摘要:
Data in multidimensional space such as a two-dimensional image is encoded with high efficiency. Further, as two-dimensional data can be decomposed to one-dimensional bases, the problem of wiring for two-dimensional parallelizing in a convolution arithmetic unit can be solved. For this purpose, two-dimensional image data f(x,y) to be encoded is inputted, and one-dimensional adaptive bases X(x),Y(y) representing the two-dimensional image are obtained. Next, a reconstructed image is generated based on the one-dimensional adaptive bases, and the one-dimensional adaptive bases are corrected based on an error E between the reconstructed image and the input image. The correction is repeated until the error E is reduced.
摘要:
A network camera system is provided that detects an occurrence of a condition change at a periphery of an image pickup apparatus, obtains a direction of the detected condition change, and notifies a user of the occurrence of the condition change and a direction of the condition change on a display of a terminal device.
摘要:
A pattern recognition method, applicable to input information including a plurality of regions, includes obtaining a certainty at which each region of the input information includes a pattern, selecting one or more regions having a relatively high-level certainty among the plurality of regions, and performing pattern detection processing on the selected region or regions.
摘要:
In an image within which a face pattern is detected, when a ratio of a skin color pixel is equal to or smaller than a first threshold value in a first region and a ratio of a skin color pixel is equal to or greater than a second threshold value in a second r region, the vicinity of the first region is determined to be a face candidate position at which the face pattern can exist. Face detection is carried out on the face candidate position. The second region is arranged in a predetermined position relative to the first region.
摘要:
In an image within which a face pattern is detected, when a ratio of a skin color pixel is equal to or smaller than a first threshold value in a first region and a ratio of a skin color pixel is equal to or greater than a second threshold value in a second r region, the vicinity of the first region is determined to be a face candidate position at which the face pattern can exist. Face detection is carried out on the face candidate position. The second region is arranged in a predetermined position relative to the first region.
摘要:
An information processing apparatus that discriminates the orientation of a target includes a calculation unit that calculates a distribution of a difference in feature amount between a plurality of learning patterns each showing the orientation of a target, a determination unit that determines, using a probability distribution obtained from the distribution of differences calculated by the calculation unit, a pixel that is in an input pattern and is to be referred to in order to discriminate the orientation of a target in the input pattern, and a discrimination unit that performs discrimination for obtaining the orientation of the target in the input pattern by comparing a feature amount of the pixel determined by the determination unit and a threshold set in advance.
摘要:
An action recognition apparatus includes an input unit for inputting image data, a moving-object detection unit for detecting a moving object from the image data, a moving-object identification unit for identifying the detected moving object based on the image data, a state detection unit for detecting a state or an action of the moving object from the image data, and a learning unit for learning the detected state or action by associating the detected state or action with meaning information specific to the identified moving object.
摘要:
A method includes detecting a feature of an input pattern using a plurality of feature detectors, selecting at least one of the feature detectors based on their output values, and calculating a feature quantity of the input pattern based on an output value from at least one selected feature detector.
摘要:
A network camera system is provided that detects an occurrence of a condition change at a periphery of an image pickup apparatus, obtains a direction of the detected condition change, and notifies a user of the occurrence of the condition change and a direction of the condition change on a display of a terminal device.
摘要:
In a hierarchical neural network having a module structure, learning necessary for detection of a new feature class is executed by a processing module which has not finished learning yet and includes a plurality of neurons which should learn an unlearned feature class and have an undetermined receptor field structure by presenting a predetermined pattern to a data input layer. Thus, a feature class necessary for subject recognition can be learned automatically and efficiently.