Commit History
-
Update README.md
Verified signature079e710 -
Update README.md
Verified signaturef7ca653 -
Update README.md
Verified signature81dee76 -
Update README.md
Verified signature0548df5 -
Update README.md
Verified signature693a14a -
Update README.md
Verified signatureda9bd21 -
Upload PersianDigitOCR.keras
Verified signaturea1c3e7d -
Delete persian_digit_model.keras
Verified signaturee20e1ce -
Update README.md
Verified signature33dfa4e -
Update README.md
Verified signaturec44e289 -
Upload persian_digit_model.keras
Verified signature812436b -
Create README.md
Verified signature# PersianDigitOCR ## Overview PersianDigitOCR is a deep learning model designed for recognizing handwritten Persian (Farsi) digits (۰-۹) from images. Built by fine-tuning the MobileNetV2 architecture pre-trained on ImageNet, this model achieves a validation accuracy of 99.75% on a subset of the HODA dataset. It is optimized for 96x96 pixel grayscale images and outputs Persian digit characters using Unicode mappings (U+06F0 to U+06F9). - **Pipeline Tag**: `image-classification` - **Date**: October 08, 2025 ## Model Details - **Base Model**: MobileNetV2 (from [google/mobilenet_v2_1.0_224](https://huggingface.co/google/mobilenet_v2_1.0_224)) - **Input**: Grayscale images resized to 96x96 pixels - **Output**: Predicted digit as a Persian Unicode character (e.g., '۰' for 0) - **Training Data**: Subset of 20,000 images from the HODA dataset (80% training, 20% validation) ## Usage Loading the Model Load the model using TensorFlow: from tensorflow.keras.models import load_model model = lo…3238a65 -
initial commit
Verified signature6e347a4