Text Recognition in UAV Aerial Images

Shu, Wang; Wang, Dianwei; Han, Pengfei; Ren, Xingang; Xu, Zhijie

doi:10.1145/3488933.3488935

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper experiments use an animated sketch coloring pair dataset from Kaggle [1] . The dataset contains 17769 pairs of sketch color animated character images, of which the training set contains 14224 images and the test set includes 3545 images [19] . FID: It measures the similarity of two sets of images from the statistical aspect of the computer vision features of the original image, and is a measure of the distance between the real image and the feature vector that generated the image.…”

Section: The Composition Structure Of the Discriminator Network Modelmentioning

confidence: 99%

A Method of Coloring Sketch Images Based on Improving Generative Adversarial Networks

Zeng

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Based on the generative adversarial network, this paper proposes a method of colorizing gray images without supervision and applies it to the field of the automatic coloring of gray comic sketches to solve the problem of the high production cost of color comics and the large consumption of human resources. The method proposed in this paper mainly improves the classical generative adversarial network model in the following aspects: first, the idea of the residual network is added to the builder model and the discriminator model to ensure that the training of the model can develop in the right direction; secondly, add a gradient penalty term to the loss function of the discriminator to accelerate the convergence of the model and speed up the iteration; at the same time, the activation function in the original model is changed to the Mish activation function, so that the information flowing through the network model has higher accuracy and better generalization. This paper trained the model of the Anime Sketch Colorization Pair dataset [1] from Kaggle, and the final experimental results show that the method is practical and feasible.

show abstract

Section: The Composition Structure Of the Discriminator Network Modelmentioning

confidence: 99%