Mrityunjoy Gain¹, Md Arifur Rahman¹, Rameswar Debnath¹, Mrim M. Alnfiai², Abdullah Sheikh³, Mehedi Masud³, Anupam Kumar Bairagi^1,*

Computer Systems Science and Engineering, Vol.46, No.1, pp. 1059-1077, 2023, DOI:10.32604/csse.2023.034809 - 20 January 2023

Abstract Colorization is the practice of adding appropriate chromatic values to monochrome photographs or videos. A real-valued luminance image can be mapped to a three-dimensional color image. However, it is a severely ill-defined problem and not has a single solution. In this paper, an encoder-decoder Convolutional Neural Network (CNN) model is used for colorizing gray images where the encoder is a Densely Connected Convolutional Network (DenseNet) and the decoder is a conventional CNN. The DenseNet extracts image features from gray images and the conventional CNN outputs a * b * color channels. Due to a large number of desaturated… More >

Pradeep K. Majhi¹, Rifat Azam¹, Richa Kothari^2,*, Naveen Kumar Arora¹, V. V. Tyagi³

Energy Engineering, Vol.119, No.1, pp. 419-427, 2022, DOI:10.32604/EE.2022.016973 - 22 November 2021

Abstract Dyes are an integral part of the dying industry and have significantly resulted in environmental pollution by altering the standard water quality after their discharge into the water bodies. The culprits behind the altered water quality are the pretreatment chemicals used during dying manufacturing processes. Various advanced treatment methods using conventional and advanced treatment options including solar energy have been put forth by researchers for the treatment of the dying effluents but, these methods have not proved significantly considerable. Therefore, the present study intends to check the efficiency of solar parabolic trough collector for treating… More >

Hui Li¹, Wei Zeng^1,*, Guorong Xiao², Huabin Wang¹

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 841-846, 2020, DOI:10.32604/iasc.2020.010118

Abstract Recent progress on image colorization is substantial and benefiting mostly from the great development of the deep convolutional neural networks. However, one type of object can be colored by different kinds of colors. Due to the uncertain relationship between the object and color, the deep neural network is unstable and difficult to converge during the training process. In order to solve this problem, this paper proposes an instance-aware automatic image colorization algorithm, which uses the semantic features of the object instance as prior knowledge to guide the deep neural network to do the colorization task. More >