CN115200311A - Method for identifying information of articles in refrigerator, refrigerator and computer storage medium - Google Patents
Method for identifying information of articles in refrigerator, refrigerator and computer storage medium Download PDFInfo
- Publication number
- CN115200311A CN115200311A CN202210741700.0A CN202210741700A CN115200311A CN 115200311 A CN115200311 A CN 115200311A CN 202210741700 A CN202210741700 A CN 202210741700A CN 115200311 A CN115200311 A CN 115200311A
- Authority
- CN
- China
- Prior art keywords
- recognition
- article
- character
- information
- identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 241001300198 Caperonia palustris Species 0.000 claims abstract description 3
- 235000000384 Veronica chamaedrys Nutrition 0.000 claims abstract description 3
- 235000004522 Pentaglottis sempervirens Nutrition 0.000 claims description 34
- 240000004050 Pentaglottis sempervirens Species 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012015 optical character recognition Methods 0.000 claims description 5
- 235000013305 food Nutrition 0.000 description 12
- 239000000463 material Substances 0.000 description 12
- 238000001514 detection method Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 3
- 235000013361 beverage Nutrition 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 235000013365 dairy product Nutrition 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000011194 food seasoning agent Nutrition 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 235000015067 sauces Nutrition 0.000 description 1
- 235000013618 yogurt Nutrition 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/003—Arrangement or mounting of control or safety devices for movable devices
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D29/00—Arrangement or mounting of control or safety devices
- F25D29/005—Mounting of control devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/68—Food, e.g. fruit or vegetables
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F25—REFRIGERATION OR COOLING; COMBINED HEATING AND REFRIGERATION SYSTEMS; HEAT PUMP SYSTEMS; MANUFACTURE OR STORAGE OF ICE; LIQUEFACTION SOLIDIFICATION OF GASES
- F25D—REFRIGERATORS; COLD ROOMS; ICE-BOXES; COOLING OR FREEZING APPARATUS NOT OTHERWISE PROVIDED FOR
- F25D2500/00—Problems to be solved
- F25D2500/06—Stock management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Thermal Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
Abstract
The invention discloses a method for identifying information of articles in a refrigerator, the refrigerator and a computer storage medium, wherein the method comprises the following steps: acquiring a bird-eye view image of the space in the bottle seat of the refrigerator; locating a character area on the upper surface of each article in the aerial view image; constructing recognition frames, wherein the recognition frames correspond to the character areas on the upper surface of an article, and each recognition frame contains all character information in the corresponding character area; extracting the identification frames, keeping the shapes of the identification frames unchanged, and splicing the identification frames; constructing a region to be identified containing all identification frames; and identifying character information in the area to be identified. The invention can output a plurality of character information by one-time recognition algorithm, thereby improving the efficiency of the recognition algorithm.
Description
Technical Field
The invention relates to the field of refrigerating devices, in particular to a method for identifying information of articles in a refrigerator, the refrigerator and a computer storage medium.
Background
With the development of appliance intellectualization, identifying internal articles has been a necessary function for intelligent refrigerators. Generally, in order to identify articles stored in a refrigerator, one or more cameras are installed inside the refrigerator for collecting photos of the articles in the refrigerator, and the collected photos are identified and then sent to a user terminal for a user to view. The camera is arranged above the article, so that the problem that the article is shielded mutually can be avoided, and the accuracy of article information identification is improved.
However, there are many problems in implementing the intelligent refrigerator, for example, there are text messages for identifying the articles in the bottle holders of the refrigerator, including article names, production dates, expiration dates, and so on. The existing method is to take the whole space image in the bottle seat of the refrigerator into an algorithm to position the specific position of the article character information on the image, and then identify the article character information and then identify the next article character information. When the number of articles in the bottle seat of the refrigerator is large, the time consumption of the method for identifying articles one by one is multiplied, and the identification efficiency is low.
Disclosure of Invention
The invention aims to provide an article information identification method in a refrigerator, the refrigerator and a computer storage medium.
In order to achieve one of the above objects, an embodiment of the present invention provides a method for identifying information on articles in a refrigerator, including the steps of:
acquiring a bird-eye view image of the space in the bottle seat of the refrigerator;
locating a character area on the upper surface of each article in the aerial view image;
constructing recognition frames, wherein the recognition frames correspond to the character areas on the surface of an article, and each recognition frame contains all character information in the corresponding character area;
extracting the identification frames, keeping the shapes of the identification frames unchanged, and splicing the identification frames;
constructing a region to be identified containing all the identification frames;
and identifying character information in the area to be identified.
As a further improvement of an embodiment of the present invention, the positioning of the character area on the upper surface of the article in the bird's eye view image specifically includes:
and positioning a character area on the upper surface of the article in the bird's-eye view image by using a character positioning algorithm.
As a further improvement of an embodiment of the present invention, the extracting the identification frames, maintaining the shapes of the identification frames unchanged, and splicing the identification frames specifically includes:
keeping the relative position relation of each recognition frame in the bird's eye view image unchanged, and extracting each recognition frame;
fixing the position of one recognition frame unchanged, moving all other recognition frames towards the direction of the recognition frame in sequence for splicing, and stopping moving when the recognition frame moves to be in contact with another recognition frame.
As a further improvement of an embodiment of the present invention, the extracting the identification frames, maintaining the shapes of the identification frames unchanged, and splicing the identification frames specifically includes:
and tightly splicing all the identification frames in sequence along the transverse direction and in sequence along the longitudinal direction.
As a further improvement of an embodiment of the present invention, the constructing a region to be identified including the identification frame specifically includes:
constructing the area to be identified in a rectangular structure;
and taking the maximum value of the overall length of all the spliced identification frames in the horizontal direction as the length of the area to be identified, and taking the maximum value of the overall length of all the spliced identification frames in the vertical direction as the width of the area to be identified.
As a further improvement of an embodiment of the present invention, the recognizing the character information of the area to be recognized specifically includes:
and identifying all character information in the area to be identified by using an OCR (optical character recognition) algorithm.
As a further improvement of an embodiment of the present invention, the method further comprises:
the recognition results are in one-to-one correspondence to each recognition frame, and character information in each recognition frame is obtained;
and acquiring character information of the upper surface of each article in the bird's-eye view image corresponding to the character area of the upper surface of the article in the bird's-eye view image.
As a further improvement of an embodiment of the present invention, the recognition results are one-to-one corresponding to each recognition frame, and character information in each recognition frame is obtained; corresponding to the character area on the upper surface of the article in the bird's-eye view image, obtaining the character information on the upper surface of each article in the bird's-eye view image, and specifically comprising:
detecting the content of date information in the character information, corresponding the date information to each recognition frame, and obtaining the date information in each recognition frame;
and obtaining the date information of the upper surface of each article in the bird's-eye view image according to the character area corresponding to the upper surface of the article in the bird's-eye view image of each recognition frame.
The present invention provides a refrigerator, comprising: a bottle holder, a camera, a memory and a processor, wherein,
the camera is arranged in the middle of the top of the bottle seat and is vertically arranged downwards;
the bottom of the bottle seat is used for placing articles;
the memory stores a computer program operable on the processor, and the processor implements the steps of the method for identifying information on an object in a refrigerator as described in any one of the above embodiments when executing the program.
The present invention also provides a computer storage medium, in which a computer program is stored, which when executed causes an apparatus of the computer storage medium to execute the steps according to the method for identifying information about an object in a refrigerator as described in any one of the above embodiments.
Compared with the prior art, the invention respectively constructs a recognition frame in the character area on the upper surface of each article in the bottle seat, extracts all the recognition frames constructed in the aerial image and keeps the shapes of the recognition frames unchanged, splices the recognition frames to form an area to be recognized, recognizes the character information in the area to be recognized, can output a plurality of character information through a recognition algorithm once, and improves the efficiency of the recognition algorithm.
Drawings
Fig. 1 is a flowchart illustrating a method for identifying information on an object in a refrigerator according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a bird's eye view image in a bottle seat of a refrigerator obtained by photographing in an embodiment of the present invention.
Fig. 3-7 are schematic diagrams of the extracted identification frame splicing process in an embodiment of the present invention.
Fig. 8 is a schematic structural diagram of constructing a region to be identified in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to the detailed description of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art without any inventive work based on the embodiments in the present application are within the scope of protection of the present application.
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
For convenience in explanation, the description herein uses terms indicating relative spatial positions, such as "upper," "lower," "rear," "front," and the like, to describe one element or feature's relationship to another element or feature as illustrated in the figures. The term spatially relative position may encompass different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures is turned over, elements described as "below" or "above" other elements or features would then be oriented "below" or "above" the other elements or features. Thus, the exemplary term "below" can encompass both a spatial orientation of below and above.
Because the information such as the production date, the shelf life and the like of the food materials in the refrigerator is scattered and unfixed, and some food materials are even arranged at the bottom of the food materials (for example, some yogurt production dates are arranged at the bottom), the food materials are not convenient to identify and uniformly manage, when the food materials are stored in the refrigerator, a label with uniform format and containing basic information of the food materials can be printed on the food materials, and the label is arranged at a fixed position of the food materials (for example, the label is pasted on the top of the food materials), so that a computer and a user can obtain the information such as the name and the production date of the food materials through the label, and the computer and the user can conveniently manage the food materials.
As shown in fig. 1, the present embodiment provides a method for identifying information on articles in a refrigerator, including the steps of:
s1: a bird's-eye view image 1 of the space in the bottle seat of the refrigerator is obtained.
In the present embodiment, the camera is provided at the top of the bottle base, and the bird's-eye image is obtained by imaging the article from above, and in order to avoid the mutual shielding between the articles in the bottle base and to prevent the article information from being adversely detected and recognized, it is preferable that the camera is provided at an intermediate position of the top of the bottle base.
Of course, in other embodiments of the present invention, two or more cameras may be disposed in the bottle seat for obtaining two or more bird's-eye images of the space inside the bottle seat of the refrigerator captured at different angles, or the camera may be disposed at the bottom of the bottle seat and vertically disposed downward for capturing information about the articles in the bottle seat located therebelow.
S2: and positioning the character area on the upper surface of each article in the bird's-eye view image.
For example, as shown in fig. 2, a schematic view of a bird's eye view image of the space in the bottle holder of the refrigerator captured in the present embodiment is shown, in practical applications, only two rows of articles can be put down in the horizontal direction in the bottle holder of the refrigerator, as described above, in order to facilitate the identification and unified management of the food materials in the articles in the bottle holder of the refrigerator, the article type information, the article production date, the shelf life and other information are generally printed on the top of the top cover of the articles.
Specifically, the character positioning algorithm is utilized to position the character area on the upper surface of the article in the bird's-eye view image, that is, the character positioning algorithm can be utilized to directly position the specific position where the article type character information, the article production date, the quality guarantee period and other digital information are positioned on the upper surface of the article placed in the bottle seat. Here, the character positioning algorithm is the prior art, and will not be described in detail herein.
Further, before performing step S2, the method further includes the steps of: and positioning the position of the article in the aerial view image, and identifying article information. In the subsequent identification method, after the specific character information of the upper surface of each article is obtained, the article type information corresponding to each character area and the position information in the bottle seat where the article is located can be associated, so that the information of the articles placed at different positions in the bottle seat, including the article type information, the article number information and the like, can be obtained.
Specifically, a Yolo V4 target detection algorithm may be used to calibrate a detection frame corresponding to each article in the bird's-eye view image, and the position of the article in the detection frame in the bottle seat is obtained corresponding to the calibrated position of each detection frame. And detecting and identifying the outer contour type of the article in each detection frame, detecting and identifying article information by using a Yolo algorithm, an SSD algorithm or a traditional detection algorithm and the like, identifying article category information by using a deep learning algorithm according to the top surface image of the article, and acquiring the category information of the article corresponding to each detection frame.
For example, in the present embodiment, the articles may be classified into a bottled article, a canned article, a boxed article, and other articles, wherein the bottled article has a bottle cap, which is an article with a distinct bottle cap such as a bottled beverage; the canned goods have circular outline in top view and are basically cylindrical goods such as canned beverages, seasoning sauce and the like which are packaged outside; the boxed article has a parallelogram-like shape in a top view, and is an article which is basically cuboid or cube and is externally packaged, such as boxed dairy products; items not belonging to the above three categories are classified as other items.
In the bird's-eye view image shown in fig. 2, the articles a1, a2, and a3 are bottled articles, the articles b1, b2, and b3 are canned articles, and the articles c1 and c2 are boxed articles.
S3: constructing recognition frames 1, wherein the recognition frames 1 correspond to the character areas on the upper surface of an object, and each recognition frame 1 contains all character information in the corresponding character area.
Specifically, after the character areas on the upper surface of each article are located, rectangular recognition frames 1 are constructed for each character area, and each recognition frame 1 contains all information in the corresponding character area.
S4: extracting the identification frames 1, keeping the shapes of the identification frames 1 unchanged, and splicing the identification frames 1.
Since it is often difficult to place labels having characters on the upper surfaces of articles in a fixed direction when placing various articles in a bottle holder, there is an angular difference between the identification frames 1 constructed corresponding to the character areas on the upper surfaces of the articles. The recognition frame c11 of the article c1 in the figure is a rectangular structure constructed in the horizontal direction, the recognition frame c21 of the article c2 placed on the right side of the article c1 is a rectangular structure constructed in the vertical direction, and the recognition frame 1 constructed at the character area on the upper surface of the bottled articles and canned articles in the figure is constructed to be inclined at a certain angle with respect to the recognition frames c11, c21 of the articles c1 and c 2.
As shown in fig. 3, the recognition frames 1 constructed in the character areas on the upper surface of each article in the bird's eye view image are extracted, the shapes, positions, and relative inclination angles of the recognition frames 1 are kept unchanged, and the recognition frames 1 are placed on the same recognition plane to perform the algorithm recognition of the unicode information.
In order to further improve the efficiency of the recognition algorithm and further reduce the size of the area to be recognized, in the embodiment of the invention, all recognition frames 1 are fixed in the arrangement sequence in the bird's-eye view image, the position of one recognition frame is unchanged, other recognition frames are sequentially moved towards the direction of the recognition frame for splicing, and the movement is stopped when the recognition frame is moved to be in contact with the other recognition frame.
For example, as shown in fig. 4 to 7, the position of the identification frame c11 corresponding to the article c1 may be controlled to be unchanged, and the identification frame c21 of the article c2 may be controlled to move towards the identification frame c11 until the identification frame c21 contacts the identification frame c 11; controlling the identification frame b11 of the article b1 to move towards the identification frame c21 again until the article b is contacted with the identification frame c 21; the identification frame a11 of the article a1 is controlled to move towards the identification frame b11 until the contact with the identification frame b11 is achieved. Forming a splicing area a.
The identification frame 1 corresponding to the articles under the bottle seat is controlled to move and splice by the same method, the position of the identification frame b21 corresponding to the article b2 is firstly controlled to be kept still, and the identification frame a21 corresponding to the article a2 is controlled to move towards the direction of the identification frame b21 until the identification frame a21 is contacted with the article b 21; controlling the identification frame b31 corresponding to the article b3 to move towards the identification frame a21 until the identification frame b21 is contacted; and controlling the identification frame a31 corresponding to the article a3 to move towards the identification frame b31 until the identification frame b31 is contacted. Forming a splicing region B.
And keeping the position of the splicing area A still, and controlling the splicing area B to move towards the direction of the splicing area A until an identification frame in the splicing area B is in contact with an identification frame in the splicing area A, namely, stopping the movement of the splicing area B, and when an identification frame B21 is in contact with an identification frame c11, stopping the movement of the splicing area B as shown in FIG. 7.
Of course, any one of the recognition frames in the same row may be kept stationary, another recognition frame may be controlled to move toward the recognition frame to form the splicing areas a and B, and then the recognition frames in the splicing areas a and B may be spliced in contact, which is not limited herein.
S5: an area to be identified 2 containing all the identification boxes 1 is constructed.
Specifically, the area to be recognized 2 in a rectangular structure is constructed, the maximum value of the overall length of all the recognition frames which are spliced in the horizontal direction is used as the length l of the area to be recognized 2, and the maximum value of the overall length of all the recognition frames which are spliced in the vertical direction is used as the width w of the area to be recognized 2.
As shown in fig. 8, the distance in the horizontal direction between the recognition box c11 positioned on the leftmost side and the recognition box a31 positioned on the rightmost side in the spliced region is taken as the length l of the region to be recognized 2, and the distance in the vertical direction between the recognition box a21 positioned on the lowermost side and the recognition box a11 positioned on the uppermost side in the spliced region is taken as the width w of the region to be recognized 2.
Of course, the smaller the area of the constructed region 2 to be recognized is, the higher the algorithm recognition efficiency for the region 2 to be recognized in the subsequent operation is, so in another embodiment of the present invention, all the recognition frames 1 are closely spliced in sequence along the transverse direction and in sequence along the longitudinal direction. Specifically, in this embodiment, the arrangement order of the recognition frames 1 does not need to be arranged according to the relative positional relationship in the bird's eye view image, but only the fact that there is at least point contact and no overlapping area between the recognition frames 1 and the recognition frames 1 spliced with the recognition frames 1 is ensured, and then the region to be recognized 2 is constructed for the splicing area.
Further, in this embodiment, when all the identification frames 1 are partially arranged in sequence along the transverse direction to perform the tight splicing processing, and another part of the identification frames 1 are sequentially subjected to the tight splicing processing along the longitudinal direction, so that the minimum area of the constructed region 2 to be identified is the optimal identification scheme of the present application.
S6: and identifying character information in the area 2 to be identified.
Specifically, the constructed region 2 to be recognized is input into a system for algorithm recognition, and all character information in the region 2 to be recognized is recognized by using an OCR recognition algorithm.
Further, the identification method in the present embodiment further includes the steps of:
s7: and (5) enabling the recognition results to correspond to each recognition frame 1 one by one, and obtaining character information in each recognition frame 1.
S8: and acquiring character information of the upper surface of each article in the bird's-eye view image corresponding to the character area of the upper surface of the article in the bird's-eye view image.
The character information in the recognition result specifically includes character information and digital information of the upper surface of the article, and the digital information is date information of the upper surface of the article.
Specifically, after all the character information in the region to be recognized 2 is obtained, the content of the date information in all the character information is detected, the date information is associated with each recognition frame 1, and the date information in each recognition frame 1 is obtained.
More specifically, the date information of the upper surface of each article in the bird's-eye view image is obtained from the character area of each recognition frame 1 corresponding to the upper surface of the article in the bird's-eye view image.
The obtained position of each article in the bottle seat and the type information of each article are combined, and the data such as the corresponding type information, the position information, the date information (production date, quality guarantee period and the like) and the like of each article placed in the bottle seat of the refrigerator can be pushed to a user.
The invention also provides a refrigerator which comprises a bottle seat, a camera, a memory and a processor.
Further, the bottle seat comprises a bottle seat top, a bottle seat bottom and a bottle seat wall surface, and the camera is arranged in the middle of the bottle seat top and vertically arranged downwards.
The bottom of the bottle holder is used for placing articles, the memory stores a computer program which can run on the processor, and the processor executes the program to realize the steps of the method for identifying the article information in the refrigerator in any one of the above embodiments.
The present invention also provides a computer storage medium, in which a computer program is stored, and the computer program is executed to cause an apparatus of the computer storage medium to execute the steps of any one of the above methods for identifying information about articles in a refrigerator.
In summary, in the invention, the character areas on the upper surface of each article in the bottle seat are respectively constructed into one recognition frame, all the recognition frames constructed in the bird's-eye view image are extracted and kept unchanged in shape, the recognition frames are spliced to form an area to be recognized, then the character information in the area to be recognized is recognized, a plurality of character information can be output through one-time recognition algorithm, and the efficiency of the recognition algorithm is improved.
It should be understood that although the present description refers to embodiments, not every embodiment contains only a single technical solution, and such description is for clarity only, and those skilled in the art should make the description as a whole, and the technical solutions in the embodiments can also be combined appropriately to form other embodiments understood by those skilled in the art.
The above-listed detailed description is merely a detailed description of possible embodiments of the present invention, and it is not intended to limit the scope of the invention, and equivalent embodiments or modifications made without departing from the technical spirit of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A method for identifying information of articles in a refrigerator is characterized by comprising the following steps:
acquiring a bird-eye view image of the space in the bottle seat of the refrigerator;
positioning a character area on the upper surface of each article in the aerial view image;
constructing recognition frames, wherein the recognition frames correspond to the character areas on the upper surface of an article, and each recognition frame contains all character information in the corresponding character area;
extracting the identification frames, keeping the shapes of the identification frames unchanged, and splicing the identification frames;
constructing a region to be identified containing all identification frames;
and identifying character information in the area to be identified.
2. The method for identifying information of articles in a refrigerator according to claim 1, wherein the locating the character area on the upper surface of the article in the bird's eye view image specifically comprises:
and positioning the character area on the upper surface of the article in the aerial view image by utilizing a character positioning algorithm.
3. The method for identifying information about articles in a refrigerator according to claim 2, wherein the extracting the identification frames, keeping the shapes of the identification frames unchanged, and splicing the identification frames specifically comprises:
keeping the relative position relation of each recognition frame in the bird's eye view image unchanged, and extracting each recognition frame;
fixing the position of one recognition frame unchanged, moving all other recognition frames towards the direction of the recognition frame in sequence for splicing, and stopping moving when the recognition frame moves to contact with another recognition frame.
4. The method for identifying information about articles in a refrigerator according to claim 2, wherein the extracting the identification frames, keeping the shapes of the identification frames unchanged, and splicing the identification frames specifically comprises:
and tightly splicing all the identification frames in sequence along the transverse direction and in sequence along the longitudinal direction.
5. The method for identifying information of articles in a refrigerator according to claim 3 or 4, wherein the constructing the area to be identified including the identification frame specifically comprises:
constructing the area to be identified in a rectangular structure;
and taking the maximum value of the overall length of all the spliced identification frames in the horizontal direction as the length of the area to be identified, and taking the maximum value of the overall length of all the spliced identification frames in the vertical direction as the width of the area to be identified.
6. The method for identifying information on articles in a refrigerator as claimed in claim 5, wherein the identifying the character information of the area to be identified specifically comprises:
and identifying all character information in the area to be identified by using an OCR (optical character recognition) algorithm.
7. The method for identifying information on articles in a refrigerator according to claim 6, further comprising:
the recognition results are in one-to-one correspondence to each recognition frame, and character information in each recognition frame is obtained;
and acquiring character information of the upper surface of each article in the bird's-eye view image corresponding to the character area of the upper surface of the article in the bird's-eye view image.
8. The method for identifying information on articles in a refrigerator as claimed in claim 7, wherein the identification result is one-to-one associated with each identification frame to obtain character information in each identification frame; corresponding to the character area on the upper surface of the article in the bird's-eye view image, obtaining the character information on the upper surface of each article in the bird's-eye view image, and specifically comprising:
detecting the content of date information in the character information, corresponding the date information to each recognition frame, and obtaining the date information in each recognition frame;
and obtaining the date information of the upper surface of each article in the bird's-eye view image according to the character area of the upper surface of each article in the bird's-eye view image corresponding to each recognition frame.
9. A refrigerator, comprising: a bottle seat, a camera, a memory and a processor, which is characterized in that,
the camera is arranged in the middle of the top of the bottle seat and is vertically arranged downwards;
the bottom of the bottle seat is used for placing articles;
the memory stores a computer program operable on the processor, and the processor implements the steps of the method for identifying information on articles in a refrigerator according to any one of claims 1 to 8 when executing the program.
10. A computer storage medium in which a computer program is stored, wherein the computer program when executed causes an apparatus of the computer storage medium to perform the steps of the method for identifying information on articles in a refrigerator according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210741700.0A CN115200311A (en) | 2022-06-27 | 2022-06-27 | Method for identifying information of articles in refrigerator, refrigerator and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210741700.0A CN115200311A (en) | 2022-06-27 | 2022-06-27 | Method for identifying information of articles in refrigerator, refrigerator and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115200311A true CN115200311A (en) | 2022-10-18 |
Family
ID=83578502
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210741700.0A Pending CN115200311A (en) | 2022-06-27 | 2022-06-27 | Method for identifying information of articles in refrigerator, refrigerator and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115200311A (en) |
-
2022
- 2022-06-27 CN CN202210741700.0A patent/CN115200311A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10572757B2 (en) | User interface for object detection and labeling | |
| US11151427B2 (en) | Method and apparatus for checkout based on image identification technique of convolutional neural network | |
| CN111340126B (en) | Article identification method, apparatus, computer device, and storage medium | |
| EP3259068B1 (en) | Detection of barcode tag conditions on sample tubes | |
| CN111507253B (en) | Display article auditing method and device based on artificial intelligence | |
| TW201945995A (en) | Smart equipment and commodity counting method, device and equipment | |
| CN105678322A (en) | Sample labeling method and apparatus | |
| CN109635705B (en) | Commodity identification method and device based on two-dimensional code and deep learning | |
| CN109448047A (en) | Shelf are distributed drawing generating method, information acquisition method, apparatus and system | |
| US20210279784A1 (en) | Analysis method and system for the item on the supermarket shelf | |
| US11367270B2 (en) | Recognition apparatus and method | |
| AU2019396253B2 (en) | Method, system and apparatus for auxiliary label detection and association | |
| CN111144417A (en) | Intelligent container small target detection method and detection system based on teacher student network | |
| CN115200311A (en) | Method for identifying information of articles in refrigerator, refrigerator and computer storage medium | |
| WO2021091481A1 (en) | System for object identification and content quantity estimation through use of thermal and visible spectrum images | |
| CN116580390A (en) | Price tag content acquisition method, price tag content acquisition device, storage medium and computer equipment | |
| CN109101917A (en) | Mask method, training method, the apparatus and system identified again for pedestrian | |
| CN113901934A (en) | Intelligent visual detection method, system and device for large infusion package product | |
| WO2023124088A1 (en) | Method for identifying information of articles in refrigerator, and refrigerator | |
| CN113916899A (en) | Method, system and device for detecting large soft infusion bag product based on visual identification | |
| CN113627415A (en) | Method and device for determining target object placement information | |
| CN111738183B (en) | Data labeling method and device | |
| CN112329841A (en) | Image processing method, image processing device, electronic equipment and computer readable medium | |
| CN110738260A (en) | Method, device and equipment for detecting placement of space boxes of retail stores of types | |
| CN115953635B (en) | Sorting method, AR (augmented reality) glasses and system for multi-class targets |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |