Color Version Research Articles

Image Colorization

Abstract: Image colorization is a complex and challenging task in computer vision, with numerous applications in art, entertainment, restoration, and more. This project aims to develop an automated image colorization system leveraging the power of deep learning techniques. The primary objective is to train a deep neural network model capable of accurately and semantically colorizing grayscale images, reproducing natural and visually appealing colour distributions. Our approach utilizes Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) to learn the intricate relationships between grayscale images and their corresponding colour versions. The project involves the following key steps: Data Collection and Preprocessing, Model architecture, Training, Evaluation, Application. The project's outcome is expected to provide a powerful and versatile tool for automating image colorization tasks, offering high-quality results while preserving the artistic intent of the original images. The fusion of deep learning and computer vision techniques in this project exemplifies the potential for artificial intelligence to revolutionize image processing and creative industries.

Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques

Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate cancer diagnosis. Stain variation between hospitals hampers the performance of CBHIR tools. This paper explores the effects of color normalization (CN) in a recently proposed CBHIR approach to tackle this issue. In this paper, three different CN techniques were used on the CAMELYON17 (CAM17) data set, which is a breast cancer data set. CAM17 consists of images taken using different staining protocols and scanners in five hospitals. Our experiments reveal that a proper CN technique, which can transfer the color version into the most similar median values, has a positive impact on the retrieval performance of the proposed CBHIR framework. According to the obtained results, using CN as a pre-processing step can improve the accuracy of the proposed CBHIR framework to 97% (a 14% increase), compared to working with the original images.

Deep Learning-Based Image Colorization using AI

Abstract -This project aims to explore the application of deep learning techniques in image colorization using artificial intelligence (AI). Leveraging convolutional neural networks (CNNs) and generative adversarial networks (GANs), our objective is to develop a robust system capable of accurately and efficiently adding color to grayscale images. By training the model on a diverse dataset of grayscale images paired with their corresponding color versions, we aim to create a colorization tool that can replicate human-like color choices and produce visually appealing results. The proposed methodology involves preprocessing the dataset, designing and training the deep learning model, and evaluating its performance on test datasets. The anticipated outcome is a user-friendly image colorization tool that can be integrated into various applications, enhancing the visual experience and productivity of users. keywords: Deep Learning, Image Colorization, Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), Artificial Intelligence (AI), Grayscale Images..

Relationships between colorization and pseudo-colorization of monochrome images

This paper investigates the relationship between colorization and pseudo-colorization techniques for converting grayscale images to color. Colorization strives to create visually believable color versions of monochrome images, either replicating the original colors or generating realistic, alternative color schemes. In contrast, pseudo-colorization maps grayscale intensities to pre-defined color palettes to improve visual appeal, enhance content understanding, or aid visual analysis. While colorization is an ill-posed problem with infinitely many RGB solutions, pseudo-colorization relies on mapping functions to deterministically assign colors. This work bridges these techniques by exploring the two following operations: first - deriving pseudo-color from colorized images - this allows for creating stylized or abstract representations from existing colorizations, and second - enriching color diversity in pseudo-colored images - this enhances visual appeal and attractiveness of pseudo-colored images. The paper emphasizes the centrality of decolorization (rgb-to-gray) models in both processes. It focuses on the theoretical underpinnings of these problems but complements them with illustrative examples for clarity.

Bounds on piercing and line-piercing numbers in families of convex sets in the plane

A family of sets has the (p,q) property if among any p members of it some q intersect. It is shown that if a finite family of compact convex sets in R2 has the (p+1,2) property then it is pierced by ⌊p2⌋+1 lines. A colorful version of this result is proved as well. As a corollary, the following is proved: Let F be a finite family of compact convex sets in the plane with no isolated sets, and let F′ be the family of its pairwise intersections. If F has the (p+1,2) property and F′ has the (r+1,2) property, then F is pierced by (⌊r2⌋2+⌊r2⌋)p points when r⩾2, and by p points otherwise. The proofs use the topological KKM theorem.

Developing and testing front-of-pack nutrition labels in India: An experimental study

The most populous country in the world, India, is experiencing a nutrition transition that involves rapidly increasing prevalence of unhealthy packaged foods. To assist consumers in making healthier packaged food choices, the Government of India is in the process of designing and implementing a new front-of-pack nutrition labelling system. The aim of this study was to provide insights into the types of labels that may be most effective across the diverse Indian population. A multi-method data collection process was employed that involved 16 focus groups (n = 112 adult participants) and a survey administered to 1,270 adults. The assessed outcome variables were objective understanding, food choice, and perceptions of labels. The five front-of-pack nutrition labels tested in the experimental survey were 2-colour and 3-colour versions of the Multiple Traffic Lights label, a colour version of the Health Star Rating label, a smiley face version of the Nutri-Score label, and red Warning Labels. All five assessed front-of-pack nutrition labels produced favourable effects for objective understanding, choice, and perception outcomes, but the 2-colour Multiple Traffic Lights label performed best across both objective understanding and choice outcomes. The results highlight the importance of including colour as an interpretation aid in the new front-of-pack nutrition label to be introduced in India.

Yellow-green emitting CaGa2S4:Eu2+ phosphor: an application for enhancing the luminous flux of the white light emitting diodes

The <span lang="EN-GB">optimal spectral characteristics and photometric qualities in white-emitting light-emitting diodes (WLEDs) featuring red-emitting LEDs instead of phosphor (pc/R-WLEDs) were determined using the luminescent efficiency (LE) theory. The color quality scale (Rf) is higher than 97K for correlating color temperature (CCTs) ranging between 2700K and 6500K. We first identified genuine pc/R-WLEDs having Rf levels at 96–97, LE levels at 120–124 lm/W with CCT levels at 2969K, 4468K, 5682K, as well as 6558K with the utilization of all four-color phosphors: blues (448 nm), reddish (650 nm) LEDs, greenish (507 nm), and yellowish (586 nm). When compared to phosphorus-converted white-emitting LEDs (pc-WLEDs) and quantum dots white-emitting LEDs (QD-WLEDs), the pc/R-WLEDs, rather than the QD-WLED, would make better representatives of improved color version, notably in the reduced color temperatures, and could eventually replace current pc-WLEDs</span>.

Automatic, Early Color-Specific Neural Responses to Object Color Knowledge.

Some familiar objects are associated with specific colors, e.g., rubber ducks with yellow. Whether and at what stage neural responses occur to these color associations remain open questions. We recorded frequency-tagged electroencephalogram (EEG) responses to periodic presentations of yellow-associated objects, shown among sequences of non-periodic blue-, red-, and green-associated objects. Both color and grayscale versions of the objects elicited yellow-specific responses, indicating an automatic activation of color knowledge from object shape. Follow-up experiments replicated these effects with green-specific responses, and demonstrated modulated responses for incongruent color/object associations. Importantly, the onset of color-specific responses was as early to grayscale as actually colored stimuli (before 100ms), the latter additionally eliciting a conventional later response (approximately 140-230ms) to actual stimulus color. This suggests that the neural representation of familiar objects includes both diagnostic shape and color properties, such that shape can elicit associated color-specific responses before actual color-specific responses occur.

The False King Olaf and His Necklace of Letters

The False King Olaf and His Necklace of Letters

Validation of the open biological negative image set for a Portuguese population: Comparing Japanese and Portuguese samples and an exploration of low-order visual properties of the stimuli.

Recently, Shirai and Watanabe Royal Society Open Science, 9(1), 211128 (2022) developed OBNIS (Open Biological Negative Image Set), a comprehensive database containing images (primarily animals but also fruits, mushrooms, and vegetables) that visually elicit disgust, fear, or neither. OBNIS was initially validated for a Japanese population. In this article, we validated the color version of OBNIS for a Portuguese population. In study 1, the methodology of the original article was used. This allowed direct comparisons between the Portuguese and Japanese populations. Aside from a few emotional classification mismatches between disgust, fear, or neither-related images, we found that arousal and valence relate distinctively in both populations. In contrast to the Japanese sample, the Portuguese reported increased arousal for more positive valenced stimuli, suggesting that OBNIS images elicit positive emotions in the Portuguese population. These results showed important cross-cultural differences regarding OBNIS. In study 2, a methodological change was introduced: instead of the three classification options used originally (fear, disgust, or neither), six basic emotions were used (fear, disgust, sadness, surprise, anger, happiness), and a "neither" option, to confirm whether some of the originally "neither-related" images are associated with positive emotions (happiness). Additionally, the low-order visual properties of images (luminosity, contrast, chromatic complexity, and spatial frequency distribution) were explored due to their important role in emotion-related research. A fourth image group associated with happiness was found in the Portuguese sample. Moreover, image groups present differences regarding the low-order visual characteristics, which are correlated with arousal and valence ratings, highlighting the importance of controlling such characteristics in emotion-related research.

Line Transversals in Families of Connected Sets in the Plane

We prove that if a family of compact connected sets in the plane has the property that every three members of it are intersected by a line, then there are three lines intersecting all the sets in the family. This answers a question of Eckhoff [Discrete Comput. Geom., 9 (1993), pp. 203--214], who proved that, under the same condition, there are four lines intersecting all the sets. In fact, we prove a colorful version of this result under weakened conditions on the sets. Three sets $A,B,C$ form a tight triple if $\textrm{conv}(A\cup B)\cap \textrm{conv}(A\cup C)\cap \textrm{conv}(B\cap C)\neq \emptyset.$ This notion was first introduced by Holmsen, who showed that if $\mathcal{F}$ is a family of compact convex sets in the plane in which every three sets form a tight triple, then there is a line intersecting at least $\frac{1}{8}|\mathcal{F}|$ members of $\mathcal{F}$. Here we prove that if $\mathcal{F}_1,\dots,\mathcal{F}_6$ are families of compact connected sets in the plane such that every three sets, chosen from three distinct families $\mathcal{F}_i$, form a tight triple, then there exists $1\le j\le 6$ and three lines intersecting every member of $\mathcal{F}_j$. In particular, this improves $\frac{1}{8}$ to $\frac{1}{3}$ in Holmsen's result.

Using Paper Texture for Choosing a Suitable Algorithm for Scanned Document Image Binarization.

The intrinsic features of documents, such as paper color, texture, aging, translucency, the kind of printing, typing or handwriting, etc., are important with regard to how to process and enhance their image. Image binarization is the process of producing a monochromatic image having its color version as input. It is a key step in the document processing pipeline. The recent Quality-Time Binarization Competitions for documents have shown that no binarization algorithm is good for any kind of document image. This paper uses a sample of the texture of the scanned historical documents as the main document feature to select which of the 63 widely used algorithms, using five different versions of the input images, totaling 315 document image-binarization schemes, provides a reasonable quality-time trade-off.

Digitalization of visual discrimination threshold and acceptable tolerance of color depth by psychophysical experiments

AbstractColor depth is of great importance to both dyes and dyeing. The assessments of properties such as color fastness, relative dye strengths require dyed fabric to be adjusted to a specific depth level. However, the study of discrimination threshold and acceptable tolerance of color depth is limited. In this study, we attempted to investigate them. Acceptability (Pass/Fail) psychophysical visual experiments were performed twice by 16 normal color version observers on approximately 1206 samples for 6 standard depths in 3 hues, yielding approximately 40,000 visual assessment data points. The color depth formula, Yang3, which performed best in linearity to color depth in a previous study, was selected to calculate the color depth values YCD3 of the samples. The calculated and the visual data were bridged statistically. Experimental results show that the average discrimination threshold and acceptable tolerance of color depth are approximately 0.45 and 2.15 in YCD3, respectively. Furthermore, the details of different hues, lighter and deeper, male and female perspectives were analyzed and discussed. The Yang3 formula exhibited uniformity at different standard depths, as expected.

Total Aortic Arch Replacements With a 4 Branched Frozen Elephant Trunk (FET) Graft in Acute Aortic Dissection (DeBakey type I)

Total Aortic Arch Replacements With a 4 Branched Frozen Elephant Trunk (FET) Graft in Acute Aortic Dissection (DeBakey type I)

Repair of Kommerell's Diverticulum and Aberrant Subclavian Arteries: Classification of the Five Groups in Declining Frequency and Their Operative Approaches

Repair of Kommerell's Diverticulum and Aberrant Subclavian Arteries: Classification of the Five Groups in Declining Frequency and Their Operative Approaches

Blake and Exhibitions, 2020

2020 exhibitions placed Blake within artistic traditions of drawing in The Artful Line at the Harris and of wood engraving in Scene through Wood at the Ashmolean. His role within a surrealist genealogy was reinterpreted in British Surrealism at Dulwich Picture Gallery, which took the International Surrealist Exhibition of 1936 as a starting point and measured its impact on British surrealists since then. Facsimiles of his Gray watercolors were the inspiration for contemporary poets in The Bard: William Blake at Flat Time House. While the Tate retrospective reconstructed Blake’s coordinates through a very detailed account of the artisanal, artistic, and commercial communities around him in his several London locations, The Bard rooted Blake in Peckham, reenergizing creative and critical psychogeographic approaches. Trianon Press facsimiles were put to different uses, prompting reflection on the role of reproduction as a medium that can extend the circulation of Blake and bypassing the conservation restrictions that limit the exposure of works and require intervals between loans, as well as other conditions relating to the loan of originals. As noted, unbound Trianon facsimiles facilitated a dialogue with contemporary poetic practice at Flat Time House. The National Gallery of Canada’s William Blake, 1757–​1827: Illustrated Books used them to juxtapose originals and copies, enabling comparisons between monochrome and color versions and between technologies of print and reproduction, while also documenting the archival practice of complementing originals with reproductions.

48.2: Invited Paper: Full Color Video Electrowetting E‐paper Display

E‐paper technology has evolved slowly since the introduction of monochrome electrophoretic displays. Grayscale electrophoretic displays are still limited to 16 levels of grey and update speed has not significantly improved. Color versions are either dark or even slower to update. The key to breaking this impasse lies in a technology that can provide fast switching, and provide a sufficiently large, transmissive aperture. We have built a multilayer electrowetting display, providing acceptable resolution (648 × 480) for a 6″, 262k color video e‐paper display.

A Mélange of Diameter Helly-Type Theorems

A Helly-type theorem for diameter provides a bound on the diameter of the intersection of a finite family of convex sets in $\mathbb{R}^d$ given some information on the diameter of the intersection of all sufficiently small subfamilies. We prove fractional and colorful versions of a long-standing conjecture by Bárány, Katchalski, and Pach. We also show that a Minkowski norm admits an exact Helly-type theorem for diameter if and only if its unit ball is a polytope and prove a colorful version for those that do. Finally, we prove Helly-type theorems for the property of “containing $k$ colinear integer points.”

Invertible Image Decolorization.

Invertible image decolorization is a useful color compression technique to reduce the cost in multimedia systems. Invertible decolorization aims to synthesize faithful grayscales from color images, which can be fully restored to the original color version. In this paper, we propose a novel color compression method to produce invertible grayscale images using invertible neural networks (INNs). Our key idea is to separate the color information from color images, and encode the color information into a set of Gaussian distributed latent variables via INNs. By this means, we force the color information lost in grayscale generation to be independent of the input color image. Therefore, the original color version can be efficiently recovered by randomly re-sampling a new set of Gaussian distributed variables, together with the synthetic grayscale, through the reverse mapping of INNs. To effectively learn the invertible grayscale, we introduce the wavelet transformation into a UNet-like INN architecture, and further present a quantization embedding to prevent the information omission in format conversion, which improves the generalizability of the framework in real-world scenarios. Extensive experiments on three widely used benchmarks demonstrate that the proposed method achieves a state-of-the-art performance in terms of both qualitative and quantitative results, which shows its superiority in multimedia communication and storage systems.

Сфрагістичні пам’ятки Мізоцького скарбу та гераль­дика князів Острозьких другої половини XIV ст.

Dated by the late 1370s, the Mizoch Treasures include unique sphragistic artefacts. Alongside the anonymous signet ring featuring a daw image used by Ruthenian boyars in the first half of the 14th century, the other two matrixes include legends and a family coat of arms. One of the matrixes, made in the mid-1300s, belonged to a Kostiantyn, a person not mentioned in any other sources. Yet, the owner of the third seal was identified. It belonged to Yuriy Danylovych, Prince of Kholm (1370-1377). His name and title were indicated in the legend, and, in the field of his seal, a version of the princely family of Ostrozky’s arms was embossed. The seals of Yuriy’s father, Danylo (1366), and brother, Fedor (1385), had the shapes of a star and two crescents on them. Given the modified layout of shapes on prince Yuriy’s seal, we assume that Yuriy was Fedor’s younger brother because, in the Ruthenian heraldry of that time, modifications of the father’s arms were typical for younger sons. A colour version of Yuriy’s arms is found in manuscript copies of one of the oldest heraldic works of Western Europe – Castilian ‘Book of Knowledge’ (1385).