PCGAN-CHAR: Progressively Trained Classifier Generative Adversarial Networks for Classification of Noisy Handwritten Bangla Characters

11 Aug 2019 Qun Liu Edward Collier Supratik Mukhopadhyay

Due to the sparsity of features, noise has proven to be a great inhibitor in the classification of handwritten characters. To combat this, most techniques perform denoising of the data before classification... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Datasets


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Document Image Classification Noisy Bangla Characters PCGAN-CHAR Accuracy 89.54 # 1
Document Image Classification Noisy Bangla Numeral PCGAN-CHAR Accuracy 96.68 # 1
Document Image Classification Noisy MNIST PCGAN-CHAR Accuracy 98.43 # 1
Image Classification Noisy MNIST (AWGN) PCGAN-CHAR Accuracy 98.43 # 1
Image Classification Noisy MNIST (Contrast) PCGAN-CHAR Accuracy 97.25 # 1
Image Classification Noisy MNIST (Motion) PCGAN-CHAR Accuracy 99.20 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet