1"
|
|||
|
|
|
|||
|
|
# 数字2的特征：垂直投影方差大，中心密度高
|
|||
|
|
if v_variance > 12 and center_density > 0.3 and density > 0.4:
|
|||
|
|
return "2"
|
|||
|
|
|
|||
|
|
return "unknown"
|
|||
|
|
|
|||
|
|
def find_a_and_digit(image_path):
|
|||
|
|
"""
|
|||
|
|
查找A和右侧的数字
|
|||
|
|
"""
|
|||
|
|
# 读取图像
|
|||
|
|
image = cv2.imread(image_path)
|
|||
|
|
if image is None:
|
|||
|
|
print(f"无法读取图像: {image_path}")
|
|||
|
|
return None, []
|
|||
|
|
|
|||
|
|
# 检测白色纸张区域
|
|||
|
|
paper_regions, white_mask = detect_white_paper(image)
|
|||
|
|
|
|||
|
|
if not paper_regions:
|
|||
|
|
print("未检测到白色纸张区域")
|
|||
|
|
return image, []
|
|||
|
|
|
|||
|
|
print(f"检测到 {len(paper_regions)} 个白色纸张区域")
|
|||
|
|
|
|||
|
|
all_results = []
|
|||
|
|
|
|||
|
|
# 处理每个纸张区域
|
|||
|
|
for i, paper_region in enumerate(paper_regions):
|
|||
|
|
x, y, w, h = paper_region
|
|||
|
|
|
|||
|
|
print(f"处理纸张区域 {i+1}: 位置({x}, {y}), 大小({w}x{h})")
|
|||
|
|
|
|||
|
|
# 提取纸张ROI
|
|||
|
|
paper_roi = image[y:y+h, x:x+w]
|
|||
|
|
|
|||
|
|
# 查找文字区域
|
|||
|
|
text_regions, binary = find_text_regions(paper_roi)
|
|||
|
|
|
|||
|
|
print(f" 在区域 {i+1} 中找到 {len(text_regions)} 个文字区域")
|
|||
|
|
|
|||
|
|
# 按x坐标排序文字区域（从左到右）
|
|||
|
|
text_regions.sort(key=lambda r: r[0])
|
|||
|
|
|
|||
|
|
# 查找A和右侧的数字
|
|||
|
|
a_found = False
|
|||
|
|
digit_found = False
|
|||
|
|
|
|||
|
|
for j, text_region in enumerate(text_regions):
|
|||
|
|
tx, ty, tw, th = text_region
|
|||
|
|
|
|||
|
|
# 简单判断：如果区域较宽，可能是A；如果较窄，可能是数字
|
|||
|
|
if tw > th * 1.5 and not a_found: # 可能是A
|
|||
|
|
a_found = True
|
|||
|
|
result = {
|
|||
|
|
'region_id': i + 1,
|
|||
|
|
'char_id': j + 1,
|
|||
|
|
'char_type': 'A',
|
|||
|
|
'position': (x + tx, y + ty, tw, th),
|
|||
|
|
'relative_position': (tx, ty, tw, th)
|
|||
|
|
}
|
|||
|
|
all_results.append(result)
|
|||
|
|
print(f" 找到A: 位置({tx}, {ty}), 大小({tw}x{th})")
|
|||
|
|
|
|||
|
|
elif tw <= th * 1.5 and a_found and not digit_found: # 可能是数字
|
|||
|
|
# 分类数字
|
|||
|
|
digit_type = classify_digit(paper_roi, text_region)
|
|||
|
|
if digit_type in ['1', '2']:
|
|||
|
|
digit_found = True
|
|||
|
|
result = {
|
|||
|
|
'region_id': i + 1,
|
|||
|
|
'char_id': j + 1,
|
|||
|
|
'char_type': digit_type,
|
|||
|
|
'position': (x + tx, y + ty, tw, th),
|
|||
|
|
'relative_position': (tx, ty, tw, th)
|
|||
|
|
}
|
|||
|
|
all_results.append(result)
|
|||
|
|
print(f" 找到数字{digit_type}: 位置({tx}, {ty}), 大小({tw}x{th})")
|
|||
|
|
break
|
|||
|
|
|
|||
|
|
# 在纸张周围绘制边框
|
|||
|
|
cv2.rectangle(image, (x, y), (x + w, y + h), (255, 0, 0), 3)
|
|||
|
|
cv2.putText(image, f"Paper {i+1}", (x, y - 10),
|
|||
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 0, 0), 2)
|
|||
|
|
|
|||
|
|
# 在识别结果周围绘制边框
|
|||
|
|
for result in all_results:
|
|||
|
|
rx, ry, rw, rh = result['position']
|
|||
|
|
color = (0, 255, 0) if result['char_type'] != "unknown" else (0, 0, 255)
|
|||
|
|
cv2.rectangle(image, (rx, ry), (rx + rw, ry + rh), color, 2)
|
|||
|
|
cv2.putText(image, result['char_type'], (rx, ry - 5),
|
|||
|
|
cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
|
|||
|
|
|
|||
|
|
return image, all_results
|
|||
|
|
|
|||
|
|
def main():
|
|||
|
|
"""
|
|||
|
|
主函数：测试A和数字识别
|
|||
|
|
"""
|
|||
|
|
# 图片路径
|
|||
|
|
img_dir = Path("imgs")
|
|||
|
|
img_path = img_dir / "a1.jpg"
|
|||
|
|
|
|||
|
|
print("开始识别图片中的A和右侧数字...")
|
|||
|
|
|
|||
|
|
# 识别图片
|
|||
|
|
if img_path.exists():
|
|||
|
|
print(f"\n识别图片: {img_path}")
|
|||
|
|
result_img, results = find_a_and_digit(str(img_path))
|
|||
|
|
|
|||
|
|
if results:
|
|||
|
|
print("\n识别结果:")
|
|||
|
|
for result in results:
|
|||
|
|
print(f" 区域{result['region_id']}-字符{result['char_id']}: {result['char_type']}, "
|
|||
|
|
f"位置: {result['position']}")
|
|||
|
|
else:
|
|||
|
|
print("未识别到A和数字")
|
|||
|
|
|
|||
|
|
# 保存结果图片
|
|||
|
|
output_path = img_dir / "result_a_digit.jpg"
|
|||
|
|
cv2.imwrite(str(output_path), result_img)
|
|||
|
|
print(f"\n结果图片已保存到: {output_path}")
|
|||
|
|
|
|||
|
|
print("\n识别完成！")
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
main()
|