Hierarchical emotional color theme extraction

Liu, Shiguang; Luo, Huarong

doi:10.1002/col.21988

Cited by 28 publications

(16 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By using uniformly selected seeds, we were able to extract colors of all color categories in the image. We have tested different sizes of extracted colors (10,15,25,35,50) and come to the conclusion that 25 colors are sufficient so that no key color is missing and resulted colors are not too similar. The color space CAM02-UCS is based on CIECAM02 color appearance model and recommended for general applications.…”

Section: Gathering Human-extracted Themesmentioning

confidence: 99%

“…Based on their working principle the color-extracting methods can be divided into four main categories: histogram-based, 28,29 clusteringbased, 30,31 segmentation-based, 32,33 and data-driven methods. [34][35][36] Unfortunately, these methods do not always guarantee the extraction of the most prominent or visible colors of the image and have several limitations, such as the extraction of multiple perceptually similar colors or inability to detect colors in smaller regions. Only a few studies have focused on extracting prominent colors from the image.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Development of a machine learning model for extracting image prominent colors

Weingerl

Hladnik

Javoršek

2020

Color Research & Application

View full text Add to dashboard Cite

Although an image can consist of myriad different colors, due to the limitations of the human visual system and the mechanism of selective visual attention, only a limited number of them are prominent, that is, they stand out or are noticeable at first sight. In this article, a framework for building a model for extracting image prominent colors based on machine learning is presented. The model is learned on human‐extracted themes of prominent colors and uses numerous features, which were defined based on the properties of human visual system. For the purpose of this study, we constructed a database of images with their associated human‐extracted themes of prominent colors, which are open to the public and available to other researchers. The analysis of observers' data shows a high interobserver agreement on prominent color categories as well as high diversity of prominent colors. According to our results, the most influential factors on the perception of prominent colors are associated with color coverage (which should be adjusted with a saliency map), color properties—lightness and chroma, and diversity of colors. To the best of our knowledge, this is the first study on image prominent colors and first attempt to extract them with a model trained on the real data. The presented model has a high practical importance, since it can be used for extracting image colors in different scenarios, for example, for automatic color design, image categorization, as a descriptor in content‐based image retrieval, and image content analysis frameworks.

show abstract

Section: Gathering Human-extracted Themesmentioning

confidence: 99%

mentioning

confidence: 99%

Development of a machine learning model for extracting image prominent colors

Weingerl

Hladnik

Javoršek

2020

Color Research & Application

View full text Add to dashboard Cite

show abstract

“…Zhang et al investigated which colour difference formula is the most efficient to be used in image colour extraction algorithms. Based on theoretical analysis and experimental data, they came to the conclusion that CIE94 colour difference formula is most efficient at grouping colours with common clustering algorithms [38]. Different from the aforementioned algorithms, which only consider colour information, Liu and Luo presented a method that takes into account users' emotion and feeling about the image [39].…”

Section: Application Of Colour Harmony Theory 61 Image Colour Extracmentioning

confidence: 99%

Theory of Colour Harmony and Its Application

Weingerl

Javoršek

2018

Teh. vjesn.

View full text Add to dashboard Cite

The colour represents an essential element of visual and graphic communications. It plays an important role in the perception of visual design and it is significant for all participants in the process of planning, developing and promoting graphic products. Designers are interested in a psychological and presentational aspect of colours, while to the technologists the colour represents one of the most important quality attributes. The process of choosing colours that are harmonious, usable and efficient is complex. In addition, many designers have inadequate background knowledge of colour theory, which could help them with the selection of colours. As a result, designers usually spend a great deal of time and expend significant effort in choosing appropriate colour combinations. In this article, the importance of colour harmony and its application when extracting colours, rating and generating colour schemes is presented.

show abstract

“…As a result, we obtained a color palette with five colors that represent visually significant colors of an image. Before determining the number of clusters to consist an image color palette, we consulted several studies that investigated harmony of a color palette, [49][50][51] perception of image colors, 52,53 and image color adjustment utilizing a color palette. [18][19][20] As a mean to manipulate image colors, it seems like that a palette with 3 to 6 colors is frequently utilized.…”

Section: Step Cmentioning

confidence: 99%

Image color adjustment for harmony with a target color

Kim

Suk

2017

Color Research & Application

View full text Add to dashboard Cite

Although a number of methods have been developed for image adjustment in various applications, very little work has been done in the context of visual design. In this regard, this article introduces a novel and practical context of image color adjustment and develops a method to adjust an image for harmony with a target color. The experiment with designers revealed that designers made significant changes in hue dimension, and preferred to promote color similarity between the image and the target color. Based on insights from designers, we proposed a method to achieve a harmonious combination of an image and a color element by increasing the hue similarity between them. The result of a user test revealed that our method is particularly useful for images with nonliving objects but less effective for images involving human skin, foods, and so on. It is expected that the practical context investigated in this study can promote a variety of related studies that satisfy the tangible needs of industries and academia. K E Y W O R D Scolor transfer, harmony, hue similarity, image color adjustment, visual design | I NT ROD UCTI ONImage adjustment encompasses a wide range of techniques, such as photo quality enhancement, color adjustment, and image stitching. In particular, editing colors in an image has received extensive attention due to the compelling power of colors upon the aesthetics and impressions of an image. A number of methods have been proposed to modify the colors based on reference images, color palettes, and users' manual inputs. By transferring the colors of one image to another, these methods aim at resembling the look and/or style of given examples.In the practice of visual design, however, color adjustment is often performed with a distinct purpose in mind. For instance, designers are frequently asked to perform a series of design works related to a corporate identity or a brand. 1,2 In such tasks, the use of color is constrained by the brand identity. [3][4][5] Figure 1 shows design cases for international companies or organizations. As shown, a specific color or a color theme is dominantly used throughout the design works. In order to communicate their identity persuasively, it is important to use images that can create aesthetics and a visual harmony with the color. These examples imply a need for image adjustment in consideration of harmony with a given color. However, harmonious image adjustment has yet to be investigated, despite its practicality and usefulness in various applications.In this regard, we made a novel attempt to develop an algorithm that adjusts the colors of an image to achieve harmony with a target color. To achieve this goal, we first benchmarked the image adjustment process of designers and built a framework of our image adjustment method based on their insights. We developed its details by adopting the technical approaches of earlier color transfer studies. Finally, a user test was carried out to examine the performance of our method in the context of graphic design.Thro...

show abstract

Hierarchical emotional color theme extraction

Cited by 28 publications

References 26 publications

Development of a machine learning model for extracting image prominent colors

Development of a machine learning model for extracting image prominent colors

Theory of Colour Harmony and Its Application

Image color adjustment for harmony with a target color

Contact Info

Product

Resources

About