Fujitsu Corporation

Yusuke Nonaka

Eigo Segawa

A detection apparatus includes a memory and a processor coupled to the memory. The processor configured to determine a position of each of a plurality of partial images relative to the wide-angle image, to extract, from among the plurality of partial images, a pair of partial images that are consecutive in an image-capturing order, that do not have an overlapping portion, and at least one of which includes an image of a damaged portion, to detect a region of the outside of the partial image to which a damaged portion is estimated to be continuous, as an image-capturing omission candidate region, to determine the image-capturing omission candidate region as an image-capturing omission region, in a case where the image-capturing omission candidate region is included in none of the other partial images, and to issue, based on the position, a notification of a position corresponding to the image-capturing omission region.

Apparatus and method for damage detection and image capture of damage without omission

An image processing method causing an image processing device to execute a process including: obtaining a first image and a second image captured at different timings for an identical inspection target by passing through an imaging range of an image sensor row; extracting respective feature points of the first image and the second image; associating the feature points of the first image and the feature points of the second image with each other; estimating a conversion formula to convert the feature point of the second image to the feature point of the first image based on a restraint condition of a quadratic equation, in accordance with respective coordinates of three or more sets of the feature points associated between the first image and the second image; and converting the second image into a third image corresponding to the first image based on the estimated conversion formula.

Image processing device, method and program to align two images

An image processing method includes: identifying a dark region by binarizing an image captured using an imaging device; generating a line image of the dark region by thinning the dark region; identifying a first multiple pairs of pixels that are included in a pixel group forming the generated line image and are separated from each other by a predetermined threshold or more; calculating a first variance of gradients of lines connecting the respective pairs in the first plurality of pairs; identifying a second plurality of pairs of pixels that are included in the pixel group forming the generated line image and are separated from each other by values smaller than the predetermined threshold; calculating a second variance of gradients of lines connecting the respective pairs in the second plurality of pairs; and evaluating the dark region based on the first variance and the second variance.

Growing community of inventors

Kawasaki, Japan

Yusuke Nonaka