ATTRIBUTE FACTOR ANALYSIS METHOD, DEVICE, AND PROGRAM

摘要

The present invention provides a method for analyzing an attribute factor from training sample sets each of which comprises a group of reference image data and attribute data accompanying the reference image data. The attribute factor analysis method includes: a dividing step of dividing an image region of the reference image data constituting each of the training sample sets into a mesh in a predetermined sample size portion; a model constructing step of constructing a regression model by performing a sparse regression analysis from a reference sample set for each portion; a dependency calculation step of obtaining an attribute factor analysis result by calculating, with respect to each of the training sample sets and using the regression model, the dependency between an explanatory variable representing a feature quantity of the reference image data at each portion and an objective variable representing the attribute data; and a visualization step of visualizing and outputting the attribute factor analysis result.