Canon Kabushiki Kaisha

Shunta Tate

Masakazu Matsugu

Katsuhiko Mori

Yasuhiro Komori

Yusuke Mitarai

Hiroto Yoshii

Yasuhiro Okuno

Masato Aoba

Takayuki Saruta

Tomoaki Kawai

Tsewei Chen

Koichi Magai

Tsuyoshi Kuroki

Masafumi Takimoto

Yuichiro Iio

There is provided with a data processing apparatus for detecting an object from an image using a hierarchical neural network. The data processing apparatus has parallel first and second neural networks. An obtaining unit obtains a table which defines different first and second portions. An operation unit performs calculation of the feature data of a third portion based on feature data of the first portion identified using the table and on a weighting parameter between first and second layers of the first neural network, and calculation of feature data of a fourth portion based on feature data of the second portion identified using the table and on a weighting parameter between the first and second layers of the second neural network.

Data processing apparatus, training apparatus, method of detecting an object, method of training, and medium

A connected layer feature is generated by connecting outputs of a plurality of layers of a hierarchical neural network obtained by processing an input image using the hierarchical neural network. An attribute score map representing an attribute of each region of the input image is generated for each attribute using the connected layer feature. A recognition result for a recognition target is generated and output by integrating the generated attribute score maps for respective attributes.

Image processing apparatus, image processing method, and non-transitory computer-readable storage medium

An apparatus includes a first acquisition unit that acquires a plurality of likelihood maps by setting a plurality of different weight parameters in a trained model that outputs, with an image feature extracted from the input image as an input, a likelihood map including, in association with a position in the input image, a likelihood indicating a possibility that the object is present, and a detection unit that detects, based on the acquired plurality of the likelihood maps, the position of the object included in the input image, wherein the trained model is a model that has learned the weight parameters based on loss values at least acquired using a first loss function for reducing a likelihood around a position of interest in the likelihood map, and a second loss function for increasing a likelihood acquired at the position of the object in the input image.

Information processing apparatus, information processing method, and storage medium

According to the present disclosure, a weight parameter of a neural network is divided into a plurality of portions having a certain size and approximation is individually performed on the portions using a weighted sum of the codebook vectors.

Information processing apparatus, information processing method, and program

An information processing apparatus includes a learning unit configured to learn a plurality of multi-layer neural networks configured to carry out a plurality of tasks, a generation unit configured to generate a shared layer candidate at a predetermined layer between or among the plurality of multi-layer neural networks, a first relearning unit configured to relearn the plurality of multi-layer neural networks in a structure using the shared layer candidate, and a determination unit configured to determine whether to share the shared layer candidate at the predetermined layer with respect to each of the plurality of tasks based on an evaluation of the relearning.

Information processing apparatus using multi-layer neural network and method therefor

An image processing apparatus includes: an acquisition unit configured to acquire a plurality of images each capturing an identical target and having a different attribute; a derivation unit configured to derive features from the plurality of images, using a first neural network; an integration unit configured to integrate the features derived from the plurality of images; and a generation unit configured to generate a higher quality image than the plurality of images from the feature integrated by the integration unit, using a second neural network.

Image processing apparatus and method for generating high quality image

In the present disclosure, an image parameter of an input image is changed, features is extracted from each of a plurality of generated images, a category of each region is determined based on the features in each image, and the results are integrated.

Image recognition apparatus, image recognition method, and program

An image recognition method for an image recognition apparatus includes detecting, setting, acquiring, selecting, and specifying. At least one part of an identification target is selected from an identification target image. An inquiry region is set based on the detected part. A feature amount of the set inquiry region is acquired. At least one instance image corresponding to the identification target image is selected based on the acquired feature amount. A specific region of the identification target from the identification target image is specified based on the selected instance image.

Image recognition method, image recognition apparatus, and recording medium

The accuracy of estimating the category of an object in an image and its region is improved. The present invention detects as to whether each of a plural types of objects is included in an object image, forms a plurality of local regions in a region including the object detected, and calculates a feature quantity of the plurality of local regions formed. Furthermore, the present invention selects a discriminant criterion adapted to the type of the object detected, from a plurality of discriminant criteria for discriminating the plural types of objects, and determines, based on the discriminant criterion selected and the feature quantity calculated, a region of the object detected from the plurality of local regions.

Image recognizing apparatus, image recognizing method, and storage medium

When a human skin region is detected, misdetection or detection failure is prevented. An image processing apparatus of the present invention acquires an image from which a human body skin region is to be extracted, and estimates a human body part region in the image. The image processing apparatus then estimates a skin attribute of the estimated human body part region and corrects the human body part region based on the estimated skin attribute. The image processing apparatus extracts the skin region from the acquired image based on the skin attribute of the estimated human body part region and the corrected human body part region.

Image processing method, image processing apparatus, and recording medium

An image processing apparatus, an image processing method, and a recording medium realize identification of an object region and a region category with high precision, estimate a relationship between partial regions in an acquired image by using a database about relationships between the images, and determine a target region in the acquired image based on the relationship.

Image processing apparatus, image processing method, and recording medium

A recognition apparatus according to an embodiment of the present invention includes: a candidate region extraction unit configured to extract a subject candidate region from an image; a feature value extraction unit configured to extract a feature value related to an attribute of the image from the subject candidate region extracted by the candidate region extraction unit; an attribute determination unit configured to determine an attribute of the subject candidate region extracted by the candidate region extraction unit on the basis of the feature value extracted by the feature value extraction unit; and a determination result integration unit configured to identify an attribute of the image by integrating determination results of the attribute determination unit.

Recognition apparatus and recognition method

A relative direction relationship is acquired between first and second input area images of a particular person taken from different directions. The particular person is identified by comparing a feature of the first input area image with a feature of a first one of registered area images of the particular person or another person taken from at least three directions, comparing a feature of the second input area image with a feature of a second registered area image of the same person as the person of the first registered area image, and determining whether the person in the first and second input area images is the same person in the first and second registered area images. The first and second registered area images are selected such that the relation between the first and second registered area images is similar to the relation between the first and second input area images.

Image recognition system, image recognition apparatus, image recognition method, and computer program

An image processing apparatus stores model information representing a subject model belonging to a specific category, detects the subject from an input image by referring to the model information, determines a region for which an image correction is to be performed within a region occupied by the detected subject in the input image, stores, for a local region of the image, a plurality of correction data sets representing correspondence between a feature vector representing a feature before correction and a feature vector representing a feature after correction, selects at least one of the correction data sets to be used to correct a local region included in the region determined to undergo the image correction, and corrects the region determined to undergo the image correction using the selected correction data sets.

Growing community of inventors

Tokyo, Japan

Shunta Tate