Image processing apparatus, image processing method, and storage medium
AssigneeCanon Kabushiki Kaisha
InventorRyosuke Tsuji
Life of this patent
Estimating the term…
Abstract
An image processing apparatus comprises a detection circuit that, by referencing dictionary data acquired by machine learning corresponding to a target photographic subject to be detected in an obtained image, detects the target photographic subject; a selection unit that selects one of a plurality of dictionary data items corresponding to the target photographic subject; and a control circuit that, in a case where a detection evaluation value in a case where the photographic subject is detected by using the dictionary data selected by the selection unit is lower than a predetermined value, controls the detection circuit to detect the target photographic subject by using the selected dictionary data and dictionary data different to the selected dictionary data.
Claims19
An image processing apparatus comprising:
- at least one processor or circuit configured to function as the following units:
- an analysis unit configured to select one among a plurality of dictionary data items, and by using the selected dictionary data, to perform analysis of an obtained image,
- wherein the plurality of dictionary data items includes at least a first dictionary data and a second dictionary data, and
- wherein the analysis unit, even in a case where a detection score for the photographic subject obtained using the first dictionary data is lower than a threshold or the photographic subject cannot be detected using the first dictionary data, performs image analysis again by using the first dictionary data, and
- in a case where a detection score for the photographic subject obtained using the second dictionary data is lower than a threshold or the photographic subject cannot be detected using the second dictionary data, performs image analysis again by using dictionary data different from the second dictionary data,
- wherein the second dictionary data is a dedicated dictionary data, with which a probability to detect a target photographic subject is higher than with a general purpose dictionary data, and wherein the dictionary data different from the second dictionary is the general purpose dictionary data, by which it is possible to detect the target photographic subject in more conditions than with the dedicated dictionary data.
An image processing apparatus comprising:
- at least one processor or circuit configured to function as the following units:
- a detection unit configured to, by referencing dictionary data acquired by machine learning corresponding to a target photographic subject to be detected in an obtained image, detect the target photographic subject;
- a selection unit configured to select one of a plurality of dictionary data items corresponding to the target photographic subject;
- and
- a control unit configured to, in a case where a detection evaluation value, in a case where the photographic subject is detected by using the dictionary data selected by the selection unit, is lower than a predetermined value, control the detection unit to detect the target photographic subject by using the selected dictionary data and dictionary data different from the selected dictionary data,
- wherein the plurality of dictionary data items include a general purpose dictionary data and a plurality of dedicated dictionary data items, and
- each of the plurality of dedicated dictionary data items are dictionary data for which, in a case where the target photographic subject is in a condition respectively corresponding to the dedicated dictionary data, a probability that it is possible to detect the target photographic subject is higher than with the general purpose dictionary data, and the general purpose dictionary data is dictionary data by which it is possible to detect the target photographic subject in more conditions than with each of the plurality of dedicated dictionary data items,
- wherein the dictionary data different from the selected dictionary data is a general purpose dictionary data, by which it is possible to detect the target photographic subject in more conditions than with a dedicated dictionary data.
An image processing method comprising:
- selecting one among a plurality of dictionary data items, and by using the selected dictionary data, performing analysis of an obtained image,
- wherein the plurality of dictionary data items includes at least a first dictionary data and a second dictionary data, and
- even in a case where a detection score for the photographic subject obtained using the first dictionary data is lower than a threshold or the photographic subject cannot be detected using the first dictionary data, image analysis is performed again by using the first dictionary data, and
- in a case where a detection score for the photographic subject obtained using the second dictionary data is lower than a threshold or the photographic subject cannot be detected using the second dictionary data, image analysis is performed again by using dictionary data different from the second dictionary data,
- wherein the second dictionary data is a dedicated dictionary data, with which a probability to detect a target photographic subject is higher than with a general purpose dictionary data, and wherein the dictionary data different from the second dictionary is the general purpose dictionary data, by which it is possible to detect the target photographic subject in more conditions than with the dedicated dictionary data.
An image processing method comprising:
- detecting a target photographic subject by referencing dictionary data acquired by machine learning corresponding to the target photographic subject to be detected in an obtained image;
- selecting one of a plurality of dictionary data items corresponding to the target photographic subject;
- and
- in a case where a detection evaluation value, in a case where the photographic subject is detected by using the dictionary data selected by the selecting, is lower than a predetermined value, controlling the detecting to detect the target photographic subject by using the selected dictionary data and dictionary data different from the selected dictionary data,
- wherein the plurality of dictionary data items include general purpose dictionary data and a plurality of dedicated dictionary data items, and
- each of the plurality of dedicated dictionary data items is dictionary data for which, in a case where the target photographic subject is in a condition respectively corresponding to the dedicated dictionary data, a probability that it is possible to detect the target photographic subject is higher than with the general purpose dictionary data, and the general purpose dictionary data is dictionary data by which it is possible to detect the target photographic subject in more conditions than with each of the plurality of dedicated dictionary data items,
- wherein the dictionary data selected by the selecting is a dedicated dictionary data, with which a probability to detect a target photographic subject is higher than with a general purpose dictionary data, and wherein the dictionary data different from the selected dictionary is the general purpose dictionary data, by which it is possible to detect the target photographic subject in more conditions than with the dedicated dictionary data.
A non-transitory computer-readable storage medium on which a program for enabling a computer to function as each unit of an image processing apparatus is stored, the image processing apparatus comprising:
- at least one processor or circuit configured to function as the following units:
- an analysis unit configured to select one among a plurality of dictionary data items, and by using the selected dictionary data, to perform analysis of an obtained image,
- wherein the plurality of dictionary data items includes at least a first dictionary data and a second dictionary data, and
- the analysis unit,
- even in a case where a detection score for the photographic subject obtained using the first dictionary data is lower than a threshold or the photographic subject cannot be detected using the first dictionary data, performs image analysis again by using the first dictionary data, and
- in a case where a detection score for the photographic subject obtained using the second dictionary data is lower than a threshold or the photographic subject cannot be detected using the second dictionary data, performs image analysis again by using dictionary data different from the second dictionary data,
- wherein the second dictionary data is a dedicated dictionary data, with which a probability to detect a target photographic subject is higher than with a general purpose dictionary data, and wherein the dictionary data different from the second dictionary is the general purpose dictionary data, by which it is possible to detect the target photographic subject in more conditions than with the dedicated dictionary data.
A non-transitory computer-readable storage medium on which a program for enabling a computer to function as each unit of an image processing apparatus is stored, the image processing apparatus comprising:
- at least one processor or circuit configured to function as the following units:
- a detection unit configured to, by referencing dictionary data acquired by machine learning corresponding to a target photographic subject to be detected in an obtained image, detect the target photographic subject;
- a selection unit configured to select one of a plurality of dictionary data items corresponding to the target photographic subject;
- and
- a control unit configured to, in a case where a detection evaluation value, in a case where the photographic subject is detected by using the dictionary data selected by the selection unit, is lower than a predetermined value, control the detection unit to detect the target photographic subject by using the selected dictionary data and dictionary data different from the selected dictionary data,
- wherein the plurality of dictionary data items include general purpose dictionary data and a plurality of dedicated dictionary data items, and
- each of the plurality of dedicated dictionary data items are dictionary data for which, in a case where the target photographic subject is in a condition respectively corresponding to the dedicated dictionary data, a probability that it is possible to detect the target photographic subject is higher than with the general purpose dictionary data, and the general purpose dictionary data is dictionary data by which it is possible to detect the target photographic subject in more conditions than with each of the plurality of dedicated dictionary data items,
- wherein the dictionary data selected by the selecting is a dedicated dictionary data, with which a probability to detect a target photographic subject is higher than with a general purpose dictionary data, and wherein the dictionary data different from the selected dictionary is the general purpose dictionary data, by which it is possible to detect the target photographic subject in more conditions than with the dedicated dictionary data.
Dependencies are inferred from the claim text.