Litcius/Paper detail

CNN Model for Image Classification on MNIST and Fashion-MNIST Dataset

Shivam S. Kadam, Amol C. Adamuthe, Ashwini Patil

2020Journal of scientific research81 citationsDOIOpen Access PDF

Abstract

Paper presents application of convolutional neural network for image classification problem. MNIST and Fashion-MNIST datasets used to test the performance of CNN model. Paper presents five different architectures with varying convolutional layers, filter size and fully connected layers. Experiments conducted with varying hyper-parameters namely activation function, optimizer, learning rate, dropout rate and batch size. Results show that selection of activation function, optimizer and dropout rate has impact on accuracy of results. All architectures give accuracy more than 99% for MNIST dataset. Fashion-MNIST dataset is complex than MNIST. For Fashion-MNIST dataset architecture 3 gives better results. Review of obtained results and from literature shows that CNN is suitable for image classification for MNIST and Fashion-MNIST dataset.

Topics & Concepts

MNIST databaseArtificial intelligencePattern recognition (psychology)Image (mathematics)Computer scienceComputer visionDeep learningImage Processing and 3D Reconstruction