Image colourisation using deep feature‐guided image retrieval. Issue 7 (29th April 2019)

• Record Type: Journal Article
• Authors: Chakraborty, Souradeep
• Is Part Of: IET image processing. Volume 13:Issue 7(2019)
• Page Start: 1130
• Page End: 1137
• Publication Date: 2019-04-29
• Subjects: image resolution -- learning (artificial intelligence) -- filtering theory -- image enhancement -- image colour analysis -- image retrieval; image colourisation -- deep feature‐guided image retrieval -- fully automated framework -- reference database -- similar retrieved images -- deep learning techniques -- colour transfer -- target greyscale image -- pixel level features -- colour enhancement -- pixel‐wise colour saturation -- original coloured images -- low‐contrast images -- Reinhard stain normalisation -- averaging technique -- joint bilateral filtering; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6169
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : In this study, the authors aim to colourise a greyscale image using a fully automated framework which retrieves similar images from a reference database and then transfers the colour from the most similar retrieved images to perform colourisation. Inspired by the recent success of deep learning techniques in extracting semantic information from images, they first use fc7 features from AlexNet to retrieve similar images from the reference database. Top‐ k retrieved images are considered for colour transfer to the target greyscale image, using various pixel level features. The images which result from the previous step are given a colour enhancement with Reinhard stain normalisation. They follow a pixel‐wise colour saturation based averaging technique to impart colour at pixel level. The final image is rectified using joint bilateral filtering. The resulting coloured images have a realistic appearance, similar in quality to the original coloured images. The proposed method outperforms several previous colourisation techniques, yielding superior performance both quantitatively and qualitatively. The method also enhances low‐contrast images.