init

xjr_application/OCR命令行指令.txt

@@ -0,0 +1,20 @@
+conda activate D:\Program Files\anaconda3\envs\paddle_env D:\Program Files\anaconda3\Scripts\conda.exe install -p D:/Program Files/anaconda3/envs/paddle_env 
+
+# 文字识别
+paddleocr --image_dir ./xjr_application/id_cards/card0.png --use_angle_cls true --use_gpu false 
+
+# 预测分类结果
+python ./tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.infer_img=./imgs/color.png
+
+python ./tools/infer_cls.py -c configs/cls/cls_mv3.yml -o Global.infer_img=./ppocr_img/id_cards/card1.png
+
+
+python ./tools/infer/predict_det.py --image_dir="./xjr_application/id_cards/card0.png" --det_model_dir="./xjr_application/model/ch_PP-OCRv3_det_infer/"
+
+
+
+
+
+
+
+

xjr_application/idCard2.py

@@ -0,0 +1,126 @@
+import cv2
+import base64
+import os
+import sys
+import copy
+
+sys.path.insert(0, ".")
+
+from tools.infer.utility import parse_args
+from tools.infer.predict_det import TextDetector
+
+
+def cv2_to_base64(image):
+    return base64.b64encode(image).decode('utf8')
+
+def merge_configs():
+    # deafult cfg
+    backup_argv = copy.deepcopy(sys.argv)
+    sys.argv = sys.argv[:1]
+    cfg = parse_args()
+
+    update_cfg_map = vars(read_params())
+
+    for key in update_cfg_map:
+        cfg.__setattr__(key, update_cfg_map[key])
+
+    sys.argv = copy.deepcopy(backup_argv)
+    return cfg
+
+class Config(object):
+    pass
+
+
+def read_params():
+    cfg = Config()
+
+    # params for text detector
+    cfg.det_algorithm = "DB"
+    # cfg.det_model_dir = "./inference/idCard2/ch_db_mv3_sfz/"
+    cfg.det_model_dir = "./output_inference/ch_db_mv3_sfz/"
+    # cfg.det_model_dir = "./inference/idCard2/det_r50_vd_db_sfz/"
+    cfg.det_resize_long = 960
+
+    # DB parmas
+    cfg.det_db_thresh = 0.3
+    cfg.det_db_box_thresh = 0.5
+    cfg.det_db_unclip_ratio = 2.0
+    cfg.use_dilation = False
+    cfg.det_db_score_mode = "fast"
+
+    # #EAST parmas
+    # cfg.det_east_score_thresh = 0.8
+    # cfg.det_east_cover_thresh = 0.1
+    # cfg.det_east_nms_thresh = 0.2
+
+    cfg.use_pdserving = False
+    cfg.use_tensorrt = False
+
+    return cfg
+
+
+#  身份证识别
+class IdCard(object):
+    # 初始化
+    def __init__(self, text_system, args):
+        self.text_system = text_system
+        self.score = 0.5
+        # 实例分割
+        # if args["idCard"]["accuracy"] == "accurate":
+        #     self.directory = "./inference/idCard/cascade_mask_rcnn_mobilenetv3_fpn_1x/"
+        # else:
+        #     self.directory = "./inference/idCard/mask_rcnn_mobilenetv3_fpn_1x/"
+
+        cfg = merge_configs()
+
+        cfg.use_gpu = args["use_gpu"]
+        if args["use_gpu"]:
+            try:
+                _places = os.environ["CUDA_VISIBLE_DEVICES"]
+                int(_places[0])
+                print("use gpu: ", args["use_gpu"])
+                print("CUDA_VISIBLE_DEVICES: ", _places)
+                cfg.gpu_mem = 8000
+            except:
+                raise RuntimeError(
+                    "Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
+                )
+        cfg.ir_optim = True
+        cfg.enable_mkldnn = args["enable_mkldnn"]
+
+        self.model = TextDetector(cfg)
+
+    def idCard(self, img):
+        dt_boxes, dt_labels, elapse = self.model(img, cls=True)
+
+        print(dt_boxes)
+        print(dt_labels)
+        new_results = {}
+
+        categorys = ["name", "sex", "nation", "birthday", "address", "number"]
+
+        if str(new_results) == '{}':
+            return ""
+
+        return new_results
+
+    def __call__(self, img=None):
+        return self.idCard(img)
+
+
+if __name__ == '__main__':
+    # from deploy.hubserving.ocr_system.module import OCRSystem
+    # text_system = OCRSystem({
+    #     "use_gpu": True,
+    #     "enable_mkldnn": False
+    # }).text_sys
+
+    module = IdCard(None, {
+        # "use_gpu": True,
+        "use_gpu": False,
+        "enable_mkldnn": False
+    })
+    # image = cv2.imread('E:\\dataset\\shenfenzheng\\images\\JPEGImages\\001.png')
+    img_path = './id_cards/card1.png'
+    image = cv2.imread(img_path)
+    res = module(img=image)

xjr_application/templates/index.html

@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>index</title>
+</head>
+<body>
+    <form action="/processing" method="POST" enctype="multipart/form-data">
+        <input type="file" name="image">
+        <button>OK</button>
+    </form>
+</body>
+</html>

xjr_application/templates/show_result.html

@@ -0,0 +1,10 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>Show image</title>
+</head>
+<body>
+    <img src="data:;base64,{{ img_stream }}">
+</body>
+</html>

xjr_application/xjr_application.py

@@ -0,0 +1,69 @@
+from paddleocr import PaddleOCR, draw_ocr
+import numpy as np
+from flask import Flask, request, jsonify, render_template
+from PIL import Image
+import requests
+import base64
+import io
+import cv2
+import time
+import json
+
+# # Paddleocr目前支持的多语言语种可以通过修改lang参数进行切换
+# # 例如`ch`, `en`, `fr`, `german`, `korean`, `japan`
+# ocr = PaddleOCR(use_angle_cls=True, lang="ch", ocr_version='PP-OCRv4')  # need to run only once to download and load model into memory
+# # img_path = './imgs/11.jpg'
+# img_path = './id_cards/card0.png'
+# result = ocr.ocr(img_path, cls=True)
+# print(result)
+# # for idx in range(len(result)):
+# #     res = result[idx]
+# #     for line in res:
+# #         print(line)
+#
+# # 显示结果
+# result = result[0]
+# print(len(result))
+# for line in result:
+#     print(line[1][0])
+# image = Image.open(img_path).convert('RGB')
+# boxes = [line[0] for line in result]
+# txts = [line[1][0] for line in result]
+# scores = [line[1][1] for line in result]
+# im_show = draw_ocr(image, boxes, txts, scores, font_path='./fonts/simfang.ttf')
+# im_show = Image.fromarray(im_show)
+# im_show.save('result.jpg')
+
+app = Flask(__name__)
+ocr = PaddleOCR(use_angle_cls=True, lang="ch", ocr_version='PP-OCRv4')
+
+@app.route('/')
+def hello_world():  # put application's code here
+    # return 'Hello World!'
+    return render_template('index.html')
+
+
+@app.route('/processing', methods=['POST'])
+def process():
+    file = request.files['image']  # 获取图像
+
+    img_pil = Image.open(file.stream)  # PIL读取图流
+    img_cv = cv2.cvtColor(np.array(img_pil), cv2.COLOR_RGB2BGR)  # PIL->cv2
+    result = ocr.ocr(img=img_cv, cls=True)
+    txts = [line[1][0] for line in result[0]]
+    json_demo = {'result': txts, 'len': len(result[0])}
+
+    # 返回，需要看实际情况返回字段
+    return json_demo  # 这个是把图片展示在前端
+
+# @app.route('/show')
+# def show_image():
+#     r = requests.get('https://s.cn.bing.net/th?id=OHR.CliffsEtretat_ZH-CN9911283373_UHD.jpg')
+#     # image = base64.b64encode(r.content).decode('ascii')
+#     image = base64.b64encode(r.content).decode()
+#     return render_template('show_image.html', img_stream=image)
+
+
+if __name__ == '__main__':
+    app.run(host='127.0.1.3', port=5555)
+