项目初始化

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/easyocr-api.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,41 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="DuplicatedCode" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <Languages>
+        <language minSize="130" name="Python" />
+      </Languages>
+    </inspection_tool>
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="8">
+            <item index="0" class="java.lang.String" itemvalue="protobuf" />
+            <item index="1" class="java.lang.String" itemvalue="mkl-random" />
+            <item index="2" class="java.lang.String" itemvalue="numpy" />
+            <item index="3" class="java.lang.String" itemvalue="starlette" />
+            <item index="4" class="java.lang.String" itemvalue="charset-normalizer" />
+            <item index="5" class="java.lang.String" itemvalue="h11" />
+            <item index="6" class="java.lang.String" itemvalue="obs" />
+            <item index="7" class="java.lang.String" itemvalue="torch" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8Inspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="W292" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N803" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (easyocr)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/easyocr-api.iml" filepath="$PROJECT_DIR$/.idea/easyocr-api.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

README.md

@@ -0,0 +1 @@
+ocr demo,里面有两个模型 一个是easyocr，一个是百度的paddleocr

api/easy_orc_api.py

@@ -0,0 +1,61 @@
+import os
+import cv2
+import easyocr
+import numpy as np
+from core.response import SuccessResponse
+from fastapi import APIRouter, UploadFile, Form
+from schemas.orc_result import ResultInfo, ResultMain
+
+
+app = APIRouter()
+
+BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+model_dir = os.path.join(BASE_DIR, 'model')
+
+reader = easyocr.Reader(
+    ['ch_sim', 'en'],
+    model_storage_directory=model_dir,
+    download_enabled=False,
+    gpu=True)
+
+
+def preprocess_img(image):
+    # 转为灰度图
+    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    # 二值化
+    _, binary = cv2.threshold(gray, 150, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
+    # 去噪声
+    denoised = cv2.medianBlur(binary, 3)
+    return denoised
+
+
+@app.post("/upload")
+async def orc(files: list[UploadFile] = Form(...)):
+    result = []
+    for file in files:
+        main = ResultMain()
+        main.file_name = file.filename
+        # 读取上传的文件内容
+        image_data = await file.read()
+
+        # 2. 将字节数据转换为 numpy 数组
+        np_array = np.frombuffer(image_data, np.uint8)
+
+        # 3. 使用 cv2.imdecode 解码为 OpenCV 图像
+        image = cv2.imdecode(np_array, cv2.IMREAD_COLOR)
+        new_image = preprocess_img(image)
+        datas = reader.readtext(np.array(new_image))
+        infos = []
+        for data in datas:
+            info = ResultInfo()
+            bounding_boxs = data[0]
+            left_up = bounding_boxs[0]
+            right_down = bounding_boxs[2]
+            info.bounding_box_left_up = [int(left_up[0]), int(left_up[1])]
+            info.bounding_box_right_down = [int(right_down[0]), int(right_down[1])]
+            info.text = data[1]
+            info.confidence = round(data[2], 4)
+            infos.append(info)
+        main.infos = infos
+        result.append(main.model_dump())
+    return SuccessResponse(data=result)

api/paddle_ocr_api.py

@@ -0,0 +1,55 @@
+from core.response import SuccessResponse
+from fastapi import APIRouter, UploadFile, Form
+from schemas.orc_result import ResultInfo, ResultMain
+
+from paddleocr import PaddleOCR
+import numpy as np
+import cv2
+
+
+app = APIRouter()
+
+
+paddle_ocr = PaddleOCR(lang='ch')
+
+
+def enhance_image(img):
+    """增强亮部和暗部，提升数字清晰度"""
+    lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)
+    l, a, b = cv2.split(lab)
+    clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8,8))
+    cl = clahe.apply(l)
+    enhanced = cv2.merge((cl, a, b))
+    return cv2.cvtColor(enhanced, cv2.COLOR_LAB2BGR)
+
+
+@app.post("/upload")
+async def orc(files: list[UploadFile] = Form(...)):
+    result = []
+    for file in files:
+        main = ResultMain()
+        main.file_name = file.filename
+        # 读取上传的文件内容
+        image_data = await file.read()
+        # 从字节数据读取图像
+        np_array = np.frombuffer(image_data, np.uint8)
+        img = cv2.imdecode(np_array, cv2.IMREAD_COLOR)
+        # 图像增强
+        img = enhance_image(img)
+        # 4. 调用 OCR 模型进行识别
+        datas = paddle_ocr.ocr(img, cls=False)
+        infos = []
+        if datas:
+            for data in datas[0]:
+                info = ResultInfo()
+                bounding_boxs = data[0]
+                left_up = bounding_boxs[0]
+                right_down = bounding_boxs[2]
+                info.bounding_box_left_up = [int(left_up[0]), int(left_up[1])]
+                info.bounding_box_right_down = [int(right_down[0]), int(right_down[1])]
+                info.text = data[1][0]
+                info.confidence = round(data[1][1], 4)
+                infos.append(info)
+            main.infos = infos
+            result.append(main.model_dump())
+    return SuccessResponse(data=result)

application.py

@@ -0,0 +1,24 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+from api.easy_orc_api import app as easy_orc_api
+
+from api.paddle_ocr_api import app as paddle_ocr_api
+
+
+app = FastAPI()
+
+
+'''
+添加cros中间件，允许跨域请求
+'''
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+app.include_router(paddle_ocr_api, prefix="/ocr", tags=["ocr识别"])

core/response.py

@@ -0,0 +1,32 @@
+# 依赖安装：pip install orjson
+from fastapi.responses import ORJSONResponse as Response
+from fastapi import status as http_status
+from core import status as http
+
+
+class SuccessResponse(Response):
+    """
+    成功响应
+    """
+    def __init__(self, data=None, msg="success", code=http.HTTP_SUCCESS, status=http_status.HTTP_200_OK, **kwargs):
+        self.data = {
+            "code": code,
+            "message": msg,
+            "data": data
+        }
+        self.data.update(kwargs)
+        super().__init__(content=self.data, status_code=status)
+
+
+class ErrorResponse(Response):
+    """
+    失败响应
+    """
+    def __init__(self, msg=None, code=http.HTTP_ERROR, status=http_status.HTTP_200_OK, **kwargs):
+        self.data = {
+            "code": code,
+            "message": msg,
+            "data": []
+        }
+        self.data.update(kwargs)
+        super().__init__(content=self.data, status_code=status)

core/status.py

@@ -0,0 +1,14 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+# @version        : 1.0
+# @Create Time    : 2022/8/10 22:20 
+# @File           : status.py
+# @IDE            : PyCharm
+# @desc           : 简要说明
+
+
+HTTP_SUCCESS = 200
+HTTP_ERROR = 400
+HTTP_401_UNAUTHORIZED = 401
+HTTP_403_FORBIDDEN = 403
+HTTP_404_NOT_FOUND = 404

main.py

@@ -0,0 +1,5 @@
+import uvicorn
+from application import app
+
+if __name__ == '__main__':
+    uvicorn.run("main:app", port=9800, reload=False, host='0.0.0.0')

requirement.txt

@@ -0,0 +1,6 @@
+fastapi==0.112.2
+uvicorn==0.32.1
+easyocr==1.7.2
+orjson==3.10.16
+python-multipart==0.0.20
+paddleocr==2.10.0

schemas/orc_result.py

@@ -0,0 +1,18 @@
+from pydantic import BaseModel, ConfigDict, field_validator
+
+
+class ResultInfo(BaseModel):
+    bounding_box_left_up: list[int] | None = []
+    bounding_box_right_down: list[int] | None = []
+    text: str | None = None
+    confidence: float | None = None
+
+    model_config = ConfigDict(from_attributes=True)
+
+
+class ResultMain(BaseModel):
+    file_name: str | None = None
+    infos: list[ResultInfo] | None = []
+
+    model_config = ConfigDict(from_attributes=True)
+

utils/opencv_util.py

@@ -0,0 +1,17 @@
+# 增强对比度 + 灰度转换 + 自适应阈值
+import cv2
+
+img = cv2.imread("fb1df265-5085-4bc2-881b-7674b620c4ac.jpg")
+
+# 转灰度图
+gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
+
+# 提升对比度
+clahe = cv2.createCLAHE(clipLimit=3.0, tileGridSize=(8, 8))
+enhanced = clahe.apply(gray)
+
+# 二值化处理
+binary = cv2.adaptiveThreshold(enhanced, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C,
+                               cv2.THRESH_BINARY_INV, 11, 2)
+
+cv2.imwrite("processed.png", binary)

utils/os_utils.py

@@ -0,0 +1,39 @@
+import os
+from fastapi import UploadFile
+
+
+def file_path(*path):
+    """
+    拼接返回文件路径
+    :param path:
+    :return:
+    """
+    return_path = os.path.join(*path)
+    return return_path
+
+
+def create_folder(*path):
+    """根据路径创建文件夹"""
+    folder_path = os.path.join(*path)
+    try:
+        os.makedirs(folder_path, exist_ok=True)
+    except Exception as e:
+        print(f"创建文件夹时错误： {e}")
+    return folder_path
+
+
+def save_images(*path, file: UploadFile):
+    """
+    保存上传的图片
+    :param path: 路径
+    :param file: 文件
+    :return:
+    """
+    save_path = os.path.join(*path, file.filename)
+
+    os.makedirs(os.path.dirname(save_path), exist_ok=True)
+    with open(save_path, "wb") as f:
+        for line in file.file:
+            f.write(line)
+    return save_path
+

utils/pillow_util.py

@@ -0,0 +1,11 @@
+from PIL import Image, ImageEnhance
+
+# 加载图片
+img = Image.open("fb1df265-5085-4bc2-881b-7674b620c4ac.jpg")
+
+# 增强对比度（1.5 倍为示例，你可以调节参数）
+enhancer = ImageEnhance.Contrast(img)
+img_enhanced = enhancer.enhance(4.0)
+
+# 保存增强后的图像
+img_enhanced.save("enhanced_image_pillow.png")