64 questions
0
votes
0
answers
48
views
Segmentation fault when initializing OCR on Raspberry Pi 5 (Python 3.13)
I'm encountering a segmentation fault when trying to initialize PaddleOCR on a Raspberry Pi 5 (8GB RAM) running Python 3.13 in a virtual environment. The error occurs during the model loading phase.
...
3
votes
2
answers
1k
views
PaddleOCR predict() method throws NotImplementedError
I'm trying to use PaddleOCR:
from paddleocr import PaddleOCR
from PIL import Image
# Initialize the OCR engine
ocr = PaddleOCR(use_textline_orientation=False, lang='es')
# Run OCR on an image path
...
- 61
3
votes
1
answer
283
views
PaddleOCR is leaking extracted data from a previous document
I've implemented an OCR queue using PaddleOCR and noticed that some documents are receiving the same extracted data as the previously processed document.
So far, this behaviour seems to be isolated to ...
- 4,969
Tooling
0
votes
2
replies
129
views
How to remove colors from image keeping black, white and gray
PaddleSharp is used to find orientation and get text form image below:
using Mat imgSrc = Mat.FromImageData(image);
PaddleRotationDetector detector = new(RotationDetectionModel....
- 28.3k
1
vote
1
answer
239
views
PP-OCRv5 lang="japan" Setting Outputs Chinese: Is This a Bug or a Feature?
I am currently using PP-OCRv5 with the PP-OCRv5_server_det model. I've set the language parameter to lang="japan" in an attempt to process Japanese text, but the output frequently contains ...
- 11
0
votes
0
answers
169
views
pm2 makes paddleocr models keep in loop when trying to start process
I have a FastAPI project that I'm trying to run on server. that project uses PaddleOCR, when I just run the project with:
fastapi run main.py
It runs normally and shows a ppocr log:
ppocr DEBUG: ...
1
vote
0
answers
365
views
PaddleOCR OCR analyzes Left-to-Right instead of Right-to-Left for Arabic- How to process RTL languages correctly?
I am using PaddleOCR with the Arabic language model (lang='ar') to perform OCR on Arabic images. While PaddleOCR correctly recognizes the Arabic characters, it processes the text in a Left-to-Right (...
0
votes
1
answer
303
views
Paddle OCR fail to extract single digit
I’m using Paddle OCR to extract prices from some products price tags, in most cases it give good results but I noticed that it fails to extract prices with single digit
When I edit the image and add ...
- 173
0
votes
0
answers
848
views
Paddle Ocr not detecting text when too much of the image is empty
I got a multitude of envelopes captured like in this screenshot (address hidden by me for confidentiality). For most of them Paddle OCR is working great. But for a couples it doesn't captures much. If ...
- 83
1
vote
0
answers
780
views
How do I finetune PaddleOCR's recognition and detection?
I've read countless articles and the official documentation explaining how to finetune Paddle but I keep running into problems. I find the documentation to also be vague. The default model works well ...
- 11
2
votes
0
answers
972
views
Segmentation Fault Error During PP-OCRv3 Model Training on GPU
I'm encountering a segmentation fault while training a text recognition model using the PP-OCRv3 configuration in PaddlePaddle. During my first attempt, I ran into an out-of-memory error on the GPU, ...
- 21
1
vote
0
answers
1k
views
RuntimeError: (PreconditionNotMet) Cannot Load cuDNN Shared Library in Docker Container with PaddleOCR
I am currently working on an OCR task using PaddleOCR within a Docker container. I am encountering the following error when trying to execute my application:
RuntimeError: (PreconditionNotMet) Cannot ...
- 31
1
vote
1
answer
1k
views
Paddle OCR Detection confidence level
I have a question regarding Paddle OCR detection model. Paddle OCR output results are the coordinates of the bounding boxes, recognized text and the confidence score, and from what I have researched ...
4
votes
2
answers
735
views
Paddle OCR not able to extract single digits from image
I am doing an image OCR using Paddle OCR. Below is the sample code I am using:
from paddleocr import PaddleOCR
import os
image_file = "3_496.png"
ocr = PaddleOCR(use_gpu=True)
image_path = ...
- 7,656
0
votes
0
answers
686
views
How to access or use PaddleOCR API for handwritten text purposes (this is for my mobile application)?
I'm a beginner building an Android mobile app which has a feature of detecting handwritten texts. I noticed that one of the good models available and is for free is the PaddleOCR. However, the Github ...
- 1