initial commit

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
\ No newline at end of file

app.py

+import uvicorn
+from fastapi import FastAPI
+from scripts.core.services.Text_Extraction_Service import router
+from scripts.config.app_configurations import *
+
+app = FastAPI()
+app.include_router(router)
+
+if __name__ == "__main__":
+    uvicorn.run("app:app", host=HOST, port=PORT)

conf/application.conf

+[LOG]
+log_level=INFO
+base_path=logs/
+file_name=structure
+handlers=console,file
+logger_name=structure
+
+
+[SERVICE]
+host=localhost
+port=8200
+
+[PATH]
+model_path = scripts/utility/model/yolov8l_r1_r2_lp_best.pt

requirements.txt

+# YOLOv5 requirements
+# Usage: pip install -r requirements.txt
+
+# Base ----------------------------------------
+matplotlib>=3.2.2
+numpy>=1.18.5
+opencv-python>=4.1.1
+Pillow>=7.1.2
+PyYAML>=5.3.1
+requests>=2.23.0
+scipy>=1.4.1
+#torch>=1.7.0  # see https://pytorch.org/get-started/locally/ (recommended)
+#torchvision>=0.8.1
+tqdm>=4.64.0
+# protobuf<=3.20.1  # https://github.com/ultralytics/yolov5/issues/8012
+
+# Logging -------------------------------------
+tensorboard>=2.4.1
+# clearml>=1.2.0
+# comet
+
+# Plotting ------------------------------------
+pandas>=1.1.4
+seaborn>=0.11.0
+
+# Export --------------------------------------
+# coremltools>=6.0  # CoreML export
+# onnx>=1.9.0  # ONNX export
+# onnx-simplifier>=0.4.1  # ONNX simplifier
+# nvidia-pyindex  # TensorRT export
+# nvidia-tensorrt  # TensorRT export
+# scikit-learn<=1.1.2  # CoreML quantization
+# tensorflow>=2.4.1  # TF exports (-cpu, -aarch64, -macos)
+# tensorflowjs>=3.9.0  # TF.js export
+# openvino-dev  # OpenVINO export
+
+# Deploy --------------------------------------
+# tritonclient[all]~=2.24.0
+
+# Extras --------------------------------------
+ipython  # interactive notebook
+psutil  # system utilization
+thop>=0.1.1  # FLOPs computation
+# mss  # screenshots
+# albumentations>=1.0.3
+# pycocotools>=2.0  # COCO mAP
+# roboflow
+
+python-dotenv==0.21.0
+fastapi==0.86.0
+python-multipart==0.0.5
+click==8.1.3
+h11==0.14.0
+uvicorn==0.19.0
+ultralytics
+paddleocr==2.7.0.3
+paddlepaddle==2.5.2
+

scripts/config/app_configurations.py

+import configparser
+
+config = configparser.ConfigParser()
+config.read('conf/application.conf')
+
+LOG_LEVEL = config.get('LOG', 'log_level')
+LOG_BASEPATH = config.get('LOG', 'base_path')
+LOG_FILE_NAME = LOG_BASEPATH + config.get('LOG', 'file_name')
+LOG_HANDLERS = config.get('LOG', 'handlers')
+LOGGER_NAME = config.get('LOG', 'logger_name')
+
+HOST = config.get('SERVICE', 'host')
+PORT = config.getint('SERVICE', 'port')
+MODEL_PATH = config.get('PATH', 'model_path')
\ No newline at end of file

scripts/config/app_constants.py

+class BaseName:
+    baseurl = "/Text_Extraction"
+
+
+
+
+class TEXT_EXTRACT:
+    text = BaseName.baseurl + "/value"
+class Image:
+    upload="/upload_image"
+
+
+

scripts/core/handler/Text_Extraction_Handler.py

+from paddleocr import PaddleOCR
+from ultralytics import YOLO
+import torch
+import cv2
+from scripts.config.app_configurations import *
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+# print(f'Using device: {device}')
+def load_ocr_model():
+    ocr = PaddleOCR(use_angle_cls=True, lang='en')
+    return ocr
+
+def load_yolo_model():
+    model = YOLO(MODEL_PATH).to(device)
+    return model
+
+
+def predict(img_path, ocr, yolo_model):
+    img = cv2.imread(img_path)
+    results = yolo_model.predict(img, iou=0.7)
+    if results:
+        r1_txt = None
+        r2_txt = None
+
+        for r in results:
+
+            # annotator = Annotator(img)
+
+            boxes = r.boxes
+            for box in boxes:
+                b = box.xyxy[0]  # get box coordinates in (top, left, bottom, right) format
+                # print("bb:  ",b.tolist())
+                x1 = int(b[0])
+                y1 = int(b[1])
+                x2 = int(b[2])
+                y2 = int(b[3])
+                w = abs(x2 - x1)
+                h = abs(y2 - y1)
+
+                cv2.rectangle(img, (x1, y1), (x2, y2), (255, 0, 0), 1)
+
+                # lp = img[max(y1 - 30, 0):min(y1+h + 30, img.shape[0]), max(x1 - 30, 0):min(x1+w + 30, img.shape[1])]
+
+                lp  = img[y1:y1 + h, x1:x1 + w]
+
+                c = box.cls
+
+                # print("class:   ", c)
+                # annotator.box_label(b, model.names[int(c)])
+
+                # img = annotator.result()
+                # cv2.imshow('YOLO V8 Detection', cv2.resize(img, (900, 600)))
+                if int(c) == 0:
+                    result = ocr.ocr(lp, cls=True)
+                    for idx in range(len(result)):
+                        res = result[idx]
+                        text_x = 10
+                        text_y = 30
+                        if res:
+
+                            for ind, line in enumerate(res):
+                                # print("line")
+                                # print(line)
+
+                                text_tuple = line[1]
+                                if r1_txt is None:
+                                    r1_txt = text_tuple[0]
+                                    print("R1  TEXT:   ", r1_txt)
+                                text_conf = text_tuple[1]
+                elif int(c) == 1:
+
+                    result = ocr.ocr(lp, cls=True)
+                    for idx in range(len(result)):
+                        res = result[idx]
+                        text_x = 10
+                        text_y = 30
+                        if res:
+
+                            for ind, line in enumerate(res):
+                                # print("line")
+                                # print(line)
+
+                                text_tuple = line[1]
+                                if r2_txt is None:
+                                    r2_txt = text_tuple[0]
+                                    print("R2   TEXT:   ", r2_txt)
+                                text_conf = text_tuple[1]
+                            # cv2.putText(lp, txt, (text_x , text_y + ind*50), cv2.FONT_HERSHEY_SIMPLEX , 1, (255, 0, 0), 2, cv2.LINE_AA)
+
+                # cv2.imshow('detected LPR', lp)
+                # cv2.waitKey(0)
+                #
+
+        if r1_txt is not None and r2_txt is not None:
+            LP = f"{r1_txt}  {r2_txt}"
+
+            # print("LP:  ", LP)
+            return LP
+
+    return "Image Not Clear"
+    # result = ocr.ocr(img_path, cls=False,det=True,rec=True)[0]
+    # txts = [line[1][0] for line in result]
+
+
+
+

scripts/core/services/Text_Extraction_Service.py

+from fastapi import APIRouter
+
+from fastapi import File
+import cv2
+import numpy as np
+import io
+from scripts.core.handler.Text_Extraction_Handler import load_ocr_model,load_yolo_model, predict
+from scripts.logging.application_logging import logger
+from scripts.config.app_constants import TEXT_EXTRACT
+
+ocr = load_ocr_model()
+yolo_model = load_yolo_model()
+router = APIRouter()
+
+
+@router.post(TEXT_EXTRACT.text)
+def extract_license_number(file: bytes = File(...)):
+    try:
+        stream = io.BytesIO(file)
+        image = np.asarray(bytearray(stream.read()), dtype="uint8")
+        image = cv2.imdecode(image, cv2.IMREAD_COLOR)
+        cv2.imwrite("test.jpg", image)
+        image_path = "test.jpg"
+
+        text = predict(image_path, ocr, yolo_model)
+        logger.info("text detected")
+
+        return text
+    except Exception as e:
+        logger.error("Error is :{}".format(e))
+

scripts/logging/application_logging.py

+import logging.handlers
+import os
+import sys
+import time
+from logging import StreamHandler
+
+from scripts.config import app_configurations
+
+LOG_HANDLERS = app_configurations.LOG_HANDLERS
+log_level = app_configurations.LOG_LEVEL
+log_file = os.path.join(app_configurations.LOG_FILE_NAME + "_" + time.strftime("%Y%m%d") + '.log')
+
+logger = logging.getLogger(app_configurations.LOGGER_NAME)
+logger.setLevel(log_level)
+
+formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s  - %(filename)s - %(module)s: %(funcName)s: '
+                              '%(lineno)d - %(message)s')
+
+if 'console' in LOG_HANDLERS:
+    # Adding the log Console handler to the logger
+    console_handler = StreamHandler(sys.stdout)
+    console_handler.setFormatter(formatter)
+    logger.addHandler(console_handler)
+
+# if 'file' in LOG_HANDLERS:
+#     # Adding the log file handler to the logger
+#     file_handler = logging.FileHandler(log_file)
+#     file_handler.setFormatter(formatter)
+#     logger.addHandler(file_handler)
\ No newline at end of file