Academic Journal
Employing Neural Style Transfer for Generating Deep Dream Images
| العنوان: | Employing Neural Style Transfer for Generating Deep Dream Images |
|---|---|
| المؤلفون: | Lafta R. Al-Khazraji, Ayad R. Abbas, Abeer S. Jamil |
| المصدر: | ARO-The Scientific Journal of Koya University, Vol 10, Iss 2 (2022) |
| بيانات النشر: | Koya University, 2022. |
| سنة النشر: | 2022 |
| المجموعة: | LCC:Technology LCC:Science |
| مصطلحات موضوعية: | Deep dream, Gradient ascent, Gram matrix, Neural style transfer, Technology, Science |
| الوصف: | In recent years, deep dream and neural style transfer emerged as hot topics in deep learning. Hence, mixing those two techniques support the art and enhance the images that simulate hallucinations among psychiatric patients and drug addicts. In this study, our model combines deep dream and neural style transfer (NST) to produce a new image that combines the two technologies. VGG-19 and Inception v3 pre-trained networks are used for NST and deep dream, respectively. Gram matrix is a vital process for style transfer. The loss is minimized in style transfer while maximized in a deep dream using gradient descent for the first case and gradient ascent for the second. We found that different image produces different loss values depending on the degree of clarity of that images. Distorted images have higher loss values in NST and lower loss values with deep dreams. The opposite happened for the clear images that did not contain mixed lines, circles, colors, or other shapes. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2410-9355 2307-549X |
| Relation: | http://aro.koyauniversity.org/index.php/aro/article/view/1051; https://doaj.org/toc/2410-9355; https://doaj.org/toc/2307-549X |
| DOI: | 10.14500/aro.11051 |
| URL الوصول: | https://doaj.org/article/b9067a6fa8ad423796ca11c186ff86e3 |
| رقم الانضمام: | edsdoj.b9067a6fa8ad423796ca11c186ff86e3 |
| قاعدة البيانات: | Directory of Open Access Journals |
| تدمد: | 24109355 2307549X |
|---|---|
| DOI: | 10.14500/aro.11051 |