Visualization and Creation of Image using Processed Dataset and Python Model Architecture
Kumar Kaustubh, Kushala Kumari S, M. Kiran · 2023
Due to high data availability, it is difficult to classify/process images with higher speed and accuracy. The generation of semantic and human-face images has been a very important problem in artificial intelligence and computer vision. This project aims to develop a machine learning-based face generator using sketches as input. The training data consists of thousands of images of faces of different races, ages, and genders. The network is trained to learn the spatial relationship between facial features such as the eyes and the nose. The generator network consists of a feature extraction network and an undersampling and oversampling network, both of which use skip connections to reduce the number of layers without affecting network performance. To determine if the created face has the needed characteristics, the discriminator network is built. Experiments show that it can generate a wide range of faces with high fidelity. This work provides a foundation for further applications in various artificial intelligence and computer vision tasks. Compared to state-of-the-art image translation methods, the performance of the proposed network is excellent.