Abstract:
An analyzing unit 9 is connected to an inserting-operation information collecting unit 5, an endoscope video output unit 6, and a processing device 2, and receives live inserting-operation information and endoscope image, standard inserting-operation information as stored information, and an endoscope image correlated therewith (endoscope image which is obtained by picking up an image of a sample at the position of a distal-end portion of an inserting portion detected based on the inserting-operation information). The analyzing unit 9 collects in real time the inserting-operation information and the endoscope image from the inserting-operation information collecting unit 5 and the endoscope video output unit 6 under the bronchoscope operation of an operator. Further, the analyzing unit 9 sequentially analyzes the collected inserting-operation information and endoscope image by comparing with the standard inserting-operation information and endoscope image correlated with the inserting-operation information, which are stored in a storing unit 2A of the processing device 2, outputs an analysis result to a notifying unit 10, and monitors the inserting operation of the endoscope inserting portion performed by the operator.
Abstract:
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.
Abstract:
An analysis section (9) is connected to an insert operation information collection section (5), an endoscope video output section (6), and a processing device (2) so as to be provided with live insert operation information and an endoscope image as well as insert operation information as a reference of the storage information and an endoscope image related to this operation information (an endoscope image picking up an examinee of the insert portion end position detected by the insert operation information). While an operator operates a bronchia endoscope, the analysis section (9) collects in real time the insert operation information from the insert operation information collection section (5) and the endoscope video output section (6) and an endoscope image and successively compares for analysis the collected insert operation information and the endoscope image to the insert operation information and the endoscope image as the related reference which is the storage information stored in a storage section (2A) of the processing device (2). The comparison result is output to a notification section (10) so as to monitor the insert operation of the endoscope insert portion by the operator.
Abstract:
PROBLEM TO BE SOLVED: To provide a server, a terminal device or the like, which make effective use of vagueness of image retrieval. SOLUTION: A server includes: a reception processing part 204 for performing processing to receive transmission data about a retrieval object image through a network 10; an image recognition part 206 for performing the image recognition processing of the received retrieval object image, and for retrieving a plurality of similar images similar to the retrieval object images from among registered images registered in an image database 220; a tag processing part 210 for acquiring tags associated with the respective similar images in the plurality of retrieved similar images; and a data creation part 214 for creating similarity retrieval result data including the plurality of associated tags acquired from an associated tag database 230, based on the plurality of tags acquired from the plurality of similar images. COPYRIGHT: (C)2010,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To provide a server, a terminal device or the like which attain a highly convenient image retrieval system. SOLUTION: The server includes: a reception processing part 204 for performing processing to receive transmission data about a retrieval object image through a network 10; an image recognition part 206 for performing the image recognition processing of the retrieval object image, and for retrieving a plurality of similar images similar to the retrieval object image from among registered images registered in an image database 220; a tag processing part 210 for acquiring tags associated with the respective similar images of the plurality of retrieved similar images, and for performing the sort processing of a plurality of tags obtained from the plurality of similar images; and a data creation part 214 for creating similar retrieval result data including the plurality of sorted tags. COPYRIGHT: (C)2010,JPO&INPIT
Abstract:
PROBLEM TO BE SOLVED: To highly accurately extract a closed area from an image even when the closed area is observed in a state that a part of four sides of the closed area is disconnected. SOLUTION: A plurality of straight lines are extracted from image data obtained by image pickup and a closed area surrounded by the plurality of extracted straight lines is extracted. COPYRIGHT: (C)2007,JPO&INPIT