摘要:
An image recognition apparatus includes an extraction unit configured to extract a feature quantity for each local area from an input image, a conversion unit configured to convert the feature quantity extracted by the extraction unit into a feature quantity indicating a degree with respect to an attribute for each local area, a verification unit configured to verify the feature quantity converted by the conversion unit against a feature quantity of a registered image, and an identification unit configured to identify whether the input image is identical to the registered image by integrating the verification result for each local area acquired by the verification unit.
摘要:
An image recognition apparatus includes an extraction unit configured to extract a feature quantity for each local area from an input image, a conversion unit configured to convert the feature quantity extracted by the extraction unit into a feature quantity indicating a degree with respect to an attribute for each local area, a verification unit configured to verify the feature quantity converted by the conversion unit against a feature quantity of a registered image, and an identification unit configured to identify whether the input image is identical to the registered image by integrating the verification result for each local area acquired by the verification unit.
摘要:
An information processing apparatus comprising: an obtaining unit configured to obtain image data; a detection unit configured to detect an object from the image data; an attribute determination unit configured to determine an attribute indicating a characteristic of the object detected by the detection unit; a registration unit configured to register the image data in at least one of a plurality of dictionaries based on the attribute determined by the attribute determination unit; and an adding unit configured to add, when the image data is registered in not less than two dictionaries, link information concerning the image data registered in the other dictionary to the image data registered in one dictionary.
摘要:
An object identification apparatus which identifies an object included in an input image includes a unit which calculates correlation values of feature amounts in standard partial feature regions respectively extracted from the input images and processing targets, and correlation values of feature amounts in adaptive partial feature regions respectively extracted from the input image and processing targets, a unit which calculates similarities based on the calculated correlation values, and a unit which integrates the plurality of calculated similarities, and outputs them as an integrated similarity between the input image and registered image as the processing targets. According to the object identification apparatus, an identification performance between two specific categories, which are similarity to each other, is improved while maintain an overall identification performance.
摘要:
An object identification apparatus, which identifies a class of a plurality of registered classes to which an object included in an input image belongs, registers a plurality of registered images used in identification of an input image, and holds designation data required to designate partial areas used in identification. The apparatus extracts feature amounts of the partial areas designated by the designation data from the input image and each of the plurality of registered images, and identifies a class to which the input image belongs based on the extracted feature amounts. The apparatus determines based on the plurality of registered images whether or not is required to update processing contents of an identification unit. When it is determined that the processing contents are required to be updated, the apparatus updates the designation data based on registered images.
摘要:
An apparatus extracts a first dictionary information associated with a first category from among multiple categories included in a dictionary and second dictionary information associated with a second category from among multiple categories included in the dictionary or another dictionary, calculates a first feature amount and a second feature amount from the first dictionary information and the second dictionary information, respectively, receives an instruction as to whether or not to integrate a name of the first category and a name of the second category in the case where it is determined that a similarity between the calculated first feature amount and second feature amount is greater than a predetermined threshold and that the name of the first category and the name of the second category do not match, and integrates the name of the first category and the name of the second category with the received post-integration name.
摘要:
An object identification apparatus, which identifies a class of a plurality of registered classes to which an object included in an input image belongs, registers a plurality of registered images used in identification of an input image, and holds designation data required to designate partial areas used in identification. The apparatus extracts feature amounts of the partial areas designated by the designation data from the input image and each of the plurality of registered images, and identifies a class to which the input image belongs based on the extracted feature amounts. The apparatus determines based on the plurality of registered images whether or not is required to update processing contents of an identification unit. When it is determined that the processing contents are required to be updated, the apparatus updates the designation data based on registered images.
摘要:
An information processing apparatus comprising: an obtaining unit configured to obtain image data; a detection unit configured to detect an object from the image data; an attribute determination unit configured to determine an attribute indicating a characteristic of the object detected by the detection unit; a registration unit configured to register the image data in at least one of a plurality of dictionaries based on the attribute determined by the attribute determination unit; and an adding unit configured to add, when the image data is registered in not less than two dictionaries, link information concerning the image data registered in the other dictionary to the image data registered in one dictionary.
摘要:
An apparatus extracts a first dictionary information associated with a first category from among multiple categories included in a dictionary and second dictionary information associated with a second category from among multiple categories included in the dictionary or another dictionary, calculates a first feature amount and a second feature amount from the first dictionary information and the second dictionary information, respectively, receives an instruction as to whether or not to integrate a name of the first category and a name of the second category in the case where it is determined that a similarity between the calculated first feature amount and second feature amount is greater than a predetermined threshold and that the name of the first category and the name of the second category do not match, and integrates the name of the first category and the name of the second category with the received post-integration name.
摘要:
An object identification apparatus which identifies an object included in an input image includes a unit which calculates correlation values of feature amounts in standard partial feature regions respectively extracted from the input images and processing targets, and correlation values of feature amounts in adaptive partial feature regions respectively extracted from the input image and processing targets, a unit which calculates similarities based on the calculated correlation values, and a unit which integrates the plurality of calculated similarities, and outputs them as an integrated similarity between the input image and registered image as the processing targets. According to the object identification apparatus, an identification performance between two specific categories, which are similarity to each other, is improved while maintain an overall identification performance.