Method and apparatus for identifying a product
Provided are a method and apparatus for identifying a product. The method includes: acquiring an image of the product; performing multilevel detection on the image to determine a label region of the product, specifically, an image region corresponding to a previous level of detection is greater than an image region corresponding to a following level of detection; and identifying information in the label region to determine information of the product. A product can be identified automatically by acquiring the image of the product and performing multilevel detection on the image, thereby efficiency is improved, a large number of products can be handled, and cost is reduced.
1. A computer-implemented method for identifying a product, comprising:
acquiring an image of the product;
dividing the image into a first plurality of regions;
performing character identification on each of the first plurality of regions;
selecting, from the first plurality of regions, a second plurality of regions having identified characters greater than a preset threshold;
determining, from the second plurality of regions, a region having a greatest number of characters in a preset unit area;
increasing a contrast ratio of the region;
identifying a text on the region with the increased contrast ratio;
and
identifying information of the product based on the text on the region.
2. The method according to claim 1 , further comprising:
determining the region having a plurality of preset characters.
3. An apparatus for identifying a product, comprising:
an acquiring module configured to acquire an image of the product;
a detecting module configured to determine a label region of the product by:
dividing the image into a first plurality of regions;
performing character identification on each of the first plurality of regions;
selecting, from the first plurality of regions, a second plurality of regions having identified characters greater than a preset threshold;
determining, from the second plurality of regions, a region having a greatest number of characters in a preset unit area;
selecting the region as the label region; and
an identifying module configured to identify information of the product based on information in the label region.
4. The apparatus according to claim 3 , wherein the detecting module is further configured to:
increase a contrast ratio of the label region; and
identify a text on the label region with the increased contrast ratio;
wherein the identifying module configured to:
identify the information of the product based on the text.
5. The apparatus according to claim 3 , wherein the detecting module is configured to determine the label region having a plurality of preset characters.
6. One or more non-transitory computer storage media comprising computer-implemented instructions that, when used by one or more computing devices, cause the one or more computing devices to:
acquire an image of a product;
divide the image into a plurality of regions;
conduct character identification operations on each of the plurality of regions;
determine, among the plurality of regions, a label region having a highest character density, wherein the highest character density corresponds to a greatest number of characters in a preset unit area; and
identify the product based on information on the label region.
7. The one or more computer storage media of claim 6 , the instructions further cause the one or more computing devices to:
increase a contrast ratio of the label region; and
identify a text on the label region with the increased contrast ratio.
8. The one or more computer storage media of claim 7 , the instructions further cause the one or more computing devices to:
identify the product based on the text on the label region.
9. The one or more computer storage media of claim 6 , the instructions further cause the one or more computing devices to:
determine the label region having a plurality of preset characters related to the product.