阅读说明：本技术 一种后厨色标识别及预警方法 (Kitchen color code identification and early warning method ) 是由 郑宏弟 聂立功 于 2020-12-25 设计创作，主要内容包括：本发明公开了一种后厨色标识别及预警方法,包括以下步骤：S1,从厨房摄像头获得实时厨房场景图片,发送至图片处理服务器；S2,图片处理服务器将图片发送到颜色框和抹布乱放识别服务器进行处理；S3,颜色框和抹布乱放识别服务器对发过来的图片进行颜色特征提取：使用计算机视觉技术对厨房场景图片进行处理,将RGB图片信息格式转换为hsv信息格式,通过不同颜色的色相阈值范围,提取不同颜色的特征矩阵,然后通过阈值二值化进行加强颜色特征；S4,通过S3提取的不同颜色的特征信息,通过计算机视觉技术中的轮廓提取出不同颜色的位置信息并进行标记映射,通过排序算法从而获取相同颜色的框或抹布是否在一起,将与正确放置位置对比错误的的位置信息标注发出预警提示。(The invention discloses a kitchen color code identification and early warning method, which comprises the following steps: s1, obtaining a real-time kitchen scene picture from a kitchen camera, and sending the real-time kitchen scene picture to a picture processing server; s2, the picture processing server sends the pictures to the color frame and rag misplacing identification server for processing; s3, the color frame and rag random placement recognition server extracts the color features of the sent pictures: processing a kitchen scene picture by using a computer vision technology, converting an RGB picture information format into an hsv information format, extracting feature matrixes of different colors through hue threshold ranges of the different colors, and then enhancing color features through threshold binarization; and S4, extracting position information of different colors through the characteristic information of different colors extracted in S3 and the outline in the computer vision technology, marking and mapping, obtaining whether frames or cleaning cloths of the same color are together through a sorting algorithm, and marking the position information which is wrongly compared with the correct placement position to give an early warning prompt.)

1. A kitchen color code identification and early warning method is characterized by comprising the following steps:

s1, obtaining a real-time kitchen scene picture from a kitchen camera, and sending the real-time kitchen scene picture to a picture processing server;

s2, the picture processing server sends the pictures to the color frame and rag misplacing identification server for processing;

s3, the color frame and rag random placement recognition server extracts the color features of the sent pictures: processing a kitchen scene picture by using a computer vision technology, converting an RGB picture information format into an hsv information format, extracting feature matrixes of different colors through hue threshold ranges of the different colors, and then enhancing color features through threshold binarization;

and S4, extracting position information of different colors through the characteristic information of different colors extracted in S3 and the outline in the computer vision technology, marking and mapping, acquiring whether frames or cleaning cloths of the same color are together through a sorting algorithm, and marking the position information which is wrongly compared with the correct placement position to send out an early warning prompt.

2. The kitchen color scale identification and early warning method of claim 1, wherein in S3, the characteristic matrix of different colors is extracted according to hue threshold ranges of different colors as follows:

H. s, V is hue, saturation and lightness respectively, H is used for representing angle measurement, and the value range is 0-360 degrees; s represents the degree that the color is close to the spectral color, the value range is 0-255, and the larger the value is, the more saturated the color is; and V brightness represents the brightness degree of the color, the value range is 0-255, the characteristic information of different colors is extracted according to different values of the different colors in the hsv, and the color frame and the rag random placement recognition server are subjected to complete color characteristic classification on the sent picture through characteristic extraction.

Technical Field

The invention belongs to the technical field of image recognition, and particularly relates to a kitchen color code recognition and early warning method.

Background

With the importance of society on the safety of kitchen food, relevant kitchen safety management policies are provided in various regions, color code management is an important management system, and kitchen workers are required to mark facilities, articles and tools related to a catering service link by using marks with different colors, and the facilities, articles and tools are used in a positioning, storing and classifying manner.

In order to standardize the application of color code management in a kitchen and prevent cross contamination of workers in a food processing process, the color frame and the rag have the same color and are placed by the identification technology, so that whether the color frame and the rag are placed according to the color code management standard can be monitored in real time, the identified violation behavior is early warned to a manager, and the intelligent supervision of the color code management is realized.

The existing video supervision does not carry out detailed analysis on the same color placement recognition scenes of a color frame and a cleaning cloth, and has the problems of complex analysis algorithm, insensitivity to color judgment and the like.

Disclosure of Invention

In view of the technical problems, the invention provides a kitchen color code identification and early warning method, which is used for judging whether a color frame and a cleaning cloth have the problem of illegal placement by analyzing the color value of a placement area by using a video AI analysis technology.

In order to solve the technical problems, the invention adopts the following technical scheme:

a kitchen color code identification and early warning method comprises the following steps:

s1, obtaining a real-time kitchen scene picture from a kitchen camera, and sending the real-time kitchen scene picture to a picture processing server;

s2, the picture processing server sends the pictures to the color frame and rag misplacing identification server for processing;

s3, the color frame and rag random placement recognition server extracts the color features of the sent pictures: processing a kitchen scene picture by using a computer vision technology, converting an RGB picture information format into an hsv information format, extracting feature matrixes of different colors through hue threshold ranges of the different colors, and then enhancing color features through threshold binarization;

and S4, extracting position information of different colors through the characteristic information of different colors extracted in S3 and the outline in the computer vision technology, marking and mapping, acquiring whether frames or cleaning cloths of the same color are together through a sorting algorithm, and marking the position information which is wrongly compared with the correct placement position to send out an early warning prompt.

Preferably, in S3, the specific characteristic matrix extracted from different colors according to the hue threshold ranges of the different colors is as follows:

H. s, V is hue, saturation and lightness respectively, H is used for representing angle measurement, and the value range is 0-360 degrees; s represents the degree that the color is close to the spectral color, the value range is 0-255, and the larger the value is, the more saturated the color is; and V brightness represents the brightness degree of the color, the value range is 0-255, the characteristic information of different colors is extracted according to different values of the different colors in the hsv, and the color frame and the rag random placement recognition server are subjected to complete color characteristic classification on the sent picture through characteristic extraction.

The invention has the following beneficial effects: can put the color frame and the rag of all kinds of colours such as red, green, blue, yellow, purple in the kitchen color classification region as required and realize intelligent analysis to almost zero artifical supervision cost accomplishes the color code management standard supervision of kitchen.

Drawings

FIG. 1 is a flowchart illustrating steps of a kitchen color scale recognition and warning method according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating an original image to be analyzed according to an embodiment of the present invention;

FIG. 3 is a schematic diagram of the color distribution of FIG. 2 after analysis;

FIG. 4 is a schematic view of the correct placement of wipes corresponding to FIG. 2.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Referring to fig. 1, a flowchart illustrating steps of a kitchen color scale identification and early warning method according to an embodiment of the present invention includes the following steps:

s1, obtaining a real-time kitchen scene picture from a kitchen camera, and sending the real-time kitchen scene picture to a picture processing server;

s2, the picture processing server sends the pictures to the color frame and rag misplacing identification server for processing;

s3, the color frame and rag random placement recognition server extracts the color features of the sent pictures: processing a kitchen scene picture by using a computer vision technology, converting an RGB picture information format into an hsv information format, extracting feature matrixes of different colors through hue threshold ranges of the different colors, and then enhancing color features through threshold binarization;

and S4, extracting position information of different colors through the characteristic information of different colors extracted in S3 and the outline in the computer vision technology, marking and mapping, acquiring whether frames or cleaning cloths of the same color are together through a sorting algorithm, and marking the position information which is wrongly compared with the correct placement position to send out an early warning prompt.

In a specific application example, in S3, the specific feature matrix extracted from different colors according to the hue threshold ranges of the different colors is as follows:

H. s, V is hue, saturation and lightness respectively, H is used for representing angle measurement, and the value range is 0-360 degrees; s represents the degree that the color is close to the spectral color, the value range is 0-255, and the larger the value is, the more saturated the color is; and V brightness represents the brightness degree of the color, the value range is 0-255, the characteristic information of different colors is extracted according to different values of the different colors in the hsv, and the color frame and the rag random placement recognition server are subjected to complete color characteristic classification on the sent picture through characteristic extraction. The following table is the hsv format information for different colors:

referring to fig. 2, a picture to be processed is transmitted from a picture processing server in a specific application example, the color sequence of the rag is "red, blue, green", and the color block table is shown in fig. 3 by converting and analyzing the picture, the color block table is shown in fig. 4 by correct color partition, the color sequence is "red, blue, green, and green", and the order of the fourth green rag and the sixth blue rag is wrong by comparative analysis.

Through the intelligent analysis of the color frames and the rags of various colors such as red, green, blue, yellow, purple and the like in the kitchen color classification area, the color scale management standard supervision of the kitchen can be completed with nearly zero manual supervision cost.

It is to be understood that the exemplary embodiments described herein are illustrative and not restrictive. Although one or more embodiments of the present invention have been described with reference to the accompanying drawings, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the following claims.