what is the difference between normal image and augmented image data as input to convolutional neural network ?? why augmented image is showing more accuracy ??

Question

arunnagiri murrugesan 2019-1-7

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/438566-what-is-the-difference-between-normal-image-and-augmented-image-data-as-input-to-convolutional-neura

编辑： Mahmoud Afifi 2020-5-7

what are the different types of augmentation of image ?

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Mahmoud Afifi 2020-5-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/438566-what-is-the-difference-between-normal-image-and-augmented-image-data-as-input-to-convolutional-neura#answer_430904

编辑：Mahmoud Afifi 2020-5-7

Data augmentation adds more variety to what the CNN sees during training. This augmentation could be a single pixel shit that introduces “new” data sample to the CNN. Of course more variety in training data increases the robustness of your model. But remember to use a realistic data augmentation that can represent expected conditions on the testing images. Check this Article that discusses this issue (it is mainly about color augmentation, but we can generalize this issue to other augmentation techniques).