Abstract: An information processing apparatus includes an index value calculation module and a parameter determination module. The index value calculation module calculates values of preset indexes for each of adjustment parameter sets to calculate regression coefficients which are used to derive a predicted value from past data. The parameter determination module selects an appropriate adjustment parameter set based on the index values calculated for each of the adjustment parameter sets and index values of neighborhood adjustment parameter sets with respect to the interested each adjustment parameter set.

Abstract: A facial validation sensor includes an imaging element, a validating unit and a feedback unit. The validating unit performs validation of an individual to be validated based on facial image data of the individual, imaged by the imaging element, and facial image data registered in advance. The feedback unit guides a face of the individual to be within an imaging range that is imaged by the imaging element. The feedback unit is an indicator providing unit that provides an indicator that is viewable from a specific direction within the imaging range that is imaged by the imaging element.

Abstract: When comparing a reference image and a registered image, a reference image is defined as a high-resolution image of the highest resolution and a first low-resolution image is generated on a lower level, and a second low-resolution image is generated on a lower level. Registered images are read one-at-a-time, feature regions are set in the hierarchical images of the registered images, and corresponding regions are found in the reference image through hierarchical searching from the low-resolution image towards the high-resolution image. An evaluation is made as to whether to select the registered image that has been read out, based on a similarity between the low-resolution hierarchical image, for example, a feature region of the hierarchical image of the registered image, and the corresponding region of the hierarchical image of the reference image, to narrow down the registered images to be compared to the reference image.

Abstract: When comparing a reference image and a registered image, a reference image is defined as a high-resolution image of the highest resolution and a first low-resolution image is generated on a lower level, and a second low-resolution image is generated on a lower level. Registered images are read one-at-a-time, feature regions are set in the hierarchical images of the registered images, and corresponding regions are found in the reference image through hierarchical searching from the low-resolution image towards the high-resolution image. An evaluation is made as to whether to select the registered image that has been read out, based on a similarity between the low-resolution hierarchical image, for example, a feature region of the hierarchical image of the registered image, and the corresponding region of the hierarchical image of the reference image, to narrow down the registered images to be compared to the reference image.