Method and apparatus for image processing and image classification
AssigneeAlibaba Group Holding Limited
InventorsLiangpeng XU, Chuan DAI, Mingqian TANG
Life of this patent
Estimating the term…
Abstract
The present disclosure provides methods and apparatuses for image processing and image classification. In one embodiment, the method for image processing comprises: receiving an image; obtaining a first classification result for the image based on a classification model; processing the image for classification based on a preset process, and providing a processing result into a re-ranking model to obtain a second classification result for the image; and determining a target classification result for the image, based on the first classification result and the second classification result.
Claims20
A method comprising:
- obtaining an image;
- computing, based on a first machine learning model, a first classification result for the image, the first machine learning model configured to label the image and output labels and respective probabilities associated with the labels for the image;
- computing, based on a second machine learning model, a second classification result for the image, the second machine learning model configured to label the image based on vector search results of the image and output labels and respective probabilities associated with the labels for the image;
- and
- determining a target classification result for an image based at least on the first classification result and the second classification result.
An apparatus comprising:
- a processor;
- and
- a storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic comprising:
- logic, executed by the processor, for obtaining an image,
- logic, executed by the processor, for computing, based on a first machine learning model, a first classification result for the image, the first machine learning model configured to label the image and output labels and respective probabilities associated with the labels for the image,
- logic, executed by the processor, for computing, based on a second machine learning model, a second classification result for the image, the second machine learning model configured to label the image based on vector search results of the image and output labels and respective probabilities associated with the labels for the image, and
- logic, executed by the processor, for determining a target classification result for an image based at least on the first classification result and the second classification result.
A non-transitory computer-readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining the steps of:
- obtaining an image;
- computing, based on a first machine learning model, a first classification result for the image, the first machine learning model configured to label the image and output labels and respective probabilities associated with the labels for the image;
- computing, based on a second machine learning model, a second classification result for the image, the second machine learning model configured to label the image based on vector search results of the image and output labels and respective probabilities associated with the labels for the image;
- and
- determining a target classification result for an image based at least on the first classification result and the second classification result.
Dependencies are inferred from the claim text.