An image such as a depth image of a scene may be received, observed, or captured by a device. A grid of voxels may then be generated based on the depth image such that the depth image may be downsampled. A background included in the grid of voxels may also be removed to isolate one or more voxels associated with a foreground object such as a human target. A location or position of one or more extremities of the isolated human target may be determined and a model may be adjusted based on the location or position of the one or more extremities.

A binary image of an input image is generated, and a character region within the binary image and a region surrounding each character are acquired as character segmentation rectangle information. A thinning process is executed on a region within the binary image which is identified based on the character segmentation rectangle information to acquire a thinned image. An edge detected image of the region identified based on the character segmentation rectangle information is acquired. Whether each character identified based on the character segmentation rectangle information is a character to be separated from a background by the binarization process or not is determined based on a result of a logical AND of the thinned image and the edge detected image.

The disclosure relates to a non-transitory computer-readable storage medium storing computer program instructions which, when executed by a processor, cause the processor to process image data defining an image of a retina to determine a location of an anatomical feature of the retina in the image by receiving the image data; calculating, for each of a plurality of pixels of the image data, a respective local orientation vector indicative of the orientation of any blood vessel present in the image; calculating a normalised local orientation vector for each of the plurality of pixels; operating on an array of accumulators, wherein each accumulator in the array is associated with a respective pixel of the image data; and determining the location of the anatomical feature in the image of the retina using the location of a pixel of the image data which is associated with an accumulator having accumulated an accumulated value.

Various embodiments herein each include at least one of systems, methods, and software to enable depth-based image element removal. Some embodiments may be implemented in a store checkout context, while other embodiments may be implemented in other contexts such as at price-checking kiosks or devices that may be deployed within a store or other retail establishment, a library at a checkout terminal, and the like. Some embodiments include removing elements of images based at least in part on depth data.

Provided are image inspection method and apparatus, and an ink jet printing apparatus that can highly accurately detect a stripe defect. An inspection image obtained by an imaging device imaging a printed matter printed by an ink jet printing apparatus including a line head is acquired. Each of at least one non-scanning direction linear structural element that is a linear structural element in a direction not parallel to a direction of scanning by the line head relative to a medium is used to execute morphology processing of a grayscale image to thereby smooth the inspection image to create a first smoothed inspection image (S22, S24). A stripe defect extending in the scanning direction is detected by using at least (1) one of the inspection image and a second smoothed inspection image created based on the inspection image and (2) the first smoothed inspection image.

In a case where noise reduction processing is performed on an image acquired by radiography, the noise reduction processing is prevented from being influenced by other image processing performed in advance. A structure determination unit determines a structure present in a target pixel of a preprocessed captured image. A first image processing unit performs a predetermined image processing based on a determination result of the structure present in the target pixel of the preprocessed captured image. A second image processing unit performs image processing different from the predetermined image processing on an image acquired through the predetermined image processing performed by the first image processing unit.

A document type recognition apparatus includes an image region separation unit, a smoothing unit, an edge enhancement unit, a histogram creation unit, and a document type recognition unit. The image region separation unit outputs a signal indicative of each region obtained by separating an input image into a character region and a pattern region. The smoothing unit performs smoothing processing to remove halftone dots of a particular number of lines or greater in the pattern region of the input image. The edge enhancement unit outputs an image subjected to edge enhancement processing depending on an amount of edge on an edge portion of the character region in the input image subjected to the smoothing processing. The histogram creation unit creates a histogram of the image subjected to the edge enhancement processing. The document type recognition unit recognizes a document type of the input image by utilizing the histogram.

A method for generating a labeled set of images for use in machine learning based stray light characterization for space-related optical systems. The method comprises (a) obtaining a set of images simulated for a space-related optical system, wherein the images of the set of images contain stray light simulated for the space-related optical system, (b) for each image of the set of images, identifying one or more clusters of light contained in the respective image and labeling the respective image by the one or more clusters of light, wherein the one or more clusters of light comprise at least one cluster of stray light, and (c) creating, based on the labeled images of the set of images, a plurality of new labeled images by applying transformations to the labeled images to generate an augmented set of labeled images.

Disclosed herein are systems and methods of estimating the autofluorescence (AF) signal and other non-target signals in each channel of a multi-channel image of a biological sample that is stained with one or more fluorescent labels. In some embodiments, the estimated autofluorescence signal can then be subtracted or masked from the multi-channel image. In some embodiments, the autofluorescence-removed multichannel image can then be use for further processing (e.g. image analysis, etc.).

Images of an unknown item picked from a store are processed to produce a cropped image. The cropped image is processed to produce a brightness/perspective corrected image, and the brightness/perspective corrected image is processed to produce a low-resolution final image. Image features of the low-resolution final image are extracted and compared against known item features for known items to identify an item code for a known item.