Supermarket commodity identification method based on deep learning
A deep learning, commodity technology, applied in the field of image processing, can solve problems such as information loss, inability to meet, and reduce recognition accuracy, and achieve the effect of improving accuracy and accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0027] ginseng figure 1 , to further describe in detail the implementation steps of the present invention.
[0028] Step 1. Product target area detection.
[0029] 1.1) Collect 3,000 pictures of shelves containing different commodities through mobile devices in major supermarkets;
[0030] 1.2) By manually labeling all commodity target windows and categories in the shelf picture, the commodity target area is expressed as (x 1 ,y 1 ,x 2 ,y 2 ), and then classify the products according to their shape and purpose. In this example, the products are divided into 31 categories: miscellaneous tools, bottled cleaning supplies, bottled beverages, bottled seasonings, bottled wine, bottled toiletries, bottled snacks, bagged seasonings, Snacks in bags, ingredients in bags, paper towels in bags, cleaning supplies in bags, daily necessities in bags, canned food, canned drinks, canned milk powder, canned wine, boxed snacks, boxed toys, boxed drinks, boxed Daily necessities, boxed toile...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap