Centre de documentation
scientifique

Dépouillements

A learning-based approach to automatically evaluate the quality of sequential color schemes for maps / Taisheng Chen in Cartography and Geographic Information Science, Vol 48 n° 5 (September 2021)  

Public [article]  inCartography and Geographic Information Science > Vol 48 n° 5 (September 2021) . - pp 377-392 Titre : A learning-based approach to automatically evaluate the quality of sequential color schemes for maps Type de document : Article/Communication Auteurs : Taisheng Chen, Auteur ; Menglin Chen, Auteur ; A - Xing Zhu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 377-392 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Rédaction cartographique [Termes IGN] amélioration des couleurs [Termes IGN] apprentissage automatique [Termes IGN] charte de couleurs [Termes IGN] cohérence des couleurs [Termes IGN] contraste de couleurs [Termes IGN] couleur (rédaction cartographique) [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] palette de couleurs [Termes IGN] saturation de la couleur [Termes IGN] visualisation cartographique Résumé : (auteur) Color quality evaluation is key to judging map quality, which can improve data visualization and communication. However, most existing methods for evaluating map colors are tedious and subjective manual methods. In this paper, we study sequential color schemes, a widely used map color type and propose a learning-based approach for evaluating the color quality. The approach consists of two steps. First, we extract and characterize the cartographic factors for determining the quality of sequential color schemes, such as color order, color match, color harmony, color discrimination and color uniformity. Second, we present a model to predict the color quality based on AdaBoost, a type of ensemble learning algorithm with excellent classification performance and use these factors as input data. We conduct a case study based on 781 samples and train the AdaBoost-based model to predict the quality of sequential color schemes. To evaluate the model’s performance, we calculated the area under the receiver operating characteristic (ROC) curve (AUC). The AUC values are 0.983 and 0.977 on the training data and testing data, respectively. These results indicate that the proposed approach can be used to automatically evaluate the quality of sequential color schemes for maps, which helps mapmakers select good colors. Numéro de notice : A2021-642 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2021.1936184 Date de publication en ligne : 29/06/2021 En ligne : https://doi.org/10.1080/15230406.2021.1936184 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98335 [article]

Developing reliably distinguishable color schemes for legends of natural resource taxonomy-based maps / Virgil Vlad in Cartography and Geographic Information Science, Vol 48 n° 5 (September 2021)  

Public [article]  inCartography and Geographic Information Science > Vol 48 n° 5 (September 2021) . - pp 393 - 416 Titre : Developing reliably distinguishable color schemes for legends of natural resource taxonomy-based maps Type de document : Article/Communication Auteurs : Virgil Vlad, Auteur ; Mihai Toti, Auteur ; Sorina Dumitru, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 393 - 416 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Rédaction cartographique [Termes IGN] carte d'occupation du sol [Termes IGN] colorimétrie [Termes IGN] couleur (rédaction cartographique) [Termes IGN] couleur primaire [Termes IGN] lecture de carte [Termes IGN] légende cartographique [Termes IGN] palette de couleurs [Termes IGN] ressources naturelles [Termes IGN] Roumanie [Termes IGN] taxinomie [Termes IGN] visualisation cartographique Résumé : (auteur) The legends of natural resource taxonomy-based maps (e.g. soil, geological, geomorphological, vegetation, and land cover/land use) need many different distinguishable colors. The existing methods of color selection for map legends are based on the designer subjectivity, ensuring schemes having few colors. An analysis of the modeling and management of colors in digital applications has led to define an algorithm to calculate an objective colorimetric measure of color difference – “DE*ab” – based on the perceptually uniform color model CIELAB. The proposed method consists of a set of specific rules for developing hierarchically structured color schemes and a specific procedure for ensuring selection of a large number of reliably distinguishable colors, based on a color difference threshold. The accuracy of color reproduction in printing processes is also taken into account. The method has been applied to develop a standard of colors for soil maps. It contains 63 colors and has been used for developing a soil map having 41 standard colors. A user test of the method results proved that thresholds of 10 DE*ab units and 15 DE*ab units ensure obtaining acceptably distinguishable colors for displaying/printing maps by using high-quality, respectively, current devices. Three datasets that support the research are given. Numéro de notice : A2021-643 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1080/15230406.2021.1942218 Date de publication en ligne : 23/08/2021 En ligne : https://doi.org/10.1080/15230406.2021.1942218 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98340 [article]