AdelaiDet
keras-ocr
AdelaiDet | keras-ocr | |
---|---|---|
4 | 4 | |
3,325 | 1,332 | |
0.2% | - | |
6.5 | 3.5 | |
2 months ago | 6 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AdelaiDet
-
FOSS self-hosted image-to-text gpu accelerated object recognition ? Is there anything on the table yet ?
https://github.com/amusi/awesome-object-detection https://mmdetection.readthedocs.io/en/latest/index.html https://github.com/thtrieu/darkflow https://github.com/OlafenwaMoses/ImageAI https://github.com/dmlc/gluon-cv https://github.com/aim-uofa/AdelaiDet/ https://github.com/aim-uofa/AdelaiDet/blob/master/configs/FCOS-Detection/README.md https://github.com/wizyoung/YOLOv3_TensorFlow
- Instance segmentation
-
[P] Object detection framework : Detectron2 VS MMDetection
There are also some nice methods built on Detectron2 in [AdelaiDet](https://github.com/aim-uofa/AdelaiDet).
-
how to recognize digits from this pics(i have many of them) so kindly suggest generic that can work for other similar images. I have searched alot for the source code on github but not found the correct solution. most of these solutions were incorrect while other were incomplete. Kindly help me :(
ABCNet
keras-ocr
- FLaNK Stack Weekly for 30 April 2023
-
Ask HN: Best pretrained OCR model for dashcam footage?
I'm trying to detect things like speed limits, stop signs, retail building signs from a relatively low quality dashcam. The video is 1440p, but the optics aren't great.
So far I've been using generic OCR models like [1] and [2], but the results aren't great.
[1] https://github.com/faustomorales/keras-ocr
-
Why do new architectures still use old models?
Yes, you should be able to do it by replacing the the backbone and training the other parts again. The results may be better or worse than you expected. See: https://github.com/faustomorales/keras-ocr/issues/113
-
How easy would it be/how would I go about implementing automated OCR + word count estimate after a file upload for a translation website?
There's plenty of OCR models around. If you'll have a Python server handling this, you can try keras-ocr. If you want to do this right in the browser, you can use a tflite model.
What are some alternatives?
CRAFT-pytorch - Official implementation of Character Region Awareness for Text Detection (CRAFT)
PaddleOCR - Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
mmocr - OpenMMLab Text Detection, Recognition and Understanding Toolbox
doctr - docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
mmpretrain - OpenMMLab Pre-training Toolbox and Benchmark
mmpose - OpenMMLab Pose Estimation Toolbox and Benchmark.
pandas-ai - Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.
TextRecognitionDataGenerator - A synthetic data generator for text recognition
Image2CAD - An application to translate raster image of CAD drawing sheet to a user editable DXF format.
gym_solo - A custom open ai gym environment for solo experimentation.