• vasupalli shyam kumar
• K.Tulasi Krishna Kumar

This paper presents a straight forward neural network approach for recognizing handwritten digits using convolution. Handwritten digit recognition is considered a challenging task for machine learning algorithms such as KNN, SVM, and SOM, due to the unique style of writing. The proposed method utilizes Convolutional Neural Networks (CNNs) [1] to an MNIST dataset [2]of 70,000 digits with 250 distinct forms of handwriting. The results show that the proposed method achieved 98.51% accuracy in predicting real-world handwritten digits with less than 0.1% loss on training with 60,000 digits, while 10,000 digits were held for validation. Overall, this study demonstrates the effectiveness of CNNs in improving handwritten digit recognition performance.

Convolution neural networks, MNIST dataset, TensorFlow, OCR, Segmentation, Cross-Validation

"IDENTIFING THE ACCURACY OF HAND WRITTEN DIGITS, USING MACHINE LEARING IN PYTHON", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.c607-c614, March-2023, Available :http://www.jetir.org/papers/JETIR2303268.pdf

"IDENTIFING THE ACCURACY OF HAND WRITTEN DIGITS, USING MACHINE LEARING IN PYTHON", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. ppc607-c614, March-2023, Available at : http://www.jetir.org/papers/JETIR2303268.pdf