The DHCD (Devnagari Character Dataset) of handwritten digits. It consists 46 characters from क to ज्ञ and ० to ९. The characters were originally written in A4 paper which were scanned and cropped manually.
This is a dataset of Devanagari Script Characters. It comprises of 92000 images [32x32 px]. There are 1024 input features of pixel values in grayscale (0 to 255). The column "character" represents the Devanagari Character Name corresponding to each image.
- Numpy
- Pandas
- Matplotlib
- Seaborn
- Sckit-Learn
- Keras (Tensorflow Backend)
Acharya S., Pant A.K., Gyawali P.K.,”Deep Learning based large scale handwritten Devanagari Character Recognition” Proceeding of 9th International Conference on Software, Knowledge, Information Management & Applications. In Press.