Method, apparatus and system for determining feature data of image data, and storage medium
Provided in the present disclosure are a method, an apparatus and a system for determining feature data of image data, and a storage medium. Wherein, the method comprises: acquiring features of image data, the features comprising a first feature and a second feature, wherein, the first feature is extracted from the image data using a first model, the first model being trained in a machine learning manner, and the second feature is extracted from the image data using a second model, the second model being constructed based on a pre-configured data processing algorithm; and determining feature data based on the first feature and the second feature. The present disclosure solves the technical problem that features recognized by the AI may not be consistent with human recognized features.
1. A method for determining feature data of image data, comprising:
acquiring features of the image data, the features comprising a first feature and a second feature, wherein, the first feature is extracted from the image data using a first model, the first model being trained in a machine learning manner, and the second feature is extracted from the image data using a second model, the second model being constructed based on a pre-configured data processing algorithm; and
determining the feature data based on the first feature and the second feature, comprising:
comparing the first feature and the second feature so as to determine whether the first feature is the same as the second feature;
if the first feature is different from the second feature, assigning the first feature and the second feature with a first label and a second label respectively, and assigning the first feature and the second feature as first feature data and second feature data respectively; and
if the first feature is the same as the second feature, assigning either the first feature or the second feature with a third label, and assigning either the first feature or the second feature as third feature data.
2. The method for determining feature data of image data of claim 1 , wherein, the acquiring features of the image data comprises one of:
extracting the first feature from the image data, and extracting the second feature from the feature region where the first feature of the image data is located;
extracting the second feature from the image data, and extracting the first feature from the feature region where the second feature of the image data is located; and
extracting the first feature and the second feature for the entirety of the image data.
3. The method for determining feature data of image data of claim 1 , wherein,
the feature data characterizes a luminance feature, a color feature, a texture feature, a shape feature, or a spatial relationship feature of the image data.
4. An apparatus for determining feature data of image data, comprising:
a processor configured to:
acquire features of the image data, the features comprising a first feature and a second feature, wherein, the first feature is extracted from the image data using a first model, the first model being trained in a machine learning manner, and the second feature is extracted from the image data using a second model, the second model being constructed based on a pre-configured data processing algorithm; and
determine the feature data based on the first feature and the second feature, wherein, the processor:
compares the first feature and the second feature so as to determine whether the first feature is the same as the second feature;
if the first feature is different from the second feature, assigns the first feature and the second feature with a first label and a second label respectively, and assigns the first feature and the second feature as first feature data and second feature data respectively; and
if the first feature is the same as the second feature, assigns either the first feature or the second feature with a third label, and assigns either the first feature or the second feature as third feature data.
5. The apparatus for determining feature data of image data of claim 4 , wherein, the processor acquires the features of the image data by one of:
extracting the first feature from the image data, and extracting the second feature from the feature region where the first feature of the image data is located;
extracting the second feature from the image data, and extracting the first feature from the feature region where the second feature of the image data is located; and
extracting the first feature and the second feature for the entirety of the image data.
6. The apparatus for determining feature data of image data of claim 4 , wherein,
the feature data characterizes a color feature, a texture feature, a shape feature, or a spatial relationship feature of the image data.
7. A system for determining feature data of image data, comprising:
a processor for executing the method of claim 1 ; and
a display for outputting the feature data.
8. A non-transitory computer readable storage medium having a program stored thereon, which program, when executed, executes the method of claim 1 .
9. The method for determining feature data of image data of claim 2 , wherein,
the feature data characterizes a luminance feature, a color feature, a texture feature, a shape feature, or a spatial relationship feature of the image data.
10. The apparatus for determining feature data of image data of claim 5 , wherein,
the feature data characterizes a color feature, a texture feature, a shape feature, or a spatial relationship feature of the image data.
11. A system for determining feature data of image data, comprising:
a processor for executing the method of claim 2 ; and
a display for outputting the feature data.