Meal image feature-based identification and pricing system

A technology of image features and meals, which is applied in the field of identification and pricing systems, can solve problems such as rising operating costs, unsatisfactory sanitation and efficiency, and achieve the effect of convenient restaurant renovation and low operating costs

Inactive Publication Date: 2018-02-23
杨冠群
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the self-service settlement mode for this type of customers, some restaurants have to rely on the waiter to undertake the meal identification and pricing link. The waiter will tell the customer the total price after visual recognition and mental calculation, and then the customer will scan the code to pay. Therefore, there are still hygiene problems. The efficiency is unsatisfactory; another type of restaurant can automatically identify

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Meal image feature-based identification and pricing system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0020] Example 1. Place 3 white plates and 1 small gray bowl in a deep red plastic tray, which respectively contain "fish-flavored shredded pork, braised lion's head, scrambled eggs with green pepper, and white rice". The test parameters output by the system after starting the recognition are:

[0021] Serial number: 1. Name: Yuxiang pork shreds, similarity similarity: 91.65%, similarity similarity of other types: 86.9%;

[0022] Serial number: 2. Name: braised lion head, similarity degree: 79%, similarity degree of other similarities: 53.2%;

[0023] Serial number: 3. Name: Scrambled eggs with green peppers, similarity of similarity: 90.4%, similarity of other similarities: 72.1%;

[0024] Serial number: 4. Name: white rice, similarity similarity: 98.95%, similarity similarity of other similarities: 65.55%;

[0025] Recognition time: 1859ms.

[0026] The recognition result of Example 1 shows that although the characteristics of the recognized meal have a certain intra-class difference ...

Example Embodiment

[0027] In Example 2, 4 white dishes are placed in a deep red plastic tray, and each dish contains 1 serving of "green vegetable meatballs" taken from different areas of the same dish. The test parameters output by the system after starting the recognition are:

[0028] Serial number: 1. Name: vegetable meatballs, similarity degree: 92.15%, similarity degree of other similarities: 74.95%;

[0029] Serial number: 2. Name: Vegetable Meatballs, Similarity Degree: 89.9%, Similarity Degree of Other Similarity: 64.6%;

[0030] Serial number: 3. Name: Vegetable meatballs, similarity degree: 90.4%, similarity degree of other similarities: 71.7%;

[0031] Serial number: 4. Name: Vegetable Meatballs, Similarity Degree: 90.7%, Similarity Degree of Other Similarity: 71.5%;

[0032] Recognition time: 1906ms.

[0033] The recognition result of Example 2 shows that although there is a maximum of 2.25% difference between the 4 meals taken from different regions of the same variety and the 4 similar samp...

Example Embodiment

[0034] In Example 3, a white plate with a diameter of 25 cm is placed in a deep red plastic tray, and 4 kinds of non-dish dishes "green vegetable meatballs, fish-flavored shredded pork, green pepper shredded pork, and rice" are placed on the plate without overlapping. The test parameters output by the system after starting the recognition are:

[0035] Serial number: 1. Name: vegetable meatballs, similarity degree: 87.35%, similarity degree of other similarities: 83.65%;

[0036] Serial number: 2. Name: Yuxiang pork shreds, similarity degree: 78.15%, similarity degree of other similarities: 70.6%;

[0037] Serial number: 3. Name: Shredded pork with green pepper, similarity degree: 90.2%, similarity degree of other similarities: 86.3%;

[0038] Serial number: 4. Name: White rice, similarity similarity: 90.7%, similarity similarity for other similarities: 83.05%;

[0039] Recognition time: 1906ms.

[0040] The recognition result of Example 3 shows that the system's recognition of 4 shared...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

PropertyMeasurementUnit
Diameteraaaaaaaaaa
Login to view more

Abstract

The invention discloses a meal image feature-based identification and pricing system. Online identification can be realized by performing comparison with inventory samples according to color and shapefeatures of an on-sale meal image snapshot on site by a camera; in combination with a pricing basis given by a background and a possibly needed meal weight, a payable amount is obtained; and a customer can finish settlement by applying a general electronic payment means. Automatic identification and pricing settlement of sold meals unrelated to utensils are realized, so that the convenience and cost performance of a settlement mode of a self-service restaurant are greatly improved.

Description

technical field [0001] The invention relates to an identification and pricing system based on image features of meals, which is used for meal identification and pricing without relying on feature information of bowls and dishes when paying in cafeterias, and can greatly improve the convenience and cost performance of this type of settlement mode. Background technique [0002] In recent years, cafeterias have quickly become the first choice for a large number of office workers to eat because of their hygienic and convenient advantages. In particular, the convenience of allowing customers to scan codes with their mobile phones in the settlement process has won wide acclaim from people. However, in the self-service settlement mode for this type of customers, some restaurants have to rely on the waiter to undertake the meal identification and pricing link. The waiter will tell the customer the total price after visual recognition and mental calculation, and then the customer will...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q30/02G06Q20/32G06Q50/12G06K9/46
CPCG06Q20/3274G06Q30/0283G06Q50/12G06V10/44G06V10/56
Inventor 杨冠群
Owner 杨冠群
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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