Image colourisation using deep feature‐guided image retrieval

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.

Tourism image classification based on convolutional neural network SqueezeNet——Taking Slender West Lake as an example

“…The research of computer vision in digital image is mainly divided into two modules: semantic perception and geometric attribute. Semantic perception includes image classification [ 12 ], object detection [ 13 ], image segmentation [ 14 ], image retrieval [ 15 ], etc. Geometric properties include 3D modeling [ 16 ], binocular vision [ 17 ] and augmented reality [ 18 ].…”

Feature matching of remote‐sensing images based on bilateral local–global structure consistency

“…Image feature matching plays a critical role in the field of computer vision as it aims to accurately establish correspondences between feature points across two or more images of the same scene [1]. Feature matching for remote sensing images holds significant value in various domains such as image fusion, change detection, environmental monitoring, map updating, image retrieval [2,3], and image mosaic [4]. Image feature matching technology refers to the process of identifying and comparing similar features between two or more images.…”