Olympus Corporation

Olympus Optical Company, Ltd.

Osaka Prefecture University Public Corporation

Yukihito Furuhashi

Takao Shibasaki

Hiroshi Matsuzaki

Akito Saito

Akio Kosaka

Yuichiro Akatsuka

Takeo Asano

Taiji Mine

Koichi Kise

Masakazu Iwamura

Kazuto Noguchi

Takahiro Kashiwagi

Takumi Toyama

Takayuki Hondo

According to an embodiment, an arithmetic method includes accepting an input of image data, detecting a representative position of a characteristic portion from the image data the input of which has been accepted, acquiring a user instructed position in the image data, calculating a position difference indicating a difference between the detected representative position and the acquired user instructed position, and selecting the representative position of the characteristic portion as a target portion if the calculated position difference is smaller than a predetermined first threshold and selecting the user instructed position as a target portion if the position difference is not smaller than the first threshold.

Arithmetic method, imaging apparatus, and storage medium

A server apparatus is configured to communicate with a photographing apparatus. Image date is recorded in a database. An evaluation acquisition unit acquires evaluation information and evaluated image data. A first feature amount extraction unit extracts a first feature amount from at least one of the evaluation information and the evaluated image data. A reception unit receives temporarily photographed image data from the photographing apparatus. A second feature amount extraction unit extracts a second feature amount from the temporarily photographed image data. A retrieval unit detects image data based on the first feature amount and the second feature amount. A parameter acquisition unit acquires a photographing parameter from the image data detected by the retrieval unit. A transmission unit transmits the photographing parameter to the photographing apparatus.

Server apparatus and photographing apparatus for setting a photographing parameter for capturing an image based on extracted user preference data

An imaging apparatus includes an object database, a composition database, an imaging unit, a determination unit, a search unit, a priority setting unit, and a display. The determination unit extracts an image feature amount from a photographed image data, and determines a kind of an object of the photographed image data, based on data stored in the object database. The search unit detects composition assisting information corresponding to the photographed image data from the composition database, based on the kind of the object and data stored in the composition database. The priority setting unit extracts characteristic information and determines presentation priority based on characteristic information differences. The display displays the composition assisting information based on the priority.

Imaging apparatus, composition assisting apparatus, composition assisting method, and non-transitory storage medium storing composition assisting program

A method of compiling an image database for a three-dimensional object recognition including the steps of: when a plurality of images each showing an object from different viewpoint are inputted, extracting local features from each of the images, and expressing the local features using feature vectors; forming sets of the feature vectors, each set representing a same part of the object from a series of the viewpoints, and generating subspaces, each subspace representing a characteristic of each set; and storing each subspace to the image database with an identifier of the object to perform a recognition process that is realized by the steps of: when at least one image of an object is given as a query, extracting query feature vectors; determining the subspace most similar to each query feature vector; and executing a counting process to the identifiers to retrieve an object most similar to the query.

Method and apparatus of compiling image database for three-dimensional object recognition

An image retrieval method comprising: a step of extracting at least one query feature vector from a query image on which a subject of the image retrieval is captured, the query feature vector representing a local feature of the query image; a step of accessing an image data base in which a plurality of reference images are stored previously, each reference image being stored in conjunction with learning images generated therefrom and reference feature vectors representing local features of the reference image and the learning images; a comparing step of comparing the query feature vector with the reference feature vectors stored in conjunction with each reference image using an approximate nearest neighbor search to find a reference feature vector approximately nearest to the query feature vector; and a selecting step of selecting a reference image with which the found reference feature vector is stored in conjunction from the reference images as a retrieval result wherein: the learning image is generated by adding a defocus and/or a motion-blur effect likely to occur on capturing the subject to each reference image, the reference feature vectors are extracted from each reference image and the learning image corresponding to the reference image respectively using the scale-space approach, the query feature vector is extracted from the query image using the scale-space approach, and each of the above steps is executed by a computer.

Image retrieval method, image retrieval program, and image registration method

A method for creating an image database comprising an extraction step of extracting reference feature vectors from a reference image which should be compared with a retrieval query image for object recognition, the reference feature vectors corresponding to local features at different positions of the reference image and representing the position and characteristics of each of the local features as a vector position, vector length, and a vector direction, a clustering step of creating a plurality of clusters consisting of different reference feature vectors in such a manner that each reference vector belongs to any of the plurality of clusters, a selection step of selecting the representative vector of the clusters from among the reference feature vectors of each of the clusters, and a step of associating the representative vector with the reference image and registering the representative vector associated therewith in the image database for the object recognition, wherein, in the clustering step, each of the clusters is created in such a manner that reference feature vectors at a near vector position belong to the same cluster, and in the selection step, reference feature vectors with long vector length are given priority to select the representative vector, and wherein the retrieval query image and the reference image are compared with each other by generating at least one query feature vector from the retrieval query image, and applying local search between the query feature vector and the representative vector, each of the steps being executed by computers.

Method of compiling image database, image database compilation program, image retrieval method

An information presentation system includes an imaging unit, a peripheral information acquisition unit which acquires peripheral information, a storage unit which stores registered information, an analytic basic information construction unit which constructs analytic basic information from the registered information stored in the storage unit, on the basis of the peripheral information acquired in the peripheral information acquisition unit, a pertinent information acquisition unit which acquires information pertinent to the image from the image obtained from the imaging unit and the analytic basic information obtained from the analytic basic information construction unit, and a presentation unit which presents the pertinent information acquired in the pertinent information acquisition unit. The analytic basic information construction unit changes the analytic basic information on the basis of at least one of a time, date, season, weather, temperature, humidity, place, surrounding brightness, average color/color distribution of the acquired image, surrounding sound and model.

Information presentation system, information presentation terminal and server

An information presentation method is to photograph an object by use of an image input device and display related information corresponding to the object on the object in a display screen or the periphery of the object in the display screen. The related information of the object is expressed by the contents of expression of a plurality of two-dimensional markers set on the object or the periphery of the object and the plurality of two-dimensional markers correspond to any one of a plurality of information series.

Information presentation method and information presentation system

An image processing device comprises an image acquisition apparatus configured to acquire an image of an object, a feature extraction unit configured to extract a feature portion from a visual field of the image acquired by the image acquisition apparatus, a weighting section configured to calculate a weight in accordance with extraction conditions of the feature portion extracted by the feature extraction unit to weight the feature portion, and a position orientation obtaining section configured to obtain a position and an orientation of the image acquisition apparatus on a reference coordinate system from the feature portion weighted by the weighting section.

Image processing device

An inputting/designating section inputs a multimedia object or designates a multimedia object previously stored in a database. A feature-value-determining section determines the feature value of the input or designated multimedia object. A weighting-factor-determining section determines the determined feature-value weighting factor of the multimedia object. A similarity-retrieval section retrieves the similarity of the multimedia object previously stored in the database by using the determined feature value and the determined feature-value weighting factor. A displaying section displays a multimedia object similar to the multimedia object designated by the inputting/designating section in accordance with the result of similarity retrieval. A similarity-ranking-changing section changes similarity rankings of the displayed multimedia object. A similarity-recalculating section recalculates the feature-value weighting factor of the multimedia object in accordance with the changed similarity ranking and recalculates a similarity by using the feature-value weighting factor.

Multimedia-object-retrieving method and system

An object retrieval method used is characterized as follows. When a user selects objects, the dispersion between the objects is found with respect to each of a plurality of feature quantities. Within a retrieval range of objects, the dispersion between the objects is found with respect to each of a plurality of feature quantities. Both dispersions are compared for each feature quantity. As a result of the comparison, there may be a feature quantity which causes more converged dispersion in the selected objects. This feature quantity is provided with a weight larger than any other feature quantities to weight each feature quantity. An object is retrieved from the retrieval range based on the weighted feature quantities.

Method and apparatus for retrieving similar objects

A three-dimensional model search method includes a step of producing a plurality of two-dimensional images obtained by observing a three-dimensional model as an object of search from points of view different from one another. In a first value extraction step, the respective feature values of the two-dimensional images are extracted from the plurality of two-dimensional images. In a search key input step, a two-dimensional image as a search key is inputted. In a second extraction step, the feature value is extracted from the two-dimensional image as the search key. In a similarity search step, the feature values extracted in the first and second extraction steps are used to carry out similarity search, and a three-dimensional model which is similar to the search key is outputted.

Similarity search of three-dimensional model using two-dimensional image as search key

An information presentation system includes a template matching unit which performs template matching between input information and a template group stored, a plurality of associated information search units which search for associated information on the basis of a matching result of the template matching unit, an information processing unit which processes output information in accordance with the input information, the matching result of the template matching unit, and a search result of the associated information search units, an output unit which outputs the information processed by the information processing unit, a template selection unit which causes a user to select a template group, and a template supply unit which transmits, to the template storage unit, the template group selected by the template selection unit from predetermined template groups. The template supply unit is arranged independently of the plurality of associated information search units.

Information presentation system

A feature quantity calculation device to calculate a feature quantity for a 3-D object from 3-D object data contained in the 3-D object includes a 3-D object data input module to input the 3-D object data, a 3-D object data analysis module to analyze the input 3-D object data, a volume data conversion module to convert the analyzed 3-D object data to volume data, and a feature quantity calculation module to calculate a feature quantity from the converted volume data.

Device and method for feature quantity calculation

A three-dimensional position and orientation sensing apparatus including: an image input section which inputs an image acquired by an image acquisition apparatus and showing at least three markers having color or geometric characteristics as one image, three-dimensional positional information of the markers with respect to an object to be measured being known in advance; a region extracting section which extracts a region corresponding to each marker in the image; a marker identifying section which identifies the individual markers based on the color or geometric characteristics of the markers in the extracted regions; and a position and orientation calculating section which calculates the three-dimensional position and orientation of the object to be measured with respect to the image acquisition apparatus, by using positions of the identified markers in the image input to the image input section, and the positional information of the markers with respect to the object to be measured.

Growing community of inventors

Hachioji, Japan

Yukihito Furuhashi