Influence of Color Spaces for Deep Learning Image Colorization

Ballester, Coloma; Bugeau, Aurélie; Carrillo, Hernan; Clément, Michel; Giraud, Rémi; Raad, Lara; Vitoria, Patricia

doi:10.48550/arxiv.2204.02850

Cited by 3 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, for the automatic image colorization task, the YUV and CIELAB color spaces (the last introduced by the International Commission on Illumination—CIE—in 1976) are mostly preferred, covering the entire range of human color perception. As recently demonstrated by Ballester et al [ 65 ], it cannot be concluded that one color space is always preferable in colorization applications, but the performance depends on the type of input images. For our Hyper-U-NET methodology, the L*a*b space, also used in the other methods tested in this work ( Section 2.4 ), was selected for Hyper-U-NET, applying some modifications needed to handle the historical input images.…”

Section: Proposed Methodsmentioning

confidence: 99%

Colorizing the Past: Deep Learning for the Automatic Colorization of Historical Aerial Images

Farella¹,

Malek²,

Remondino³

2022

J. Imaging

View full text Add to dashboard Cite

The colorization of grayscale images can, nowadays, take advantage of recent progress and the automation of deep-learning techniques. From the media industry to medical or geospatial applications, image colorization is an attractive and investigated image processing practice, and it is also helpful for revitalizing historical photographs. After exploring some of the existing fully automatic learning methods, the article presents a new neural network architecture, Hyper-U-NET, which combines a U-NET-like architecture and HyperConnections to handle the colorization of historical black and white aerial images. The training dataset (about 10,000 colored aerial image patches) and the realized neural network are available on our GitHub page to boost further research investigations in this field.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Colorizing the Past: Deep Learning for the Automatic Colorization of Historical Aerial Images

Farella¹,

Malek²,

Remondino³

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…In the literature, three prior types lead to different colorization methods. Several surveys [7,1,3] provide a detailed overview of these approaches. In this work, we will focus on iColoriT: Towards Propagating Local Hint to the Right Region in Interactive Colorization by Leveraging Vision Transformer [14], one of the few hybrid approaches combining both color priors learned from a large dataset of images and color hints indicated by users.…”

Section: Introductionmentioning

confidence: 99%

A Brief Analysis of iColoriT for Interactive Image Colorization

García,

Randall,

Raad

2024

Image Processing on Line

View full text Add to dashboard Cite

This paper briefly describes and analyzes iColoriT, a hybrid colorization method based on a Vision Transformer that propagates user hints to relevant regions of a grayscale image while using color priors learned from a large image dataset. This approach gives users more control over color inference and shows a quick way to achieve results. Source CodeThe source code and documentation for this algorithm are available from the web page of this article 1 . Usage instructions are included in the README file of the archive. The authors' original method implementation is available here 2 . This is an MLBriefs article. The source code has not been reviewed!

show abstract

“…They make use of the image itself to promote the selfoptimization learning of the relationship between features and expression, which is fast and accurate. In order to improve the accuracy of deep learning object detection models, researchers are currently thinking about combining the deep learning method with color space conversion [13]. Liu et al [14] converted an original potato RGB image to the HSL, HSV, Lab, XYZ, and YCrCb color spaces and then created Mask R-CNN models for each color space to detect wilt plaque on leaves.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced YOLOv5 Model for Greenhouse Cucumber Fruit Recognition Based on Color Space Features

et al. 2022

View full text Add to dashboard Cite

The identification of cucumber fruit is an essential procedure in automated harvesting in greenhouses. In order to enhance the identification ability of object detection models for cucumber fruit harvesting, an extended RGB image dataset (n = 801) with 3943 positive and negative labels was constructed. Firstly, twelve channels in four color spaces (RGB, YCbCr, HIS, La*b*) were compared through the ReliefF method to choose the channel with the highest weight. Secondly, the RGB image dataset was converted to the pseudo-color dataset of the chosen channel (Cr channel) to pre-train the YOLOv5s model before formal training using the RGB image dataset. Based on this method, the YOLOv5s model was enhanced by the Cr channel. The experimental results show that the cucumber fruit recognition precision of the enhanced YOLOv5s model was increased from 83.7% to 85.19%. Compared with the original YOLOv5s model, the average values of AP, F1, recall rate, and mAP were increased by 8.03%, 7%, 8.7%, and 8%, respectively. In order to verify the applicability of the pre-training method, ablation experiments were conducted on SSD, Faster R-CNN, and four YOLOv5 versions (s, l, m, x), resulting in the accuracy increasing by 1.51%, 3.09%, 1.49%, 0.63%, 3.15%, and 2.43%, respectively. The results of this study indicate that the Cr channel pre-training method is promising in enhancing cucumber fruit detection in a near-color background.

show abstract

Influence of Color Spaces for Deep Learning Image Colorization

Cited by 3 publications

References 49 publications

Colorizing the Past: Deep Learning for the Automatic Colorization of Historical Aerial Images

Colorizing the Past: Deep Learning for the Automatic Colorization of Historical Aerial Images

A Brief Analysis of iColoriT for Interactive Image Colorization

An Enhanced YOLOv5 Model for Greenhouse Cucumber Fruit Recognition Based on Color Space Features

Contact Info

Product

Resources

About