Forty years of color quantization: a modern, algorithmic survey

Celebi, M. Emre

doi:10.1007/s10462-023-10406-6

Cited by 4 publications

(8 citation statements)

References 349 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantitative assessment remains to be one of the least explored aspects of CQ. 8 Most CQ studies employ pixelwise image fidelity metrics such as the mean squared error (MSE), or its variants such as the peak signal-to-noise ratio (PSNR), computed in the RGB color space. Recently, Ref.…”

Section: Quantitative Assessment and Discussionmentioning

confidence: 99%

“…• Sources: Wikimedia Commons (73), PxHere (23), and Kodak lossless true color image suite (4). • Categories: animals (18), food (17), miscellaneous (6), objects (23), people (8), places (11), plants (6), and vehicles (11). • Licenses: public domain (14), CC0 (25), CC BY (7), and CC BY-SA (54).…”

Section: Description Of the Datasetmentioning

confidence: 99%

“…7 Early CQ algorithms were mostly hierarchical, whereas modern CQ algorithms tend to be partitional. 8 Yet another classification scheme is based on whether or not the palette size is allowed to change during the CQ process. Static algorithms assume that the palette size is a constant to be specified by the user in advance, whereas dynamic algorithms compute the palette size automatically at run-time.…”

Section: Introductionmentioning

confidence: 99%

“…Despite the over four decades of research on CQ, there is currently no benchmark dataset on which CQ algorithms can be developed, tested, and compared. 8 Many CQ studies employ a subset of the USC-SIPI image database (Available at Ref. 14) or the Kodak lossless true color image suite (Available at Ref.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast, partitional algorithms find all the clusters simultaneously as a partition of the data without imposing a hierarchical structure on the data 7 . Early cq algorithms were mostly hierarchical, whereas modern cq algorithms tend to be partitional 8 . Yet another classification scheme is based on whether or not the palette size is allowed to change during the cq process.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

cq100: a high-quality image dataset for color quantization research

Celebi

Delgado

2023

J. Electron. Imag.

View full text Add to dashboard Cite

.Color quantization (cq) is a classical image processing operation that reduces the number of distinct colors in a given image. Although the idea of cq dates back to the early 1970s, the first true cq algorithm, median-cut, was proposed later in 1980. Since then, hundreds of publications have investigated the topic of cq, proposing dozens of algorithms. A vast majority of these publications demonstrate their results on small datasets, containing a handful of images of mixed quality. Furthermore, the reproducibility of cq research is often limited due to the use of private test images or public test images with multiple non-identical copies on the World Wide Web or restrictive licenses. To address these problems, we curated a large, diverse, and high-quality dataset of 24-bit color images called cq100 and released it under a permissive license. We present an overview of cq100 and demonstrate its use in comparing cq algorithms.

show abstract

Section: Quantitative Assessment and Discussionmentioning

confidence: 99%

Section: Description Of the Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

cq100: a high-quality image dataset for color quantization research

Celebi

Delgado

2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

A comparative study of color quantization methods using various image quality assessment indices

Pérez-Delgado,

Celebi

2024

Multimedia Systems

View full text Add to dashboard Cite

This article analyzes various color quantization methods using multiple image quality assessment indices. Experiments were conducted with ten color quantization methods and eight image quality indices on a dataset containing 100 RGB color images. The set of color quantization methods selected for this study includes well-known methods used by many researchers as a baseline against which to compare new methods. On the other hand, the image quality assessment indices selected are the following: mean squared error, mean absolute error, peak signal-to-noise ratio, structural similarity index, multi-scale structural similarity index, visual information fidelity index, universal image quality index, and spectral angle mapper index. The selected indices not only include the most popular indices in the color quantization literature but also more recent ones that have not yet been adopted in the aforementioned literature. The analysis of the results indicates that the conventional assessment indices used in the color quantization literature generate different results from those obtained by newer indices that take into account the visual characteristics of the images. Therefore, when comparing color quantization methods, it is recommended not to use a single index based solely on pixelwise comparisons, as is the case with most studies to date, but rather to use several indices that consider the various characteristics of the human visual system.

show abstract

Impressions of Guangzhou city in Qing dynasty export paintings in the context of trade economy: a color analysis of paintings based on k-means clustering algorithm

Ao,

Ye,

et al. 2024

Herit Sci

View full text Add to dashboard Cite

Study on export paintings has gradually shifted from artistic form to cultural connotation, with an emphasis on cross-cultural communication. Although the economic and social dimensions of their artistic value have been explored, few studies delve into the connection between Qing-era Guangzhou's trade culture and its color characteristics. Utilizing the HSV color model and the k-means algorithm, this study analyzes the color traits of 35 export paintings depicting Guangzhou landscapes and works from the "Thirteen-houses commercial zone," revealing Qing-era Guangzhou's urban impressions and Sino-Western artistic interactions. Key findings include: (1) the hue pixel range in Guangzhou export paintings primarily spans 10°–60° and 120°–250° (dominated by red and yellow-green), saturation values range from 1–82% (primarily low saturation), and value values range from 11–94% (with a wide variance); (2) compared to traditional Chinese paintings, the transformation from pure color (正色) → inter-color (间色) → projection-perspective and light source illustrates both the blending of Eastern and Western artistic cultures and a diminishing influence of traditional ceremonial culture; (3) in contrast with Western artworks, some Guangzhou export paintings display a Westernization trend in color structures, evident in vibrant colors and stark chiaroscuro contrasts. As bespoke art commodities, export paintings microscopically reflect Guangzhou's unique trade culture and socio-political dynamics. The shifts in color schemes, integration of realistic styles, and human-centric characteristics unveil the intricate interplay between quasi-realism and transcendental aesthetics in Qing-era Guangzhou, as well as the nuanced dynamics between social capital and art within a global trade network.

show abstract

Forty years of color quantization: a modern, algorithmic survey

Cited by 4 publications

References 349 publications

cq100: a high-quality image dataset for color quantization research

cq100: a high-quality image dataset for color quantization research

A comparative study of color quantization methods using various image quality assessment indices

Impressions of Guangzhou city in Qing dynasty export paintings in the context of trade economy: a color analysis of paintings based on k-means clustering algorithm

Contact Info

Product

Resources

About