TY - JOUR ID - 2099 TI - Automatic Grayscale Image Colorization using a Deep Hybrid Model JO - Journal of AI and Data Mining JA - JADM LA - en SN - 2322-5211 AU - Kiani, K. AU - Hematpour, R. AU - Rastgoo, R. AD - Electrical and Computer Engineering Faculty, Semnan University, Semnan, Iran. Y1 - 2021 PY - 2021 VL - 9 IS - 3 SP - 321 EP - 328 KW - Grayscale image colorization KW - deep learning KW - Convolutional neural network KW - Inception-v2 KW - Color space DO - 10.22044/jadm.2021.9957.2131 N2 - Image colorization is an interesting yet challenging task due to the descriptive nature of getting a natural-looking color image from any grayscale image. To tackle this challenge and also have a fully automatic procedure, we propose a Convolutional Neural Network (CNN)-based model to benefit from the impressive ability of CNN in the image processing tasks. To this end, we propose a deep-based model for automatic grayscale image colorization. Harnessing from convolutional-based pre-trained models, we fuse three pre-trained models, VGG16, ResNet50, and Inception-v2, to improve the model performance. The average of three model outputs is used to obtain more rich features in the model. The fused features are fed to an encoder-decoder network to obtain a color image from a grayscale input image. We perform a step-by-step analysis of different pre-trained models and fusion methodologies to include a more accurate combination of these models in the proposed model. Results on LFW and ImageNet datasets confirm the effectiveness of our model compared to state-of-the-art alternatives in the field. UR - https://jad.shahroodut.ac.ir/article_2099.html L1 - https://jad.shahroodut.ac.ir/article_2099_56d99dec486ae27ca1e71ba2853ea374.pdf ER -