Image recognition method and device thereof
AssigneeIndustrial Technology Research Institute
InventorsHsin-Yi Chen, Chia-Liang Yeh, Sen-Yih Chou
Life of this patent
Estimating the term…
Abstract
An image recognition method adapted to recognize a target image is provided. The method includes: providing the target image; training a learning database based on a plurality of feature blocks of the target image; randomly obtaining a plurality of incomplete feature blocks of the target image; adding the plurality of incomplete feature blocks into the learning database to form an enhancement learning database; and recognizing the target image based on the enhancement learning database. In addition, an image recognition device is also provided.
Claims14
An image recognition method, adapted to recognize a target image, wherein a portion of the target image is shielded, the image recognition method comprising:
- providing the target image;
- training a learning database based on a plurality of feature blocks of the target image;
- randomly obtaining a plurality of incomplete feature blocks of the target image;
- adding the incomplete feature blocks to the learning database to form an enhancement learning database;
- and
- recognizing the target image based on the enhancement learning database.
An image recognition device, adapted to recognize a target image, wherein a portion of the target image is shielded, the image recognition device comprising:
- an image capturing module, adapted to capture the target image;
- a storage module, adapted to store the target image;
- and
- a processing module, electrically connected to the image capturing module and the storage module, and adapted to provide a plurality of feature blocks of the target image to the storage module to train a learning database, wherein the processing module is adapted to randomly obtain a plurality of incomplete feature blocks of the target image, add the incomplete feature blocks to the learning database to form an enhancement learning database, and thereby recognizes the target image based on the enhancement learning database.
Dependencies are inferred from the claim text.