Colorizing gray level images by using wavelet filters
Source of Publication
2019 IEEE 10th GCC Conference and Exhibition, GCC 2019
© 2019 IEEE. This paper discusses a new algorithm to produce colored version of gray scale natural still images. This algorithm employs artificial neural network (ANN) to predict RGB channels using the Discrete Wavelet Transform (DWT). A group of natural color images are used to train three ANNs. The trained networks estimate low resolution RGB layers of the gray scale image which are the best match to the trained images. The colored version of the image is produced form the predicted RGB layers and information form grayscale image. The performances of the new algorithm are analyzed subjectively and objectively using the peak signal to noise and Structural Similarity, as well as it is compared to similar algorithm based on discrete cosine transform. Acceptable colorized images were obtained from different still images.
Institute of Electrical and Electronics Engineers Inc.
Color images, Colorization, Discrete cosine transform artificial neural network, Discrete wavelet transform, Image processing, Peak signal to noise ratio, Still images
Taher, F.; Darweesh, M.; and Al-Ahmad, H., "Colorizing gray level images by using wavelet filters" (2019). All Works. 969.
Indexed in Scopus