48results about How to "Appropriately extracted" patented technology

The invention provides a face region estimating device capable of extracting a person's face region even when an illumination environment, for example, is changed and persons with different skin colors are contained in a picked-up image taken by a camera. The face region estimating device includes: a mobile body detecting unit for extracting the outline of a mobile body from the picked-up image and for generating an object distance image composed of pixels corresponding to a distance in which the mobile body exists; a head region setting unit for setting a head region based on the pixel distribution in the object distance image corresponding to a predetermined range on the basis of a pixel position at the upper part of the outline; and a face region extracting unit for extracting the person's face region from the picked-up image based on the color distribution in the picked-up image corresponding to the head region.

In learning for pattern recognition, an aggregation of different types of object image data is inputted, and local features having given geometric structures are detected from each object image data inputted. The detected local features are put through clustering, plural representative local features are selected based on results of the clustering, and a learning data set containing the selected representative local features as supervisor data is used to recognize or detect an object that corresponds to the object image data. The learning thus makes it possible to appropriately extract, from an aggregation of images, local features useful for detection and recognition of subjects of different categories.

An information classification system includes a server that includes a knowledge base that receives classification information to be classified, conducts language analysis of the classification information to acquire a plurality of keywords and classify the plurality of keywords into elements made up of a classification target word and a related word that modifies the classification target word, and conduct a search with the related word being for a judgment condition for decision of the classification while separating the classification target word from the related word, so as to assign a classification identification value to the information; a classification candidate extraction section that extracts the classification identification value that the knowledge base assigns to generate an automatic classification result; and a classification update section that receives the automatic classification result, displays a GUI for classification confirmation allowing confirmation of correctness of the automatic classification result, and corrects registered items in the knowledge base with a correction value received through the GUI for classification confirmation while referring to log data that is a processing history about automatic classification for the language analysis and the element classification.

A Fourier transform spectrometer (Da) of the invention extracts, in generating an integrated interferogram obtained by integrating a plurality of interferograms, an output of an interferometer (11a) within a predetermined range according to positioning information of a center burst in an interferogram measured at a time before measurement of an interferogram at the present time.

When an image representing biological information is input from a biological information input unit 10, such as a fingerprint sensor or the like, for obtaining an image representing biological information, such as a fingerprint or the like, statistical quantities, such as the mean value and standard deviation of the pixel values of the sampled image, are calculated. Then, using the statistical quantities, a region containing biological information is extracted, its sensitivity variations are eliminated and the effects of stains, such as a residual fingerprint is nullified, thereby generating a favorable biological image with high contrast.

A driving support device, a driving support method, and a computer program provide an image of the peripheral environment of a vehicle which is captured by a camera. The traveling state of the vehicle is obtained and, based on same, a blind spot region for a driver created by a right front pillar, as it would appear after a predetermined period of time, is calculated by taking into consideration the time lag between capture of an image by the camera and projection of that image by a projector. An image corresponding to the calculated blind spot region is extracted from the image captured by the camera, and the extracted image is projected onto the inside surface of the right front pillar.

A clock extracting circuit for receiving an encoded signal and for extracting a clock signal from the encoded signal. The circuit comprises an edge detector that detects rising and falling edges of the encoded signal and produces edge detection pulses indicating the edges being detected; a mask signal generator producing a mask signal which is inverted in response to the edge detection pulses, which are produced one for each period of the received encoded signal, on the basis of the edge detection pulses; a mask signal delay section delaying the mask signal by a delay time controllable and outputting the delayed mask signal; a clock generator producing the clock signal on the basis of edges of the delayed mask signal; and a delay controller that controls the delay time of the mask signal delay section so as to set a duty ratio of the produced clock signal to a predetermined value.

A control method for suppressing vibration of a robot arm including a plurality of coupled links and driving units configured to drive the links includes calculating a first arm speed from at least one of acceleration and an angular velocity detected in a damping position for suppressing vibration, calculating a third arm speed according to the detected first arm speed and a second arm speed in the damping position calculated on the basis of a driving amount of the driving units, and subjecting the driving units to correction control on the basis of the calculated third arm speed.

Immediately after data write, a negative voltage which has an absolute value lager than that in data erase and which falls within a range over which no FN current flows is applied to a control gate, and at the same time 0 V is applied to a silicon substrate, source, and drain. In this manner, electrons trapped in a first gate oxide film are detrapped into the silicon substrate. This prevents a memory cell from passing write verify although electrons stored in a nitride film are few, prevents data changes caused by a decrease in the read margin, and improves the data holding characteristic of a memory cell.

Disclosed is a face component extraction apparatus including an eye detection unit which detects a plurality of combinations of eye regions, each combination forming a pair, a first calculation unit which calculates a first evaluation value for each pair of eye regions, a fitting unit which fits a plurality of extraction models for extracting a plurality of face components in the image based on a number of pairs of eye regions whose first evaluation values are equal to or greater than a predetermined value, a second calculation unit which calculates a second evaluation value for each of a number of pairs of eye regions, and a deciding unit which decides a fitting mode of the plurality of extraction models to be fitted by the fitting unit based on calculation results of a number of second evaluation values by the second calculation unit.

A transmitting method has steps of modulating carrier waves having frequencies set at ½N−n (n≦N; n is a positive integer) of a reference frequency with transmission signals to produce modulated signals, multiplexing the modulated signals by frequency division multiplexing to produce an input signal, and transmitting the input signal to a synchronous detector in which the transmission signals are extracted from the input signal by calculating a moving average of the input signal every sampling period of time corresponding to the reference frequency and performing an addition and subtraction calculation corresponding to the cycle of each carrier wave for the moving averages. The frequency of each carrier wave, modulated with one transmission signal having a first signal level, is equal to or lower than the frequency of any carrier wave modulated with another transmission signal having a second signal level higher than the first signal level.

An information processing apparatus includes: a reach-extent extraction unit configured to extract, with use of a relationship graph representing relationships between a plurality of elements included in a system and location information that indicates, on the relationship graph, a plurality of locations in the system where anomalies have been detected, paths in the relationship graph as being reach extents, the path including a set of the elements that are directly or indirectly related to each of the plurality of locations as a source; and a shared-extent extraction unit configured to extract an influence process of an anomaly by extracting an extent that is shared in at least a prescribed number of paths among paths in the relationship graph that have been extracted as the reach extents.

Provided is a therapeutic electromagnetic stimulation device for providing magnetic stimulation by applying a magnetic field to a specific site of an object person, the device including: a magnetic field generating means configured to generate one of a therapeutic magnetic field and a detection magnetic field for detection of information at least including positional information; magnetic field detecting means configured to detect intensities of components in a plurality of directions of one of the therapeutic magnetic field and the detection magnetic field at least at two detection positions; and a data generating means configured to generate custom data pairs for an individual object person, the custom data pairs being for deriving at least information of positions of the magnetic field generating means from the intensities of the corresponding components, the data generating means generating the custom data pairs using: (1) a sampling detection result of the detection of the intensities of the corresponding components in a state in which the magnetic field generating means are disposed respectively at a plurality of sampling spots near the specific site of the object person; and (2) a plurality of parent data pairs each including (a) at least information of a three-dimensional position of the magnetic field generating means pairing with (b) information of the intensities of the corresponding components of the magnetic field at a position having at least the information of the three-dimensional position, the information (a) and (b) being previously recorded.

An image editing method includes detecting positions of the moving object contained in the images for the stored series of images, detecting a locus of movement of the moving object based on the detected positions of the moving object contained in the series of images, specifying an image corresponding to a feature point of the detected locus of movement of the moving object, extracting, from the series of images stored in the memory, images which include the specified image and correspond to a second shooting time interval longer than the first shooting time interval, and storing the extracted series of images as an image file in a memory.

Interesting section extracting device 104 for extracting interesting section interesting to user from video file with reference to audio signal included in the video file such that specified time T0 is included in the interesting section. The interesting section extracting device 104 includes: interface device 109 configured to obtain specified time T0; likelihood vector generating unit 202 configured to calculate, in one-to-one correspondence with first unit sections of the audio signal, likelihoods for anchor models Ar that respectively represent features of a plurality of types of sound pieces, and generate likelihood vectors having the calculated likelihoods as components thereof; and interesting section extracting unit 209 configured to calculate first feature section as candidate section, which is candidate for the interesting section to be extracted, by using likelihood vectors F and extract, as the interesting section, part of the first feature section including the specified time T0.

A time series data monitoring system includes: a series pattern candidate generating unit that generates series pattern candidates included in time series data obtained from a monitored system using the time series data and a prediction model of the time series data; and a series pattern generating unit that classifies the series pattern candidates generated by the series pattern candidate generating unit and outputs, as a series pattern of the time series data, a candidate satisfying a predetermined condition among the classified series pattern candidates.

There are provided an ink jet printing apparatus that can appropriately set drying intensity and a drying intensity setting method thereof. An ink jet printing apparatus includes a printing section that prints an image on a sheet with aqueous ink by an ink jet method, an ink drying section that dries the ink by heating the sheet having been subjected to printing, and a varnish coating section that coats the sheet of which the ink has been dried with UV varnish. The drying intensity of the ink drying section is set so that temperature where the sheet reaches is in a prescribed range. Regions corresponding to the same drawing conditions are extracted from an image to be printed, and drying intensity is set on the basis of a drawing condition corresponding to the maximum occupied area among the regions.

An image measuring apparatus according to an embodiment of the present invention comprises: an imaging device that images a workpiece to acquire an image of this workpiece; and a processing device that performs measurement of the workpiece based on this image and outputs a measurement result. Moreover, the processing device sets a region in the image, sets a plurality of first points along a contour line of this region, sequentially moves these plurality of first points so that the plurality of first points approximate to the contour line included in the image, acquires the moved plurality of first points as a plurality of second points, and calculates the measurement result based on these plurality of second points.

Provided is technology enabling identifying the page of a color chart being measured while measuring the colors of the color chart, and generating color correction data. An information processing device 100 has a generator 121 that generates image data for printing a color chart 200 including, in part of the multiple patches, patches of an identification patch group 210 that represents page information by the sequence of patches in the group, the page information being at least one of the page number and order of pages in the color chart 200; an extractor 125 that extracts, from the color measurement results of the color chart 200 printed based on the image data, the page information represented by the patch sequence of the identification patch group 210 in the color chart 200; and an adjuster 127 that generates color correction data based on the color measurement results of the color chart 200.