Gray Scale Image Colorization for Human Faces
| Autor: | Sarika Zaware, Gauri Sangale, Vaidehi Patil, Vranda Gupta, Divya Pathak |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Artificial neural network
Computer science business.industry Computation ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Pattern recognition Autoencoder Convolutional neural network Grayscale Convolution Image (mathematics) Task (project management) Domain (software engineering) Computer vision Artificial intelligence business |
| Zdroj: | SSRN Electronic Journal. |
| ISSN: | 1556-5068 |
| DOI: | 10.2139/ssrn.3884916 |
| Popis: | Image colorization is an eclectic topic of research. Former approaches to the gray scale image colorization problem rely on manual methods with human intervention that produced some de-saturated results that are not likely to be true colorizations. To fully automate the process of colorization, enormous amount of computation power and datasets are required which is daunting. This paper proposes an approach to fully automate the task using an autoencoder model restricting our domain to just colorizing human faced images. This can be useful in colorizing old black and white pictures and movie snapshots. We used Convolution Neural Network (CNN) for colorization because of its ability to deal with image datasets. This approach includes pre-processing input images, model generation, training and post processing of output. The experimental results demonstrated that this method outperforms the state of art technique as far as human faces are concerned. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|