Combining Deep Learning and Multi-class Discriminant Analysis for Granite Tiles Classification

Filisbino, Tiene A.; Giraldi, Gilson A.; Simo, Lucas; Thomaz, Carlos Eduardo

doi:10.1109/wvc.2017.00011

Cited by 4 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PLSA was used to learn the data in different models to obtain the corresponding semantic topic distribution, and then the two models were fused through adaptive asymmetric algorithm to obtain better classification effect. Then, Filisbino [12] proposed a learning method combining mixed generation and discriminant model. It used continuous PLSA to model the visual features of images to reduce the impact of cluster granularity on classification performance, and adopted an integrated classifier chain to classify multi-labeled images.…”

Section: Introductionmentioning

confidence: 99%

Modified generative adversarial networks for image classification

Zhao

2021

Evol. Intel.

View full text Add to dashboard Cite

In the image classification task, the existing neural network models have insufficient ability to characterize the features of the classified objects, which leads to the problem of low recognition accuracy. Therefore, we propose a modified Generative Adversarial Networks (GAN) for image classification. Based on the traditional generative adversarial network, By constructing multiple generation models and introducing collaboration mechanism, the generation models can learn from each other and make progress together in the training process to improve the fitting ability of the model for real data and further improve the classification quality. Finally, a generative adversarial network is designed to generate the occlusion samples, so that the model has good robustness for the occlusion objects recognition. The Top-1 error rate is used as the evaluation index. The experiments are conducted on the public data sets containing Cifar10, Cifar100, ImageNet2012. The comparison experiment results show that the proposed method can improve the feature representation ability of the GAN and improve the accuracy of image classification. The average accuracy is higher than 90% and the error rate is lower than 1.0%.

show abstract

Section: Introductionmentioning

confidence: 99%