CN114758194A - Automatic aquatic product pricing method for intelligent electronic scale - Google Patents
Automatic aquatic product pricing method for intelligent electronic scale Download PDFInfo
- Publication number
- CN114758194A CN114758194A CN202210468585.4A CN202210468585A CN114758194A CN 114758194 A CN114758194 A CN 114758194A CN 202210468585 A CN202210468585 A CN 202210468585A CN 114758194 A CN114758194 A CN 114758194A
- Authority
- CN
- China
- Prior art keywords
- aquatic product
- aquatic
- intelligent electronic
- model
- electronic scale
- 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 26
- 238000004321 preservation Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 17
- 238000012360 testing method Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 10
- 238000012795 verification Methods 0.000 claims description 7
- 239000013505 freshwater Substances 0.000 claims description 6
- 238000005303 weighing Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 230000004083 survival effect Effects 0.000 abstract 1
- 240000007651 Rubus glaucus Species 0.000 description 3
- 235000011034 Rubus glaucus Nutrition 0.000 description 3
- 235000009122 Rubus idaeus Nutrition 0.000 description 3
- 238000009360 aquaculture Methods 0.000 description 3
- 244000144974 aquaculture Species 0.000 description 3
- 241000252230 Ctenopharyngodon idella Species 0.000 description 2
- 241001596950 Larimichthys crocea Species 0.000 description 2
- 241001125843 Trichiuridae Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G19/00—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
- G01G19/40—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight
- G01G19/413—Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight using electromechanical or electronic computing means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an automatic aquatic product pricing method for an intelligent electronic scale, which comprises the following steps: constructing an aquatic product intelligent identification model, and obtaining a plurality of groups of aquatic product name results with the highest confidence; judging whether the aquatic product has size specification or fresh-keeping state difference; counting the number of pixel points occupied by the aquatic product in the picture to obtain the size specification of the aquatic product; judging the fresh-keeping state of the aquatic product according to the temperature; judging whether the proportion of pixel points occupied by the aquatic product in each sub-picture between every two pictures changes or not, and judging the death and the survival of the aquatic product; according to the recognition result, the unit price of the aquatic product is called, and then the price of the aquatic product is automatically calculated according to the weight. According to the invention, the same aquatic products with different sizes and specifications and different preservation states are distinguished by identifying the pixel point regions and judging the variation difference of the pixel points by separating the sub-pictures, and then the intelligent identification model of the aquatic products is matched, so that the identification capability of the intelligent electronic scale is obviously improved, and the automatic pricing of the intelligent electronic scale on the aquatic products is realized.
Description
Technical Field
The invention relates to the technical field of agricultural product circulation, in particular to an automatic aquatic product pricing method for an intelligent electronic scale.
Background
China is a fishery big country and a world-level aquaculture big country, and the total output value of the Chinese aquaculture in 2019 reaches 12572.4 billion yuan, accounting for 19 percent of the total agricultural output value. Therefore, aquaculture is one of the important sources of national economy in China. In the process of aquatic product circulation, aquatic products of different types and states have different economic values and use values, and in order to increase the market price of the aquatic products and ensure the economic benefit to the greatest extent, the aquatic product circulation process has an important process, namely aquatic product type identification.
At present, in the circulation process of aquatic products in China, the classification of the aquatic products mainly adopts a manual identification method, but the method not only needs to culture the identifiers for a long time, but also can bring different results to the identifiers with different qualities, so that the accuracy of the identification result cannot be ensured, and the method has the advantages of low intelligent degree, low efficiency, high labor intensity and rapid and accurate pricing disadvantage in the circulation process of the aquatic products.
Disclosure of Invention
The invention provides an automatic aquatic product pricing method for an intelligent electronic scale, which considers product price differences caused by size and specification differences and storage differences during sales of aquatic products in the market, solves the problem that the existing intelligent electronic scale cannot effectively identify the aquatic products with special differences, and greatly improves the accuracy of aquatic product identification.
The specific technical scheme is as follows:
an automatic aquatic product pricing method for an intelligent electronic scale comprises the following steps:
(1) inputting basic information and corresponding unit prices of all aquatic products consisting of aquatic product names, sizes and specifications and a fresh-keeping state into an intelligent electronic scale, collecting picture information of all aquatic products according to a size and specification classification standard based on the number of pixel points occupied by aquatic products in an image, introducing the picture information and the corresponding aquatic product name information into a model as a training set for model training, and constructing to obtain an aquatic product intelligent recognition model;
(2) acquiring image information, weight information and temperature information of aquatic products to be sold by using an intelligent electronic scale, and inputting the image information of the aquatic products into the aquatic product intelligent identification model in the step (1) to obtain an aquatic product name result with the highest confidence coefficient;
(3) calling the information of the size and the specification corresponding to the name result of the aquatic product obtained in the step (2) in the intelligent electronic scale, and judging whether the aquatic product has the difference of the size and the specification;
if the size and the specification are different, the step (4) is carried out; if the size and specification difference does not exist, performing the step (5);
(4) calling the image information obtained in the step (2), selecting a plurality of pictures, counting the average number of pixel points occupied by the aquatic products in the pictures, and comparing the average number with the classification standard of the size and specification input in the intelligent electronic scale to obtain the size and specification corresponding to the aquatic products, wherein the size and specification is used as an aquatic product identification result;
(5) calling preservation state information corresponding to the aquatic product name result obtained in the step (2) in the intelligent electronic scale, and judging whether the aquatic products have a difference in preservation state;
if the difference exists, performing the step (6); if the difference of the preservation states does not exist, the name of the aquatic product in the step (2) or the name of the aquatic product containing the size specification in the step (4) is used as the aquatic product identification result;
(6) calling the temperature information obtained in the step (2), and judging whether the aquatic product belongs to a fresh aquatic product, a frozen fresh aquatic product or a frozen aquatic product according to the temperature information; if the aquatic product belongs to a fresh ice aquatic product or a frozen aquatic product, taking the result as an aquatic product identification result; if the product belongs to fresh water products, performing the step (7);
(7) calling the image information obtained in the step (2), selecting at least two pictures with an interval of more than 2 seconds, uniformly dividing each picture into four equally divided sub-pictures, counting pixel points occupied by the water products in each sub-picture, calculating the proportion of the pixel points occupied by the water products in each sub-picture, and judging whether the proportion of the pixel points occupied by the water products in each sub-picture between every two pictures changes or not; if the proportion changes, the aquatic product is judged to be a fresh and live aquatic product, and the result is taken as an aquatic product identification result; if the proportion is not changed, determining that the aquatic product is fresh but dead, and taking the result as an aquatic product identification result;
(8) and (4) calling the unit price of the aquatic product in the intelligent electronic scale according to the aquatic product identification results obtained in the steps (4) to (7), and automatically calculating the price of the aquatic product to be sold according to the weight information obtained in the step (2).
Further, in the step (1), the picture information is a plurality of groups of photos of each aquatic product, and the total number of the photos is 1000-2000.
Further, in the step (1), the picture information and the corresponding aquatic product name information are divided into a training set, a testing set and a verification set for model training, and an aquatic product intelligent identification model is constructed.
Furthermore, the construction process of the aquatic product intelligent identification model is as follows:
(1) at the PC end, operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, wherein the parameters of the EfficientNet model are epoch ═ 30, batch _ size ═ 16, learning _ rate ═ 0.01, and drop _ rate ═ 0.5, and performing parameter training on the model by using a training set;
(2) operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, and adjusting and determining model parameters by using a verification set;
(3) operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, and testing the model by using a test set, wherein the precision of the model is required to be higher than 90%;
(4) after the precision meets the requirement, a tool is used for converting the model into a tflite model, so that the tflite model can be used at an android end. The model can be converted to a tflite model using a toco tool and a TensorFlow Lite optimization converter.
Further, in the step (4), three pictures are selected, and the average number of pixel points occupied by the water products in the pictures is counted.
Further, in the step (6), the temperature range of the fresh aquatic products is 10-25 ℃; the temperature range of the iced fresh water product is 0-6 ℃; the temperature range of the frozen aquatic product is-18 ℃ to 0 ℃; an infrared temperature sensor is installed below a weighing platform of the intelligent electronic scale.
Further, in step (7), three frames of pictures spaced by 2 seconds are selected.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the same aquatic products with different sizes and specifications and different preservation states are distinguished by identifying the pixel point regions and judging the variation difference of the pixel points by separating the sub-pictures, and then the intelligent identification model of the aquatic products is matched, so that the identification capability of the intelligent electronic scale is obviously improved, and the automatic pricing of the intelligent electronic scale on the aquatic products is realized.
Drawings
FIG. 1 is a flow chart of the automatic pricing method for aquatic products using the intelligent electronic scale of the invention.
Detailed Description
The present invention will be further described with reference to the following specific examples, which are only illustrative of the present invention, but the scope of the present invention is not limited thereto.
Example 1
An automatic aquatic product pricing method for an intelligent electronic scale comprises the following specific steps:
(1) inputting basic information and corresponding unit prices of all aquatic products consisting of aquatic product names, sizes and specifications and fresh-keeping states and a size and specification classification standard based on the number of pixel points occupied by the aquatic products in the images into an intelligent electronic scale, collecting picture information of all aquatic products, dividing the picture information and the corresponding aquatic product name information into a training set, a testing set and a verification set, introducing the training set, the testing set and the verification set into a model for model training, and constructing an aquatic product intelligent identification model;
for aquatic products without size and specification difference and fresh-keeping state difference in price, only the name of the aquatic product needs to be input; if the difference of the size specification or the preservation state exists, name restriction according to the size specification or the preservation state (such as large yellow croaker and small yellow croaker, large abalone and small abalone, fresh live grass carp, fresh dead grass carp, fresh iced hairtail, frozen hairtail and the like) needs to be input; the picture information is a plurality of groups of pictures of each aquatic product, and the total number of the pictures can be 1000-2000; the images can be taken under different environments, at different times and at different angles, so that the models can be better identified.
The construction process of the aquatic product intelligent identification model comprises the following steps:
(A) at the PC end, operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, wherein the parameters of the EfficientNet model are epoch ═ 30, batch _ size ═ 16, learning _ rate ═ 0.01, and drop _ rate ═ 0.5, and performing parameter training on the model by using a training set;
(B) operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, and adjusting and determining model parameters by using a verification set;
(C) operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, and testing the model by using a test set, wherein the precision of the model is required to be higher than 90%;
(D) after the precision meets the requirement, a toco tool and a TensorFlow Lite optimization converter are adopted to convert the model into a tflite model, so that the tflite model can be used at an android end.
In addition to the EfficientNet deep learning model, other models are also adopted for testing, such as resnet and mobilenet, but the model is not ideal in operation speed and precision; the model size of resnet is 81.3M, and the operation speed cannot keep up due to the fact that the model size is larger for embedded equipment; the precision of the mobilenet aiming at aquatic products is less than 20 percent and far reaches the actual precision requirement. In addition to the running framework of the TensorFlow Lite algorithm, other deep learning frameworks such as PyTorch and TensorFlow are adopted, but the running speed and the precision are not ideal, the speed of the PyTorch framework for running the Efficientnet is about 5s/img, the speed of the TensorFlow framework for running the Efficientnet is about 5.5s/img, the speed and the precision can not meet the actual running speed requirement, the model size of the TensorFlow Lite framework is 3.8M, the running speed of the raspberry pie 4B is about 0.4s/img, the precision reaches more than 90% under a data set, and the practical application requirement is met.
(2) Acquiring image information, weight information and temperature information of aquatic products to be sold by using an intelligent electronic scale, and inputting the image information of the aquatic products into the aquatic product intelligent identification model in the step (1) to obtain an aquatic product name result with the highest confidence coefficient;
when a plurality of groups of results with high confidence coefficients are obtained, an operator of the intelligent electronic scale can assist the intelligent electronic scale to screen more accurate aquatic product name results, and the intelligent electronic scale can directly select the aquatic product name result with the highest confidence coefficient and manually correct the aquatic product name result; if the result is correct, no operation is performed, and if the result is incorrect, manual adjustment is performed.
The image information is obtained through a camera above the intelligent electronic scale, the weight information is obtained through a weight sensor of a weighing platform of the intelligent electronic scale, and an infrared temperature sensor is further installed below the weighing platform of the intelligent electronic scale; the intelligent electronic scale display is connected with the raspberry pie, a data processing function, an image recognition algorithm and the like are deployed on the raspberry pie, and the intelligent electronic scale display is connected with the weight sensor, the camera and the infrared temperature sensor through a circuit.
(3) Calling size and specification information corresponding to the aquatic product name result obtained in the step (2) in the intelligent electronic scale, and judging whether the aquatic products have size and specification differences;
if the size and the specification are different, the step (4) is carried out; if the size and specification difference does not exist, performing the step (5);
(4) calling the image information obtained in the step (2), selecting a plurality of pictures, counting the average number of pixel points occupied by the aquatic products in the pictures, and comparing the average number with the classification standard of the size and specification input in the intelligent electronic scale to obtain the size and specification corresponding to the aquatic products, wherein the size and specification is used as an aquatic product identification result;
the classification standard of the size specification takes the number of pixel points occupied by aquatic products as a judgment basis, and the data are directly input into the intelligent electronic scale in the previous period of data input; the number of the photos is generally 3-5, so that errors caused by the angle of the aquatic product placed on the platform can be ensured.
(5) Calling preservation state information corresponding to the aquatic product name result obtained in the step (2) in the intelligent electronic scale, and judging whether the aquatic products have a difference in preservation state;
if the difference of the preservation state exists, the step (6) is carried out; if the difference of the preservation states does not exist, the name of the aquatic product in the step (2) or the name of the aquatic product containing the size specification in the step (4) is used as the aquatic product identification result;
(6) calling the temperature information obtained in the step (2), and judging whether the aquatic product belongs to a fresh aquatic product, a frozen fresh aquatic product or a frozen aquatic product according to the temperature information; if the aquatic product belongs to a fresh ice aquatic product or a frozen aquatic product, taking the result as an aquatic product identification result; if the product belongs to a fresh water product, performing the step (7);
the temperature range of the fresh aquatic products is 10-25 ℃; the temperature range of the iced fresh water product is 0-6 ℃; the temperature range of the frozen aquatic product is-18 ℃ to 0 ℃.
(7) Calling the image information obtained in the step (2), selecting at least two pictures (three pictures at intervals of 2 seconds) at intervals of more than 2 seconds, uniformly dividing each picture into four equally divided sub-pictures, counting pixel points occupied by the water products in each sub-picture, calculating the proportion of the pixel points occupied by the water products in each sub-picture, and judging whether the proportion of the pixel points occupied by the water products in each sub-picture between every two pictures is changed; if the proportion changes, the aquatic product is judged to be a fresh and live aquatic product, and the result is taken as an aquatic product identification result; if the proportion is not changed, determining that the aquatic product is fresh but dead, and taking the result as an aquatic product identification result;
(8) and (4) calling the unit price of the aquatic product in the intelligent electronic scale according to the aquatic product identification results obtained in the steps (4) to (7), and automatically calculating the price of the aquatic product to be sold according to the weight information obtained in the step (2).
Claims (7)
1. An automatic aquatic product pricing method for an intelligent electronic scale is characterized by comprising the following steps:
(1) inputting basic information and corresponding unit prices of all aquatic products consisting of aquatic product names, sizes and specifications and a fresh-keeping state into an intelligent electronic scale, collecting picture information of all aquatic products according to a size and specification classification standard based on the number of pixel points occupied by aquatic products in an image, introducing the picture information and the corresponding aquatic product name information into a model as a training set for model training, and constructing to obtain an aquatic product intelligent recognition model;
(2) acquiring image information, weight information and temperature information of aquatic products to be sold by using an intelligent electronic scale, and inputting the image information of the aquatic products into the aquatic product intelligent identification model in the step (1) to obtain an aquatic product name result with the highest confidence coefficient;
(3) calling size and specification information corresponding to the aquatic product name result obtained in the step (2) in the intelligent electronic scale, and judging whether the aquatic products have size and specification differences;
if the size and the specification are different, performing the step (4); if the size and specification difference does not exist, the step (5) is carried out;
(4) calling the image information obtained in the step (2), selecting a plurality of pictures, counting the average number of pixel points occupied by the aquatic products in the pictures, and comparing the average number with a size specification classification standard input in an intelligent electronic scale to obtain the size specification corresponding to the aquatic products;
(5) calling preservation state information corresponding to the aquatic product name result obtained in the step (2) in the intelligent electronic scale, and judging whether the aquatic products have a difference in preservation state;
if the difference of the preservation state exists, the step (6) is carried out; if the difference of the preservation states does not exist, the name of the aquatic product in the step (2) or the name of the aquatic product containing the size specification in the step (4) is used as the aquatic product identification result;
(6) calling the temperature information obtained in the step (2), and judging whether the aquatic product belongs to a fresh aquatic product, a frozen fresh aquatic product or a frozen aquatic product according to the temperature information; if the aquatic product belongs to a fresh ice aquatic product or a frozen aquatic product, taking the result as an aquatic product identification result; if the product belongs to fresh water products, performing the step (7);
(7) calling the image information obtained in the step (2), selecting at least two pictures with an interval of more than 2 seconds, uniformly dividing each picture into four equally divided sub-pictures, counting pixel points occupied by the water products in each sub-picture, calculating the proportion of the pixel points occupied by the water products in each sub-picture, and judging whether the proportion of the pixel points occupied by the water products in each sub-picture between every two pictures changes or not; if the proportion changes, the aquatic product is judged to be a fresh and live aquatic product, and the result is taken as an aquatic product identification result; if the proportion is not changed, determining that the aquatic product is fresh but dead, and taking the result as an aquatic product identification result;
(8) and (4) calling the unit price of the aquatic product in the intelligent electronic scale according to the aquatic product identification results obtained in the steps (4) to (7), and automatically calculating the price of the aquatic product to be sold according to the weight information obtained in the step (2).
2. The automatic pricing method for aquatic products for intelligent electronic scales according to claim 1, wherein in the step (1), the picture information is a plurality of groups of photos of each aquatic product, and the total number of the photos is 1000-2000.
3. The automatic aquatic product pricing method for the intelligent electronic scale according to claim 1, wherein in the step (1), the picture information and the corresponding aquatic product name information are divided into a training set, a testing set and a verification set for model training, and an aquatic product intelligent identification model is constructed.
4. The automatic aquatic product pricing method for the intelligent electronic scale as claimed in claim 3, wherein the construction process of the intelligent aquatic product identification model is as follows:
(A) at the PC end, operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, wherein the parameters of the EfficientNet model are epoch ═ 30, batch _ size ═ 16, learning _ rate ═ 0.01, and drop _ rate ═ 0.5, and performing parameter training on the model by using a training set;
(B) operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, and adjusting and determining model parameters by using a verification set;
(C) operating an EfficientNet model under a TensorFlow Lite algorithm operating framework, and testing the model by using a test set, wherein the precision of the model is required to be higher than 90%;
(D) after the precision meets the requirement, the model is converted into a tflite model, so that the tflite model can be used at an android end.
5. The automatic aquatic product pricing method for the intelligent electronic scale according to claim 1, wherein in the step (4), three pictures are selected, and the average number of pixel points occupied by the aquatic product in the pictures is counted.
6. The automatic pricing method for aquatic products using intelligent electronic scale according to claim 1, wherein in step (6), the temperature of fresh aquatic products is in the range of 10 ℃ to 25 ℃; the temperature range of the iced fresh water product is 0-6 ℃; the temperature range of the frozen aquatic product is-18 ℃ to 0 ℃; an infrared temperature sensor is installed below a weighing platform of the intelligent electronic scale.
7. The automatic pricing method for aquatic products for intelligent electronic scales according to claim 1, characterized in that in step (7), three frames of pictures spaced by 2 seconds are selected.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210468585.4A CN114758194A (en) | 2022-04-28 | 2022-04-28 | Automatic aquatic product pricing method for intelligent electronic scale |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210468585.4A CN114758194A (en) | 2022-04-28 | 2022-04-28 | Automatic aquatic product pricing method for intelligent electronic scale |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114758194A true CN114758194A (en) | 2022-07-15 |
Family
ID=82333345
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210468585.4A Pending CN114758194A (en) | 2022-04-28 | 2022-04-28 | Automatic aquatic product pricing method for intelligent electronic scale |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114758194A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180253618A1 (en) * | 2016-06-24 | 2018-09-06 | Ping An Technology (Shenzhen) Co., Ltd. | Method, system, electronic device, and medium for classifying license plates based on deep learning |
CN208520456U (en) * | 2018-07-18 | 2019-02-19 | 深圳仪普生科技有限公司 | A kind of aquatic products self-help shopping fish jar scale |
CN110940407A (en) * | 2019-12-11 | 2020-03-31 | 北京星际华通科技有限公司 | Intelligent electronic scale for Internet of things and transaction method, device and system thereof |
CN111814614A (en) * | 2020-06-28 | 2020-10-23 | 袁精侠 | Intelligent object-identifying electronic scale weighing method and system |
-
2022
- 2022-04-28 CN CN202210468585.4A patent/CN114758194A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180253618A1 (en) * | 2016-06-24 | 2018-09-06 | Ping An Technology (Shenzhen) Co., Ltd. | Method, system, electronic device, and medium for classifying license plates based on deep learning |
CN208520456U (en) * | 2018-07-18 | 2019-02-19 | 深圳仪普生科技有限公司 | A kind of aquatic products self-help shopping fish jar scale |
CN110940407A (en) * | 2019-12-11 | 2020-03-31 | 北京星际华通科技有限公司 | Intelligent electronic scale for Internet of things and transaction method, device and system thereof |
CN111814614A (en) * | 2020-06-28 | 2020-10-23 | 袁精侠 | Intelligent object-identifying electronic scale weighing method and system |
Non-Patent Citations (1)
Title |
---|
洪耀球;: "基于卷积神经网络图像识别的智能电子秤***", 景德镇学院学报, no. 03, 15 June 2020 (2020-06-15) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109001407B (en) | Lake water quality analysis system | |
CN103076288B (en) | A kind of flesh of fish self-grading device based on computer vision and method | |
CN112232978B (en) | Aquatic product length and weight detection method, terminal equipment and storage medium | |
CN110781889B (en) | Deep learning-based nondestructive testing method for total sugar content in blueberry fruits | |
CN111582072A (en) | Transformer substation picture bird nest detection method combining ResNet50+ FPN + DCN | |
CN111462058B (en) | Method for rapidly detecting effective rice ears | |
CN103632157A (en) | A method for counting seeds of a wheatear portion per wheat | |
CN109827957A (en) | A kind of rice leaf SPAD value estimating and measuring method based on computer vision and system | |
CN107704878A (en) | A kind of high-spectral data storehouse semi-automation method for building up based on deep learning | |
CN116058195B (en) | Illumination regulation and control method, system and device for leaf vegetable growth environment | |
CN114004866A (en) | Mosquito recognition system and method based on image similarity difference | |
CN110675400A (en) | Rapid and intelligent mutton quality index detection method based on mobile phone APP | |
CN114049577A (en) | Fish specification measuring method and system | |
CN117029673B (en) | Fish body surface multi-size measurement method based on artificial intelligence | |
CN105405145B (en) | A kind of granule number grain method based on image Segmentation Technology | |
CN110956198B (en) | Visual weight measurement method for monocular camera | |
CN116295022A (en) | Pig body ruler measurement method based on deep learning multi-parameter fusion | |
CN110044485B (en) | Image type fabric color measuring method | |
CN106023235B (en) | A kind of method that the effective seed number of crops measures | |
CN110009609A (en) | A kind of method of quick detection yellow rice kernel | |
CN109946636A (en) | A kind of digital multimeter indicating value automatic calibrating method based on deep learning | |
CN107044947B (en) | A kind of recognition methods of the PM2.5 pollution index based on characteristics of image | |
CN114758194A (en) | Automatic aquatic product pricing method for intelligent electronic scale | |
CN112184627A (en) | Citrus fresh-keeping quality detection method based on image processing and neural network and application | |
CN107563327B (en) | Pedestrian re-identification method and system based on self-walking feedback |
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 |