My Final Project
Different people in the world write the digits in different ways. Identifying these handwritten digits and classifying these digits is a big issue. This project recognizes the handwritten digits using KE SNN algorithm.
Demo Link
One can try this at - https://api.alpes.ai/digit/
How I built it
The whole data of handwritten images are stored in the data set called MNIST. This database of handwritten digits has a training set of 60,000 examples and a test set of 10,000 examples. The MNIST data is collected from the large dataset called NIST. It is a subset of NIST. The digits in the dataset have been size-normalized and converted to fixed-size images. The images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field. In MNIST the train and test data files contain grayscale images of all the digits that are from zero to nine. For each digit the train and test data files are unique. Each image is 28 pixels in height and 28 pixels in width, for a total of 784 pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0 and 1. The trainset of MNIST data is used to train the non-iterative algorithm and then the model is used to test. This whole model is deployed as API.
Image Source - https://en.wikipedia.org/wiki/MNIST_database
Top comments (0)