Development of colorization of grayscale images using CNN-SVM
Nowadays, there is a growing interest in colorizing many grayscales or black and white images dating back to before the colored camera for historical and aesthetic reasons. Image and video colorization can be applied to historical images, natural images, astronomical photography. This paper proposes...
保存先:
| 主要な著者: | , , , , |
|---|---|
| フォーマット: | 図書の章 |
| 言語: | English English |
| 出版事項: |
Springer
2021
|
| 主題: | |
| オンライン･アクセス: | http://irep.iium.edu.my/88884/1/88884_Development%20of%20colorization%20of%20grayscale.pdf http://irep.iium.edu.my/88884/7/88884_Development%20of%20colorization%20of%20grayscale_SCOPUS.pdf http://irep.iium.edu.my/88884/ https://link.springer.com/book/10.1007%2F978-3-030-70917-4 |
| タグ: |
タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
|
| 要約: | Nowadays, there is a growing interest in colorizing many grayscales or black and white images dating back to before the colored camera for historical and aesthetic reasons. Image and video colorization can be applied to historical images, natural images, astronomical photography. This paper proposes a fully automated image colorization using a deep learning algorithm. First, the image dataset was selected for training and testing purposes. A convolutional neural network (CNN) was designed with several layers of convolutional and max pooling. Support Vector Machine (SVM) regression was used at the final stage. The proposed algorithm was implemented using Python with Keras and Tensorflow libraries in Google Colab. Results showed that the proposed system could predict the colored image from the training process's learning knowledge. A survey was then conducted to validate our findings. |
|---|