Nec Corporation

Ge Medical Systems Global Technology Company, LLC

Takami Sato

Kota Iwamoto

Soma Shiraishi

Yu Nabeto

Katsumi Kikuchi

Ruihan Bao

Shin Norieda

Ryota Mase

Yoshinori Saida

Ryoma Oami

Yuzo Senda

Kyota Higa

Yasufumi Hirakawa

Takahiro Kimoto

Toshiyuki Nomura

Naotake Fujita

Takato Ozawa

Kouichi Ueda

Katsuhiko Takahashi

Takao Goto

Makoto Yoshimoto

Makoto Terao

Ryosuke Sakai

Seiichi Kitagawa

Tomokazu Kaneko

The present invention provides a registration system () including: a placement member () being a plate-shaped member that transmits light, or being a plate-shaped member having a hole penetrating from a front to a back; a first camera () that captures a product () placed on the placement member () from a front side of the placement member (); a second camera () that captures the product () placed on the placement member () from a back side of the placement member (); and a processing apparatus () that registers, in association with identical product identification information, a first image in which the first camera () captures the product () and a second image in which the second camera () captures the product ().

Registration system, processing device, and processing method

The present invention provides a processing apparatus () including: an acquisition unit () that acquires a plurality of images, captured by a plurality of cameras, of a product held by a customer with a hand; a detection unit () that detects an object from each of the plurality of images; a positional information generation unit () that generates positional information indicating a position in the image, for the each detected object; a product kind-related information generation unit () that generates product kind-related information that determines a product kind, for the each detected object; an extraction unit () that extracts a group of a plurality of objects which satisfies conditions with each other, the conditions being related to the positional information and the product kind-related information; and a product recognition result output unit () that outputs a product recognition result for the each extracted group.

Processing apparatus, processing method, and non-transitory storage medium

An image acquisition unit () acquires a recognition processing image. A recognition unit () recognizes a product in the recognition processing image based on an estimation model. A registration unit () registers a result of the recognition in recognized product information. An output unit () outputs a result of the recognition. A correction reception unit () receives an input for correcting a result of the recognition. A correction unit () changes a result of the recognition to a result of the recognition after a correction, and also stores correction information in which a result of the recognition after a correction and the recognition processing image are associated with each other. A learning unit () performs relearning by using the recognition processing image stored as the correction information and updates the estimation model, when a number of the recognition processing image stored exceeds a predetermined value.

Processing system, processing method, and non-transitory storage medium

A product detection apparatus () includes an acquisition unit (), an image processing unit (), and an output unit (). The acquisition unit () acquires a plurality of images (one example of a first image) generated by an image capture unit () in association with a date and a time when the image is generated. These plurality of images are generated at different timings from each other. The image processing unit () detects a state (hereinafter, described as a first state) in which a new product is present on a product shelf () continuously for a reference time or longer by processing the plurality of images. The output unit () performs a first output when the first state is detected. The first output indicates that a product () has been returned to the product shelf () after the product () is taken out of the product shelf () by a customer.

Product detection apparatus, product detection method, and non-transitory storage medium

An article determination apparatus () is used with two image capture units (). One image capture unit (), an article shelf (), and the other image capture unit () are arranged in this order. The acquisition unit () acquires images generated by the two image capture units (). The image processing unit () generates first size data and second size data by processing the images acquired by the acquisition unit (). The first size data and the second size data indicate the size of an area in which an article is captured in an image generated by one image capture unit () and by the other image capture unit (), respectively. The determination unit () determines that an estimation result of the article name of the article by image processing is correct when a relation between the first size data and the second size data satisfies a criterion.

Article determination using image processing

An installation assistance apparatus () includes a first image capture unit and a second image capture unit that are placed in such a way as to face each other in a plan view, an acquisition unit () acquiring a first image from the first image capture unit, a detection unit () detecting a position of at least part of the second image capture unit in the first image by processing the first image, a determination unit () determining whether the position of the second image capture unit satisfies a criterion, and an output processing unit () causing a determination result by the determination unit () to be output.

Installation assistance apparatus, installation assistance method, and non-transitory computer-readable storage medium

An image acquisition unitacquires a plurality of images. The plurality of images include an object to be inferred. An image cut-out unitcuts out an object region including the object from each of the plurality of images acquired by the image acquisition unit. An importance generation unitgenerates importance information by processing the object region cut out by the image cut-out unit. The importance information indicates the importance of the object region when an object inference model is generated, and is generated for each object region, that is, for each image acquired by the image acquisition unit. A learning data generation unitstores a plurality of object regions cut out by the image cut-out unitand a plurality of pieces of importance information generated by the importance generation unitin a learning data storage unitas at least a part of the learning data.

Generating learning data from important, cut-out object regions

The present invention provides a processing apparatus () including: a web product image acquisition unit () acquiring a web product image publicly available in a web page determined based on a predetermined search condition; a product identification information acquisition unit () acquiring product identification information of a product indicated by the web product image; and a registration unit () registering the web product image and the product identification information in association with each other in a product database.

Disclosed is a display condition analysis device which is capable of analyzing the display conditions of products. This display condition analysis device is provided with: a product recognition means for recognizing, from a display image taken of products on display, the products in the display image; and a display condition analysis means for analyzing, on the basis of the positions of the recognized products, the display conditions of the products on display.

Display condition analysis device, display condition analysis method, and program recording medium

A housing device () includes a housing portion (), a light source (), and an optical sensor (). The housing portion () includes a holding body (). An article is housed in the housing portion (). The holding body () extends in one direction. The light source () is attached to the holding body () along the one direction. The light source () applies light toward at least a part of a space (S) located on a side of the holding body () with respect to the one direction of the holding body (), a front of the space (S), and a back of the space (S). The optical sensor () is attached to the holding body (). At least a part of a visual field of the optical sensor () faces in at least a part of the space (S), the front of the space (S), and the back of the space (S).

Housing device

An object recognition device () includes a holding body (), a light source (), and an optical sensor (). The holding body () extends in one direction. The light source () is attached to the holding body () along the one direction. The light source () applies light toward at least a part of a space (S) located on a side of the holding body () with respect to the one direction of the holding body (), a front of the space (S), and a back of the space (S). The optical sensor () is attached to the holding body (). At least a part of a visual field of the optical sensor () faces in at least a part of the space (S), the front of the space (S), and the back of the space (S).

Object recognition device

The present invention provides a processing apparatus () including a product database management unit () that registers a registration target product in a product database, and a special information management unit () that, when a similar-appearance product being similar in appearance to the registration target product at a predetermined level or more is registered in the product database, registers both the registration target product and the similar-appearance product as first processing target products requiring first processing, and registers information associating the registration target product and the similar-appearance product.

Processing apparatus, and accounting apparatus

Provided is a technology for recording effective data, as a result of inspection on a to-be-inspected object. This inspection assistance device is provided with: a reception unit that receives information about a to-be-inspected object; an acquisition unit that acquires image data captured by an imaging device; and a recording control unit that, in the case when the imaging time of the image data falls within a prescribed time range based on the time at which the information was received being set as a reference, and when the to-be-inspected object indicated by the received information coincides with the to-be-inspected object recognized from the image data, records the information pertaining to the result of inspection on the to-be-inspected object and the information about the to-be-inspected object in association with each other.

Growing community of inventors

Tokyo, Japan

Takami Sato