The University of Tokyo

Nippon Telegraph and Telephone Corporation

Foo.log Inc.

Kiyoharu Aizawa

Kunio Kashino

Kaoru Hiramatsu

Makoto Ogawa

Tatsuya Miyazaki

Go Irie

Kazuya Kodama

Yasuhiro Ohtsuka

Toshihiko Yamasaki

Keigo Kitamura

Low-dimensional feature values with which semantic factors of content are ascertained are generated from relevance between sets of two types of content. Based on a relation indicator indicating a pair of groups indicating which groups are related to first types of content groups among second types of content groups, an initial feature value extracting unitextracts initial feature values of the first type of content and the second type of content. A content pair selecting unitselects a content pair by selecting one first type of content and one second type of content from each pair of groups indicated by the relation indicator. A feature value conversion function generating unitgenerates feature conversion functionsof converting the initial feature values into low-dimensional feature values based on the content pair selected from each pair of groups.

Feature amount generation method, feature amount generation device, and feature amount generation program

Provided is an image processing apparatus which is connected to and accessible to a database storing a plurality of pieces of previously prepared reference data, and which stores at least one piece of individual data having an image captured by the user in association with the information regarding the food/beverage contained in the captured image. The image processing apparatus compares information of the food/beverage in the captured image with the reference data stored in the database and the individual data, and acquires the food/beverage information included in the reference data together with the reference image similar to the captured image, the food/beverage information associated with the captured image in the individual data, or the food/beverage information in the reference data or the individual data including the food/beverage information relating to the captured image.

Image processing apparatus

To provide an information processing device for outputting estimated nutrition value information on at least one dish or a drink through simplified processing. The information processing device holds as reference information a captured image of at least one dish or a drink and nutrition value information set for the item of food or drink included in the image so as to be correlated to each other, receives an image including at least one dish or a drink, and retrieves a plurality of images similar to the image received from among the reference information held. Further, the information processing device calculates a statistic of a plurality of nutrition value information pieces correlated to the plurality of respective images retrieved, and outputs the statistic calculated.

Information processing device

An image processing method using multiple images includes the steps of imaging multiple differently focused images I (m&equals;1, . . . , n); deriving an identical equation based on superposition models realized between the multiple differently focused images I and desired images I, obtaining a solution by substituting multiple images I and the functions T and T of different focusing into the identical equation; performing an image process for generating desired image I based on this solution; and selectively generating a desired image I by controlling the function T .

Image processing method using multiple images

An image sensor with sampling control system including a sensor unit having a number of pixel circuits arranged in matrix, a memory unit having a number of memory circuits arranged in matrix, each memory circuits being corresponding to respective pixel circuits, a first horizontal shift register writing a pixel read-out pattern into said memory circuits in accordance with an externally supplied sample selection signal, a first vertical shift register for generating signals for writing and reading said pixel read-out pattern into and out of said memory circuits, a second vertical shift register driven in synchronism with said first vertical shift register for supplying a pixel value read-out signal to said pixels circuits, a second horizontal shift register for outputting pixel values selected in accordance with the pixel read-out pattern, a third horizontal shift register for outputting all pixel values, and a switch unit for selectively reading the pixel values out of any one of said second and third horizontal shift registers in accordance with a node signal.

Growing community of inventors

Tokyo, Japan

Kiyoharu Aizawa