stef_buwalda/ProjectIOT
1
0
Fork 0
mirror of https://github.com/StefBuwalda/ProjectIOT.git synced 2025-10-29 18:59:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update yolomain.py

Browse Source 
Werkende OCR zit er nu in.
Nutteloze lines zijn weggehaald.
show image kan nog weg eventueel
This commit is contained in:
zoloko13
2025-06-12 10:51:40 +02:00
parent 78854fa84f
commit ea0669df61
1 changed files with 14 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

29
OCR YOLO11/yolomain.py
View File

@@ -1,37 +1,36 @@
from ultralytics import YOLO
from ultralytics.utils.downloads import safe_download
from ultralytics.utils.plotting import Annotator, colors
from PIL import Image
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
import os
os.chdir("C:/Users/celma/OneDrive - Hanze/School/periode 1.4/IOT/YOLO11/License Plate Recognition.v11i.yolov11")
crop_dir_name = "C:/Users/celma/OneDrive - Hanze/School/periode 1.4/IOT/YOLO11/License Plate Recognition.v11i.yolov11/test/crops"
if not os.path.exists(crop_dir_name):
os.makedirs(crop_dir_name)
model = YOLO("license_plate_detector.pt") # Loads the pre-trained YOLO11 model
model = YOLO("license_plate_detector.pt")
names = model.names
results = model.predict("test/images/000c.jpg", show=True, save=True)
img = Image.open("test/images/000c.jpg") # Load the original image using PIL
results = model.predict("test/images/000i.jpg", show=False, save=False)
img = Image.open("test/images/000i.jpg")
boxes = results[0].boxes.xyxy.cpu().tolist()
clss = results[0].boxes.cls.cpu().tolist()
# annotator = Annotator(results[0], line_width=2, example=names)
#print(results)
print(boxes)
if boxes is not None:
for box, cls in zip(boxes,clss):
# annotator.box_label(box, color=colors(int(cls), True), label=names(int(cls)))
crop_obj = boxes[int(box[1]):int(box[3]) + int(box[0]):int(box[2])]
cropped_img = img.crop(
(int(box[0]), int(box[1]), int(box[2]), int(box[3]))
)
save_path = os.path.join(crop_dir_name, "cropped_image.jpg")
cropped_img.save("cropped_image.jpg")
cropped_img.show()
cropped_img.show()
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-large-printed")
image = cropped_img.convert("RGB")
pixel_values = processor(images=image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(text)