Classified data multi-view visual coloring method and system based on similar significance

Abstract

The invention provides a classifiied data multi-view visual coloring method and system based on similar saliency. The method comprises the following steps: receiving classification data; projecting the classified data to a visual space, and obtaining position information of the classified data; measuring the separation degree between each class of data based on the position information, and calculating change information of the same class on different classification data based on similarity measurement; recombining the color palettes or randomly selecting a plurality of colors from the discretized color space as initial solutions, and searching an approximate optimal solution based on a simulated annealing algorithm by combining the separation degree and change information between classes to generate the color palettes; and rendering the classification data based on the optimal palette. The simulated annealing algorithm is adopted, the given palette can be rapidly redistributed or the palette can be directly generated, meanwhile, distribution in data and changes between the data are considered, color difference measurement is combined, the similar significance of the changed area is improved, the intra-class distinction degree is kept, and the efficiency of visual analysis is improved.

Description

technical field

[0001] The disclosure belongs to the technical field of data visualization, and in particular relates to a multi-view visual coloring method and system for classified data based on similarity salience. Background technique

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] Comparison is an indispensable task in the process of data analysis and visualization. We often need to find a class that has changed in multiple labeled data, and this comparison task is usually completed in the form of a side-by-side view. Applicable methods are histograms, line charts, and scatter plots, and regardless of the visualization, each class is represented by a unique color. Color is important for people to detect differences, however, finding an appropriate coloring scheme remains a challenging and unsolved problem. To address this problem, we looked for a solut...

Images