WO2020134099A1 - 物品识别方法、设备和系统 - Google Patents

物品识别方法、设备和系统 Download PDF

Info

Publication number
WO2020134099A1
WO2020134099A1 PCT/CN2019/099757 CN2019099757W WO2020134099A1 WO 2020134099 A1 WO2020134099 A1 WO 2020134099A1 CN 2019099757 W CN2019099757 W CN 2019099757W WO 2020134099 A1 WO2020134099 A1 WO 2020134099A1
Authority
WO
WIPO (PCT)
Prior art keywords
item
feature
image
identified
information
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.)
Ceased
Application number
PCT/CN2019/099757
Other languages
English (en)
French (fr)
Inventor
刘朋樟
张屹峰
刘巍
陈宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Wodong Tianjun Information Technology Co Ltd
Original Assignee
Beijing Wodong Tianjun Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Wodong Tianjun Information Technology Co Ltd filed Critical Beijing Wodong Tianjun Information Technology Co Ltd
Publication of WO2020134099A1 publication Critical patent/WO2020134099A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • G06N3/09Supervised learning
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/0464Convolutional networks [CNN, ConvNet]
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07FCOIN-FREED OR LIKE APPARATUS
    • G07F9/00Details other than those peculiar to special kinds or types of apparatus
    • G07F9/02Devices for alarm or indication, e.g. when empty; Advertising arrangements in coin-freed apparatus

Definitions

  • the present disclosure relates to the field of computers, and in particular, to an item identification method, device, and system.
  • a related-art vending machine collects images of items taken away, processes the collected images using a neural network model, and outputs the probability that the items taken away belong to each saleable item. If there are 1,000 types of items for sale, each time the neural network model is recognized, a 1000-dimensional vector will be output. Each dimension of the vector corresponds to the probability of a type of item for sale. Items taken away are usually identified as the most probable items for sale. article.
  • Some embodiments of the present disclosure provide an item identification method, including:
  • the type of the item to be identified is determined according to the similarity comparison result.
  • the first feature database is received data sent by the cloud device and stored locally; the data of the first feature database corresponds to a local set of items to be identified.
  • the first feature database is updated accordingly.
  • the first feature database is a subset of the second feature database located in the cloud device
  • the method for establishing the second feature database includes:
  • the feature information of the image of each item is sent to the cloud device and added to the second feature database; or,
  • the image of each item is sent to the cloud device, and the cloud device calculates the feature information of the image of each item and adds it to the second feature database.
  • generating feature information of the item to be identified includes:
  • the feature extraction model is obtained by training a feature-based classification model and deleting the classification layer of the classification model after training.
  • the classification model includes a classification layer, and the classification layer is used to perform image processing based on image feature information. classification.
  • the first feature database is a subset of the second feature database located in the cloud device
  • the method for establishing the second feature database includes:
  • the feature extraction model is obtained by training a feature-based classification model and deleting the classification layer of the classification model after training.
  • the classification model includes a classification layer, and the classification layer is used to perform image processing based on image feature information. classification.
  • the classification model is a neural network model
  • the feature extraction model includes a convolutional layer, a pooling layer, and a fully connected layer.
  • the feature extraction model is used to generate feature information of the image of the newly added item without retraining, and is added to the second feature database.
  • the feature extraction model is retrained if the preset conditions are met.
  • the preset conditions include: the newly added item reaches a preset ratio or quantity, meets a preset time interval, or the accuracy of item identification is lower than a preset value.
  • the method is performed by a vending machine or cloud device.
  • Some embodiments of the present disclosure provide an item identification method, including:
  • the classification model includes a classification layer, and the classification layer is used to classify images according to image feature information;
  • the feature extraction model processes the input image of each item and outputs feature information of the image of the corresponding item
  • the feature information of the image of each item is added to the second feature database, and the feature extraction model and the second feature database are used for item identification.
  • the feature extraction model is used to generate feature information of images of newly added items without retraining.
  • the image of the newly added item comes from a vending machine.
  • the feature extraction model is retrained if the preset conditions are met.
  • the preset conditions include: the newly added item reaches a preset ratio or quantity, meets a preset time interval, or the accuracy of item identification is lower than a preset value.
  • the method further includes: the feature extraction model and the subset of the second feature database are delivered to each vending machine for item identification by the vending machine, and the data of the subset of the second feature database corresponds to the sales The set of items to be identified on the freighter.
  • it also includes:
  • the type of the item to be identified is determined according to the similarity comparison result.
  • Some embodiments of the present disclosure provide a cloud device, including:
  • a processor coupled to the memory, the processor configured to perform the method performed by the cloud device in any of the foregoing embodiments based on instructions stored in the memory.
  • Some embodiments of the present disclosure propose a vending machine, including:
  • a processor coupled to the memory, the processor configured to perform the method performed by the vending machine in any of the foregoing embodiments based on instructions stored in the memory.
  • Some embodiments of the present disclosure propose an item identification system, including:
  • Some embodiments of the present disclosure propose a non-transitory computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the method in any of the foregoing embodiments.
  • FIG. 1 is a schematic diagram of an item identification system according to some embodiments of the present disclosure.
  • FIG. 2a is a schematic flowchart of item identification by a vending machine 12 according to some embodiments of the present disclosure.
  • FIG. 2b is a schematic flowchart of item identification performed by the cloud device 11 according to some embodiments of the present disclosure.
  • FIG. 3 shows a schematic diagram of establishing a second feature database according to some embodiments of the present disclosure.
  • FIG. 4 shows a schematic diagram of the cloud device of some embodiments of the present disclosure delivering feature information of images of some items to each vending machine.
  • FIG. 5 shows a schematic diagram of updating the second feature database for newly added items in some embodiments of the present disclosure.
  • FIG. 6 is a schematic diagram of a cloud device according to some embodiments of the present disclosure.
  • FIG. 7 is a schematic diagram of a vending machine according to some embodiments of the present disclosure.
  • the present disclosure proposes an item identification solution to solve at least one of the foregoing problems and improve the operability of the vending machine.
  • the present disclosure recognizes items based on image feature comparison and implements a new type of item recognition scheme; on the other hand, the model of building a feature database can generate the characteristics of untrained items, making the untrained Items can also be identified; on the one hand, the model for building a feature database does not need to be retrained for each new item; on the other hand, item identification can be performed in a smaller range, which is helpful to reduce the probability of item misidentification.
  • FIG. 1 is a schematic diagram of an item identification system according to some embodiments of the present disclosure.
  • the article identification system 10 of this embodiment includes a cloud device 11 and a number of vending machines 12. These vending machines 12 can be located in different locations, for example, and can realize automatic vending. Information exchange between the cloud device 11 and each vending machine 12 is possible.
  • the cloud device 11 may establish a feature database based on the feature extraction model.
  • the vending machine 12 therein can collect images of items to be identified, for example.
  • the cloud device 11 or the vending machine 12 can perform item identification based on the feature database and the image of the item to be identified. The two article identification methods are described below in conjunction with FIGS. 2a and 2b.
  • the feature database located in the vending machine 12 is set as the first feature database
  • the feature database located in the cloud device 11 is set as the second feature database.
  • the second feature database usually includes feature information of images of all items.
  • the first feature database is a subset of the second feature database, and the data of the first feature database corresponds to the set of items to be identified locally by the vending machine (ie, items sold by the vending machine).
  • the first feature database is updated accordingly.
  • the computing resources of the vending machine are sufficient, or, regardless of the recognition efficiency, the first feature database may also be the complete set of the second feature database.
  • the cloud device 11 may send the feature extraction model and each first feature database (that is, feature information of an image of some items in the second feature database) to Each vending machine 12, and then, the vending machine 12 uses the feature extraction model issued by the cloud device 11 to obtain the feature information of the image of the item to be identified, and through the feature information of the image of the item to be identified and the first feature database issued by the cloud device 11
  • Article identification is carried out in a manner of comparing feature information of images of each article in. This embodiment is described below with reference to FIG. 2a.
  • FIG. 2a is a schematic flowchart of item identification by a vending machine 12 according to some embodiments of the present disclosure.
  • this embodiment includes steps S21-S26.
  • step S21 the cloud device 11 builds a second feature database based on the feature extraction model (refer to the schematic diagram of establishing a second feature database shown in FIG. 3, and id represents an item identifier).
  • the feature extraction model can be obtained through steps S211 to 212, for example:
  • the training data is used to train a feature-based classification model.
  • the classification model includes a classification layer, which is used to classify images based on image feature information.
  • the training data includes, for example, the image of the item and the type of the item annotating the image, that is, which item is annotated in the image.
  • step S212 the classification layer of the feature-based classification model after training is deleted to obtain a feature extraction model.
  • the feature-based classification model is, for example, a neural network model.
  • the neural network model includes, for example, a convolutional layer, a pooling layer, a fully connected layer, and a classification layer, and the corresponding feature extraction model includes a convolutional layer, a pooling layer, and a fully connected layer. .
  • the classification layer is, for example, a softmax layer. If there are 1000 saleable items, define a softmax layer with a dimension of 1000.
  • the softmax layer will output a 1000-dimensional vector, and each dimension of the vector corresponds to the probability of a saleable item.
  • each image can be characterized as a D-dimensional feature vector, such as 256 dimensions, through the feature extraction model.
  • the number of types of items is N.
  • Each item uses K images to extract features, and N ⁇ K D-dimensional feature vectors can be obtained through the feature extraction model.
  • K feature vectors of each item are clustered, and m feature vectors are selected according to the clustering result to characterize the item.
  • the clustering algorithm may use the K-means algorithm.
  • the final feature database includes feature information of N items, and the feature information of each item is m D-dimensional feature vectors.
  • the establishment of the second feature database may be implemented through steps S213 to 214, for example:
  • step S213 the feature extraction model processes the input image of each item and outputs feature information of the image of the corresponding item.
  • step S214 the feature information of the image of each item is added to the second feature database.
  • step S22 the cloud device 11 extracts the corresponding subset of the second feature database as the first feature database of the vending machine 12 according to the set of items to be identified of the vending machine 12, and delivers the feature extraction model and the first feature database to the corresponding Each of the vending machines 12 is used to identify items by the vending machine.
  • the second feature database has feature information of 1,000 items, and a certain vending machine 1 sells 20 items
  • the feature information of these 20 items is sent to the vending machine as the first feature database of the vending machine 1 1.
  • the vending machine 1 can perform item identification within the range of 20 items, without the need to perform item identification within the range of 1000 items, and the item identification within a smaller range is conducive to reducing the probability of incorrect identification of items and improving identification effectiveness.
  • each vending machine has the ability to recognize all items, so each vending machine can pull feature information of any item from the second feature database as needed.
  • FIG. 4 shows a schematic diagram of the cloud device delivering the feature information of the image of some items to each vending machine.
  • the characteristic information of the item with the item ID of 1/3/4 sold by the vending machine 1 is sent to the vending machine 1
  • the item ID of the item sold by the vending machine 2 is 2/4/7
  • the characteristic information of the item of the item is sent to the vending machine 2
  • the characteristic information of the item with the item id of 9/11/12 sold by the vending machine n is sent to the vending machine n.
  • the feature information of different items is relatively similar, the feature information of similar items can be separately delivered to different vending machines, so that the difference in feature information of different items in the same vending machine is relatively large, which is conducive to improving item recognition Accuracy.
  • the cloud device 11 can also send the feature information of the images of all the items in the feature database to each vending machine, and the items can also be realized Identify.
  • step S23 a certain vending machine 12 collects an image of the item to be identified.
  • the vending machine 12 may use a camera to collect an image of the item to be identified.
  • the camera may be disposed in the vending machine 12 adjacent to the cabinet door, so as to collect images of the items.
  • step S24 the vending machine 12 uses the feature extraction model to generate feature information of the image of the item to be recognized.
  • step S25 the vending machine 12 compares the generated feature information of the image of the item to be recognized with the feature information of the image of each item in the first feature database stored in the machine.
  • the Euclidean distance between the feature information of the image of the item to be recognized and the feature information of the image of each item in the feature database is calculated.
  • step S26 the vending machine 12 determines the type of the item to be identified based on the similarity comparison result.
  • the item to be identified can be determined as the item in the first feature database that is most similar to the item to be identified.
  • each vending machine recognizes items based on the image feature comparison, and implements a new item identification scheme.
  • each vending machine has the ability to identify all items, but it can perform item identification in the limited item types it sells. It is not necessary to perform item identification in all item types in the feature database, which is helpful to reduce the probability of item misidentification.
  • the vending machine 12 collects the image of the item to be identified and uploads it to the cloud device 11, and then the cloud device 11 uses the feature extraction model to obtain the image of the item to be identified Feature information, determine the subset of the second feature database (that is, the first feature database) according to the set of items to be recognized of the vending machine 12 through the feature information of the image of the item to be recognized and the feature information of the image of each item in the first feature database
  • the article identification is performed in a comparison manner, and the article identification result is returned to the vending machine 12. The embodiment will be described below with reference to FIG. 2b.
  • FIG. 2b is a schematic flowchart of item identification performed by the cloud device 11 according to some embodiments of the present disclosure.
  • this embodiment includes the following steps: steps S31 to S36.
  • step S31 as in step S21, the cloud device 11 builds a second feature database based on the feature extraction model.
  • the cloud device 11 may save the feature extraction model and the second feature database.
  • step S32 a certain vending machine 12 collects the image of the item to be identified and uploads it to the cloud device 11.
  • step S33 the cloud device 11 uses the feature extraction model to acquire feature information of the image of the item to be identified.
  • step S34 the cloud device 11 determines a subset of the second feature database (ie, the first feature database) according to the set of items to be identified of the vending machine 12, and compares the generated feature information of the image of the item to be identified with the first feature database The feature information of the images of each item is compared for similarity.
  • the second feature database ie, the first feature database
  • the cloud device 11 may also compare the feature information of the image of the item to be recognized with the feature information of the images of all the items in the second feature database Similarity comparison can also realize item identification.
  • step S35 the cloud device 11 determines the type of the item to be identified according to the similarity comparison result.
  • the item to be identified can be determined as the item in the first feature database that is most similar to the item to be identified.
  • step S36 the cloud device 11 returns the item identification result to the vending machine 12, and the vending machine 12 obtains the item identification result.
  • the above-mentioned embodiment recognizes items based on the image feature comparison, and implements a new item identification scheme.
  • complex operations such as feature extraction and similarity comparison are implemented by cloud devices with powerful computing capabilities, which can improve recognition efficiency and greatly reduce the performance requirements of vending machines.
  • FIG. 5 for a schematic diagram of updating the second feature database for newly added items.
  • the feature extraction model may not be retrained, and the current feature extraction model is used to directly generate feature information of the images of several newly added items.
  • the feature information of the newly added item can be directly added to the second feature database as incremental information and delivered to the vending machine that sells the newly added item.
  • the model for constructing the feature database does not need to be retrained for each new item, the number of model trainings is reduced, and the model for constructing the feature database can generate features of items that have not been trained, so that no training has been done Items can also be identified.
  • the feature extraction model is retrained if it meets the preset conditions, where the preset conditions include: the newly added items reach a preset ratio or number, satisfying the preset time interval (such as the number Month), or, the accuracy of item identification is lower than the preset value.
  • the feature extraction model can be retrained based on the image of the original item and the image of the newly added item. Then, a new feature extraction model is used to extract the feature information of the images of all items, thereby generating a new feature database.
  • the image of the newly added item may come from a vending machine that actually sells the item, and is not limited to having to come from a test vending machine. Vending machines that actually sell items may belong to different operators.
  • the image of the newly added item may come from a certain operator.
  • the items sold by various operators may be different, but the images of these items can eventually participate in the training of the feature extraction model. Even if there are few item images uploaded by a certain operator, using all the item images uploaded by all operators can still train a feature extraction model with high accuracy. Relative to each operator independently maintaining a feature database, it is conducive to reducing costs. The capability of this feature extraction model will continue to be optimized as the number of uploaded item images increases.
  • FIG. 6 is a schematic diagram of a cloud device according to some embodiments of the present disclosure.
  • the cloud device 11 of this embodiment includes:
  • a processor 112 coupled to the memory is configured to execute the method performed by the cloud device 11 in any of the foregoing embodiments based on instructions stored in the memory.
  • FIG. 7 is a schematic diagram of a vending machine according to some embodiments of the present disclosure.
  • the vending machine 12 of this embodiment includes:
  • a processor 122 coupled to the memory, the processor configured to perform the method performed by the vending machine 12 in any of the foregoing embodiments based on instructions stored in the memory.
  • the memories 111, 121 may include, for example, a system memory, a fixed non-volatile storage medium, and the like.
  • the system memory stores, for example, an operating system, application programs, a boot loader (Boot Loader), and other programs.
  • Some embodiments of the present disclosure propose a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the item identification method in any of the foregoing embodiments.
  • the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more computer usable non-transitory storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code .
  • a computer usable non-transitory storage media including but not limited to disk storage, CD-ROM, optical storage, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)

Abstract

本公开提出一种物品识别方法、设备和系统,涉及计算机领域。本公开基于图像特征比对的方式来识别物品,实现了一种新型的物品识别方案;再一方面,构建特征数据库的模型可以生成没有训练过的物品的特征,使得没有训练过的物品也能被识别;再一方面,构建特征数据库的模型不需要针对每种新物品重新进行训练;再一方面,可以在更小范围内进行物品识别,有利于降低物品错误识别的概率。

Description

物品识别方法、设备和系统
交叉引用
本申请是以CN申请号为201811628625.7,申请日为2018年12月29日的申请为基础,并主张其优先权,该CN申请的公开内容在此作为整体引入本申请中。
技术领域
本公开涉及计算机领域,特别涉及一种物品识别方法、设备和系统。
背景技术
一种相关技术的售货机,其采集被拿走物品的图像,利用神经网络模型对采集的图像进行处理,输出被拿走物品分别属于各个可售物品的概率。假如有1000种可售物品,则每次识别神经网络模型会输出一个1000维的向量,向量的每个维度对应一种可售物品的概率,被拿走物品通常被识别为概率最大的可售物品。
发明内容
本公开的一些实施例提出一种物品识别方法,包括:
基于采集的待识别物品的图像信息,生成所述待识别物品的特征信息;
将生成的所述待识别物品的特征信息与第一特征数据库中的各物品的图像的特征信息进行相似性比较;
根据相似性比较结果确定所述待识别物品的种类。
在一些实施例中,所述第一特征数据库是接收的云端设备发送的数据,并被保存在本地;所述第一特征数据库的数据对应于本地待识别物品集。
在一些实施例中,当本地待识别物品集发生变化时,所述第一特征数据库相应进行更新。
在一些实施例中,所述第一特征数据库是位于云端设备的第二特征数据库的子集,
所述第二特征数据库的建立方法包括:
各物品的图像的特征信息被发送至云端设备,并添加到所述第二特征数据库;或者,
各物品的图像被发送至云端设备,云端设备计算各物品的图像的特征信息,并添加到所述第二特征数据库。
在一些实施例中,生成所述待识别物品的特征信息包括:
利用特征提取模型处理输入的待识别物品的图像信息,输出所述待识别物品的特征信息,
其中,特征提取模型是通过训练基于特征的分类模型,并删除训练完成的所述分类模型的分类层得到的,所述分类模型包括分类层,所述分类层用于根据图像特征信息对图像进行分类。
在一些实施例中,所述第一特征数据库是位于云端设备的第二特征数据库的子集,
所述第二特征数据库的建立方法包括:
利用特征提取模型处理输入的各物品的图像信息,输出相应物品的特征信息,并添加到所述第二特征数据库,
其中,特征提取模型是通过训练基于特征的分类模型,并删除训练完成的所述分类模型的分类层得到的,所述分类模型包括分类层,所述分类层用于根据图像特征信息对图像进行分类。
在一些实施例中,所述分类模型为神经网络模型,所述特征提取模型包括卷积层、池化层和全连接层。
在一些实施例中,所述特征提取模型在不重新训练的情况下,被用于生成新增加物品的图像的特征信息,并添加到所述第二特征数据库。
在一些实施例中,所述特征提取模型在符合预设条件的情况下被重新训练,
其中的预设条件包括:新增加的物品达到预设的比例或数量,满足预设的时间间隔,或者,物品识别的准确率低于预设值。
在一些实施例中,所述方法由售货机或云端设备执行。
本公开的一些实施例提出一种物品识别方法,包括:
训练基于特征的分类模型,所述分类模型包括分类层,所述分类层用于根据图像特征信息对图像进行分类;
删除训练完成的所述分类模型的分类层得到特征提取模型;
所述特征提取模型处理输入的各物品的图像,输出相应物品的图像的特征信息;
各物品的图像的特征信息被添加到第二特征数据库,所述特征提取模型和所述第 二特征数据库用于进行物品识别。
在一些实施例中,所述特征提取模型在不重新训练的情况下,被用于生成新增加物品的图像的特征信息。
在一些实施例中,新增加的物品的图像来自售货机。
在一些实施例中,所述特征提取模型在符合预设条件的情况下被重新训练,
其中的预设条件包括:新增加的物品达到预设的比例或数量,满足预设的时间间隔,或者,物品识别的准确率低于预设值。
在一些实施例中,还包括:所述特征提取模型和第二特征数据库的子集被下发到各个售货机,用于售货机进行物品识别,第二特征数据库的子集的数据对应于售货机的待识别物品集。
在一些实施例中,还包括:
接收售货机上传的待识别物品的图像信息;
基于所述特征提取模型提取所述待识别物品的特征信息;
根据所述售货机的待识别物品集确定第二特征数据库的子集;
将所述待识别物品的特征信息与第二特征数据库的子集中的各物品的图像的特征信息进行相似性比较;
根据相似性比较结果确定所述待识别物品的种类。
本公开的一些实施例提出一种云端设备,包括:
存储器;以及
耦接至所述存储器的处理器,所述处理器被配置为基于存储在所述存储器中的指令,执行前述任意一个实施例中由云端设备执行的方法。
本公开的一些实施例提出一种售货机,包括:
存储器;以及
耦接至所述存储器的处理器,所述处理器被配置为基于存储在所述存储器中的指令,执行前述任意一个实施例中由售货机执行的方法。
本公开的一些实施例提出一种物品识别系统,包括:
前述的云端设备;以及
前述的若干售货机。
本公开的一些实施例提出一种非瞬时性计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现前述任意一个实施例中的方法。
附图说明
下面将对实施例或相关技术描述中所需要使用的附图作简单地介绍。根据下面参照附图的详细描述,可以更加清楚地理解本公开,
显而易见地,下面描述中的附图仅仅是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1为本公开一些实施例的物品识别系统的示意图。
图2a为本公开一些实施例的由售货机12进行物品识别的流程示意图。
图2b为本公开一些实施例的由云端设备11进行物品识别的流程示意图。
图3示出了本公开一些实施例的第二特征数据库的建立示意图。
图4示出了本公开一些实施例的云端设备将部分物品的图像的特征信息下发到各个售货机的示意图。
图5示出了本公开一些实施例的第二特征数据库针对新增加物品的更新示意图。
图6为本公开一些实施例的云端设备的示意图。
图7为本公开一些实施例的售货机的示意图。
具体实施方式
下面将结合本公开实施例中的附图,对本公开实施例中的技术方案进行清楚、完整地描述。
发明人发现,相关技术的神经网络模型无法识别没有训练过的物品,如果有新的物品,神经网络模型需要被重新训练,此外,需要在全部可售物品范围进行物品识别,这些问题造成售货机的可运营性比较差。
鉴于此,本公开提出一种物品识别方案,以解决前述的至少一个问题,提高售货机的可运营性。
一方面,本公开基于图像特征比对的方式来识别物品,实现了一种新型的物品识别方案;再一方面,构建特征数据库的模型可以生成没有训练过的物品的特征,使得没有训练过的物品也能被识别;再一方面,构建特征数据库的模型不需要针对每种新物品重新进行训练;再一方面,可以在更小范围内进行物品识别,有利于降低物品错误识别的概率。
图1为本公开一些实施例的物品识别系统的示意图。
如图1所示,该实施例的物品识别系统10包括:云端设备11以及若干售货机12。 这些售货机12例如可以位于不同的地点,能够实现自动售货。云端设备11与各个售货机12之间可以进行信息交互。
其中的云端设备11例如可以基于特征提取模型建立特征数据库。其中的售货机12例如可以采集待识别物品的图像。云端设备11或售货机12可以根据特征数据库和待识别物品的图像进行物品识别。下面结合图2a和图2b分别描述这两种物品识别方法。
为了方便描述,位于售货机12的特征数据库设为第一特征数据库,位于云端设备11的特征数据库设为第二特征数据库。第二特征数据库通常包括全部物品的图像的特征信息。在一些实施例中,第一特征数据库是第二特征数据库的子集,第一特征数据库的数据对应于售货机本地待识别物品集(即该售货机售卖的物品)。当售货机本地待识别物品集发生变化时,第一特征数据库相应进行更新。当然,如果售货机的计算资源足够,或者,不考虑识别效率的情况下,第一特征数据库也可以是第二特征数据库的全集。
在一些实施例中,如果由售货机12进行物品识别,则云端设备11可以将特征提取模型和各个第一特征数据库(即第二特征数据库中的部分物品的图像的特征信息)被下发到各个售货机12,然后,售货机12利用云端设备11下发的特征提取模型获取待识别物品的图像的特征信息,通过待识别物品的图像的特征信息与云端设备11下发的第一特征数据库中的各物品的图像的特征信息比对的方式进行物品识别。下面结合图2a描述该实施例。
图2a为本公开一些实施例的由售货机12进行物品识别的流程示意图。
如图2a所示,该实施例包括:步骤S21~S26。
在步骤S21,云端设备11基于特征提取模型建立第二特征数据库(参考图3示出的第二特征数据库的建立示意图,id表示物品标识)。
其中的特征提取模型例如可以通过步骤S211~212来获得:
在步骤S211,利用训练数据训练基于特征的分类模型。分类模型包括分类层,分类层用于根据图像特征信息对图像进行分类。
其中的训练数据例如包括物品的图像和对图像进行标注的物品种类,即标注图像中的是哪种物品。
在步骤S212,删除训练完成的基于特征的分类模型的分类层得到特征提取模型。
其中的基于特征的分类模型例如为神经网络模型,神经网络模型例如包括卷积 层、池化层、全连接层和分类层,相应的特征提取模型包括卷积层、池化层和全连接层。
其中的分类层例如为softmax层。假如有1000种可售物品,则定义一个维度为1000的softmax层,softmax层会输出一个1000维的向量,向量的每个维度对应一种可售物品的概率。
假设每张图像经特征提取模型可以表征为一个D维度的特征向量,如256维。物品的种类数为N,每种物品利用K张图像提取特征,经特征提取模型可以得到N×K个D维的特征向量。可选的,对每种物品的K个特征向量进行聚类,根据聚类结果选取其中的m个特征向量来表征该种物品。其中的聚类算法例如可以选用K-means算法。最终特征数据库中包括N种物品的特征信息,每种物品的特征信息为m个D维的特征向量。
其中的建立第二特征数据库例如可以通过步骤S213~214来实现:
在步骤S213,特征提取模型处理输入的各物品的图像,输出相应物品的图像的特征信息。
在步骤S214,各物品的图像的特征信息被添加到第二特征数据库。
在步骤S22,云端设备11根据售货机12的待识别物品集提取第二特征数据库相应的子集作为该售货机12的第一特征数据库,将特征提取模型和第一特征数据库分别下发到相应的各个售货机12用于售货机进行物品识别。
例如,第二特征数据库中有1000种物品的特征信息,某个售货机1售卖其中的20种物品,则这20种物品的特征信息作为售货机1的第一特征数据库被下发到售货机1,使得售货机1可以在20种物品范围内进行物品识别,而不需要在1000种物品范围内进行物品识别,在更小范围内进行物品识别,有利于降低物品错误识别的概率和提高识别效率。但是,每台售货机具备全部物品的识别能力,因此,每台售货机可以根据需要从第二特征数据库中拉取任意物品的特征信息。
图4示出了云端设备将部分物品的图像的特征信息下发到各个售货机的示意图。例如,根据各个售货机售卖的物品的情况,售货机1售卖的物品id为1/3/4的物品的特征信息下发到售货机1,售货机2售卖的物品id为2/4/7的物品的特征信息下发到售货机2,售货机n售卖的物品id为9/11/12的物品的特征信息下发到售货机n。此外,如果不同物品的特征信息比较相似,则可以将相似的物品的特征信息分别下发到不同的售货机,使得同一台售货机中的不同物品的特征信息差异比较大,有利于提 高物品识别的准确性。
本领域技术人员可以理解,如果不考虑降低物品错误识别概率和提高识别效率的问题,云端设备11也可以将特征数据库中的全部物品的图像的特征信息下发到各个售货机,同样可以实现物品识别。
在步骤S23,某个售货机12采集待识别物品的图像。
其中,售货机12例如可以利用摄像头采集待识别物品的图像。摄像头例如可以设置在售货机12中邻近柜门的位置,便于采集物品的图像。
在步骤S24,售货机12利用特征提取模型生成待识别物品的图像的特征信息。
在步骤S25,售货机12将生成的待识别物品的图像的特征信息与本机存储的第一特征数据库中的各物品的图像的特征信息进行相似性比较。
例如,计算待识别物品的图像的特征信息与特征数据库中的各物品的图像的特征信息之间的欧氏距离,欧式距离越小,说明越相似。
在步骤S26,售货机12根据相似性比较结果确定待识别物品的种类。
通常情况下,待识别物品可以被确定为第一特征数据库中与待识别物品最相似的物品。
上述实施例基于图像特征比对的方式来识别物品,实现了一种新型的物品识别方案。此外,每台售货机具备全部物品的识别能力,但可以在其售卖的有限物品种类中进行物品识别,不需要在特征数据库的全部物品种类中进行物品识别,有利于降低物品错误识别的概率。
在另一些实施例中,如果由云端设备11进行物品识别,则售货机12采集待识别物品的图像,并上传到云端设备11,然后,云端设备11利用特征提取模型获取待识别物品的图像的特征信息,根据售货机12的待识别物品集确定第二特征数据库的子集(即第一特征数据库)通过待识别物品的图像的特征信息与第一特征数据库中的各个物品的图像的特征信息比对的方式进行物品识别,并将物品识别结果返回售货机12。下面结合图2b描述该实施例。
图2b为本公开一些实施例的由云端设备11进行物品识别的流程示意图。
如图2b所示,该实施例包括:包括:步骤S31~S36。
在步骤S31,与步骤S21相同,云端设备11基于特征提取模型建立第二特征数据库。云端设备11可以保存特征提取模型以及第二特征数据库。
在步骤S32,某个售货机12采集待识别物品的图像,并上传到云端设备11。
在步骤S33,云端设备11利用特征提取模型获取待识别物品的图像的特征信息。
在步骤S34,云端设备11根据该售货机12的待识别物品集确定第二特征数据库的子集(即第一特征数据库),将生成的待识别物品的图像的特征信息与第一特征数据库中的各个物品的图像的特征信息进行相似性比较。
本领域技术人员可以理解,如果不考虑降低物品错误识别概率和提高识别效率的问题,云端设备11也可以将待识别物品的图像的特征信息与第二特征数据库中的全部物品的图像的特征信息进行相似性比较,同样可以实现物品识别。
相似性比较方法参考前述,这里不再赘述。
在步骤S35,云端设备11根据相似性比较结果确定待识别物品的种类。
通常情况下,待识别物品可以被确定为第一特征数据库中与待识别物品最相似的物品。
在步骤S36,云端设备11将物品识别结果返回该售货机12,该售货机12得到物品识别结果。
上述实施例基于图像特征比对的方式来识别物品,实现了一种新型的物品识别方案。此外,特征提取和相似性比较等复杂运算由运算能力强大的云端设备实现,可以提高识别效率,售货机的性能要求大大降低。
上述的物品识别方案对特征提取模型的应用有很多优点。下面具体说明。
参考图5示出的第二特征数据库针对新增加物品的更新示意图。假设特征提取模型针对已有物品已经完成训练和特征提取,如果有新增加的物品,特征提取模型可以不重新训练,利用当前的特征提取模型,直接生成新增加的若干物品的图像的特征信息,新增加的物品的特征信息可以作为增量信息直接添加到第二特征数据库,并下发到售卖该新增加的物品的售货机。
由此可见,在本公开中,构建特征数据库的模型不需要针对每种新物品重新进行训练,模型训练的次数减少,构建特征数据库的模型可以生成没有训练过的物品的特征,使得没有训练过的物品也能被识别。这些特点使得本公开的方案具有良好的可运营性,极大地提升了新物品的上线速度。
在一些实施例中,特征提取模型在符合预设条件的情况下再被重新训练,其中的预设条件包括:新增加的物品达到预设的比例或数量,满足预设的时间间隔(如数月),或者,物品识别的准确率低于预设值。
特征提取模型可以基于原有物品的图像和新增加物品的图像进行重新训练。然 后,利用新的特征提取模型提取所有物品的图像的特征信息,从而生成新的特征数据库。
在一些实施例中,新增加的物品的图像可以来自实际售卖物品的售货机,而不受限于必须来自测试用售货机。实际售卖物品的售货机可能属于不同的运营商。
在一些实施例中,新增加的物品的图像可以来自某个运营商。
各个运营商售卖的物品可能不同,但是这些物品的图像最终都可以参与特征提取模型的训练。即使某个运营商上传的物品图像较少,但利用全部运营商上传的物品图像,仍然可以训练得到高准确率的特征提取模型。相对于每个运营商独立的维护一个特征数据库来说,有利于降低成本。该特征提取模型的能力会随着上传物品图像的增多持续得到优化。
图6为本公开一些实施例的云端设备的示意图。
如图6所示,该实施例的云端设备11包括:
存储器111;以及
耦接至所述存储器的处理器112,所述处理器被配置为基于存储在所述存储器中的指令,执行前述任意一个实施例中由云端设备11执行的方法。
图7为本公开一些实施例的售货机的示意图。
如图7所示,该实施例的售货机12包括:
存储器121;以及
耦接至所述存储器的处理器122,所述处理器被配置为基于存储在所述存储器中的指令,执行前述任意一个实施例中由售货机12执行的方法。
其中,存储器111,121例如可以包括系统存储器、固定非易失性存储介质等。系统存储器例如存储有操作系统、应用程序、引导装载程序(Boot Loader)以及其他程序等。
本公开的一些实施例提出一种计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现前述任意一个实施例中的物品识别方法。
本领域内的技术人员应当明白,本公开的实施例可提供为方法、系统、或计算机程序产品。因此,本公开可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且,本公开可采用在一个或多个其中包含有计算机可用程序代码的计算机可用非瞬时性存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上所述仅为本公开的较佳实施例,并不用以限制本公开,凡在本公开的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本公开的保护范围之内。

Claims (20)

  1. 一种物品识别方法,包括:
    基于采集的待识别物品的图像信息,生成所述待识别物品的特征信息;
    将生成的所述待识别物品的特征信息与第一特征数据库中的各物品的图像的特征信息进行相似性比较;
    根据相似性比较结果确定所述待识别物品的种类。
  2. 如权利要求1所述的方法,其中,
    所述第一特征数据库是接收的云端设备发送的数据,并被保存在本地;
    所述第一特征数据库的数据对应于本地待识别物品集。
  3. 如权利要求2所述的方法,其中,当本地待识别物品集发生变化时,所述第一特征数据库相应进行更新。
  4. 如权利要求1所述的方法,其中,
    所述第一特征数据库是位于云端设备的第二特征数据库的子集,
    所述第二特征数据库的建立方法包括:
    各物品的图像的特征信息被发送至云端设备,并添加到所述第二特征数据库;
    或者,
    各物品的图像被发送至云端设备,云端设备计算各物品的图像的特征信息,并添加到所述第二特征数据库。
  5. 如权利要求1所述的方法,其中,生成所述待识别物品的特征信息包括:
    利用特征提取模型处理输入的待识别物品的图像信息,输出所述待识别物品的特征信息,
    其中,特征提取模型是通过训练基于特征的分类模型,并删除训练完成的所述分类模型的分类层得到的,所述分类模型包括分类层,所述分类层用于根据图像特征信息对图像进行分类。
  6. 如权利要求1所述的方法,其中,
    所述第一特征数据库是位于云端设备的第二特征数据库的子集,
    所述第二特征数据库的建立方法包括:
    利用特征提取模型处理输入的各物品的图像信息,输出相应物品的特征信息,并添加到所述第二特征数据库,
    其中,特征提取模型是通过训练基于特征的分类模型,并删除训练完成的所述分类模型的分类层得到的,所述分类模型包括分类层,所述分类层用于根据图像特征信息对图像进行分类。
  7. 如权利要求5或6所述的方法,其中,所述分类模型为神经网络模型,所述特征提取模型包括卷积层、池化层和全连接层。
  8. 如权利要求6所述的方法,其中,
    所述特征提取模型在不重新训练的情况下,被用于生成新增加物品的图像的特征信息,并添加到所述第二特征数据库。
  9. 如权利要求5、6或8所述的方法,其中,所述特征提取模型在符合预设条件的情况下被重新训练,
    其中的预设条件包括:新增加的物品达到预设的比例或数量,满足预设的时间间隔,或者,物品识别的准确率低于预设值。
  10. 如权利要求1所述的方法,所述方法由售货机或云端设备执行。
  11. 一种物品识别方法,包括:
    训练基于特征的分类模型,所述分类模型包括分类层,所述分类层用于根据图像特征信息对图像进行分类;
    删除训练完成的所述分类模型的分类层得到特征提取模型;
    所述特征提取模型处理输入的各物品的图像,输出相应物品的图像的特征信息;
    各物品的图像的特征信息被添加到第二特征数据库,所述特征提取模型和所述第二特征数据库用于进行物品识别。
  12. 如权利要求11所述的方法,其中,
    所述特征提取模型在不重新训练的情况下,被用于生成新增加物品的图像的特征信息。
  13. 如权利要求12所述的方法,其中,新增加的物品的图像来自售货机。
  14. 如权利要求11所述的方法,其中,所述特征提取模型在符合预设条件的情况下被重新训练,
    其中的预设条件包括:新增加的物品达到预设的比例或数量,满足预设的时间间隔,或者,物品识别的准确率低于预设值。
  15. 如权利要求11所述的方法,还包括:
    所述特征提取模型和第二特征数据库的子集被下发到各个售货机,用于售货机进行物品识别,第二特征数据库的子集的数据对应于售货机的待识别物品集。
  16. 如权利要求11所述的方法,还包括:
    接收售货机上传的待识别物品的图像信息;
    基于所述特征提取模型提取所述待识别物品的特征信息;
    根据所述售货机的待识别物品集确定第二特征数据库的子集;
    将所述待识别物品的特征信息与第二特征数据库的子集中的各物品的图像的特征信息进行相似性比较;
    根据相似性比较结果确定所述待识别物品的种类。
  17. 一种云端设备,包括:
    存储器;以及
    耦接至所述存储器的处理器,所述处理器被配置为基于存储在所述存储器中的指令,执行权利要求1、5-9、11-16中任一项所述的方法。
  18. 一种售货机,包括:
    存储器;以及
    耦接至所述存储器的处理器,所述处理器被配置为基于存储在所述存储器中的指令,执行权利要求1-5任一项所述的方法。
  19. 一种物品识别系统,包括:
    权利要求17所述的云端设备;以及
    权利要求18所述的若干售货机。
  20. 一种非瞬时性计算机可读存储介质,其上存储有计算机程序,该程序被处理器执行时实现权利要求1-16中任一项所述的方法。
PCT/CN2019/099757 2018-12-29 2019-08-08 物品识别方法、设备和系统 Ceased WO2020134099A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811628625.7A CN109711473A (zh) 2018-12-29 2018-12-29 物品识别方法、设备和系统
CN201811628625.7 2018-12-29

Publications (1)

Publication Number Publication Date
WO2020134099A1 true WO2020134099A1 (zh) 2020-07-02

Family

ID=66258009

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/099757 Ceased WO2020134099A1 (zh) 2018-12-29 2019-08-08 物品识别方法、设备和系统

Country Status (2)

Country Link
CN (1) CN109711473A (zh)
WO (1) WO2020134099A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112287086A (zh) * 2020-11-13 2021-01-29 北京京东尚科信息技术有限公司 一种智能应答方法、装置、服务器和介质
WO2022179382A1 (zh) * 2021-02-25 2022-09-01 山东英信计算机技术有限公司 一种物体识别方法、装置、设备及介质
CN115840831A (zh) * 2022-12-27 2023-03-24 北京爱奇艺科技有限公司 一种商品检索方法、装置、设备及存储介质
CN116226431A (zh) * 2022-12-06 2023-06-06 北京中能达科技股份有限公司 商品上新方法、商品识别方法、装置、系统及电子设备
CN116453250A (zh) * 2023-03-10 2023-07-18 中国建设银行股份有限公司 识别模型生成方法及装置、服务调用方法、设备、介质

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7085370B2 (ja) * 2017-03-16 2022-06-16 株式会社リコー 診断装置、診断システム、診断方法およびプログラム
CN109711473A (zh) * 2018-12-29 2019-05-03 北京沃东天骏信息技术有限公司 物品识别方法、设备和系统
CN110674844A (zh) * 2019-08-27 2020-01-10 广州伊思高科技有限公司 一种智能货柜增量学习训练方法
CN110826481A (zh) * 2019-11-01 2020-02-21 北京云迹科技有限公司 数据处理方法、商品识别方法、服务器和存储介质
CN113465251B (zh) * 2020-05-28 2022-10-18 海信集团有限公司 智能冰箱及食材识别方法
CN113674249A (zh) * 2021-08-24 2021-11-19 重庆忽米网络科技有限公司 基于工业互联网的pcb板印刷质量检测方法
CN113808116A (zh) * 2021-09-24 2021-12-17 无锡精质视觉科技有限公司 基于图像识别的智能检测方法、系统及产品检测系统
CN113947148A (zh) * 2021-10-19 2022-01-18 深圳市玻尔智造科技有限公司 一种跨数据集的目标检测联合训练方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170309113A1 (en) * 2014-10-21 2017-10-26 Nec Corporation Vending machine recognition apparatus, vending machine recognition method, and recording medium
CN107833363A (zh) * 2017-09-28 2018-03-23 中南大学 基于图像识别的自助售货机自动库存管理系统及方法
CN108492258A (zh) * 2018-01-17 2018-09-04 天津大学 一种基于生成对抗网络的雷达图像去噪方法
CN109711473A (zh) * 2018-12-29 2019-05-03 北京沃东天骏信息技术有限公司 物品识别方法、设备和系统

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170302641A1 (en) * 2014-03-28 2017-10-19 Confia Systems, Inc. Secure and Anonymized Authentication
CN105224066A (zh) * 2014-06-03 2016-01-06 北京创思博德科技有限公司 一种基于云端处理的手势识别方法
CN107316023A (zh) * 2017-06-27 2017-11-03 昝立民 一种用于共享设备的人脸识别系统
CN209132890U (zh) * 2017-09-27 2019-07-19 中山市宾哥网络科技有限公司 结算箱
CN107730168B (zh) * 2017-09-28 2021-10-01 中南大学 一种基于图像识别的自动售货机自动库存管理系统及方法
CN108960119B (zh) * 2018-06-28 2021-06-08 武汉市哈哈便利科技有限公司 一种用于无人售货柜的多角度视频融合的商品识别算法
CN108647671B (zh) * 2018-06-28 2023-12-22 武汉市哈哈便利科技有限公司 一种光学标识视觉识别方法及基于该方法的无人售货柜
CN108932321B (zh) * 2018-06-29 2020-10-23 金蝶软件(中国)有限公司 人脸图像检索方法、装置、计算机设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170309113A1 (en) * 2014-10-21 2017-10-26 Nec Corporation Vending machine recognition apparatus, vending machine recognition method, and recording medium
CN107833363A (zh) * 2017-09-28 2018-03-23 中南大学 基于图像识别的自助售货机自动库存管理系统及方法
CN108492258A (zh) * 2018-01-17 2018-09-04 天津大学 一种基于生成对抗网络的雷达图像去噪方法
CN109711473A (zh) * 2018-12-29 2019-05-03 北京沃东天骏信息技术有限公司 物品识别方法、设备和系统

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112287086A (zh) * 2020-11-13 2021-01-29 北京京东尚科信息技术有限公司 一种智能应答方法、装置、服务器和介质
WO2022179382A1 (zh) * 2021-02-25 2022-09-01 山东英信计算机技术有限公司 一种物体识别方法、装置、设备及介质
US20240071066A1 (en) * 2021-02-25 2024-02-29 Shandong Yingxin Computer Technologies Co., Ltd. Object recognition method and apparatus, and device and medium
US12592069B2 (en) * 2021-02-25 2026-03-31 Shandong Yingxin Computer Technologies Co., Ltd. Object recognition method and apparatus, and device and medium
CN116226431A (zh) * 2022-12-06 2023-06-06 北京中能达科技股份有限公司 商品上新方法、商品识别方法、装置、系统及电子设备
CN115840831A (zh) * 2022-12-27 2023-03-24 北京爱奇艺科技有限公司 一种商品检索方法、装置、设备及存储介质
CN116453250A (zh) * 2023-03-10 2023-07-18 中国建设银行股份有限公司 识别模型生成方法及装置、服务调用方法、设备、介质

Also Published As

Publication number Publication date
CN109711473A (zh) 2019-05-03

Similar Documents

Publication Publication Date Title
WO2020134099A1 (zh) 物品识别方法、设备和系统
US20240070554A1 (en) Optimizing training data for image classification
Song et al. Optimized graph learning using partial tags and multiple features for image and video annotation
WO2022068196A1 (zh) 跨模态的数据处理方法、装置、存储介质以及电子装置
CN110782042A (zh) 横向联邦和纵向联邦联合方法、装置、设备及介质
WO2021030899A1 (en) Automated image retrieval with graph neural network
US20220012502A1 (en) Activity detection device, activity detection system, and activity detection method
Paoletti et al. Subspace clustering for action recognition with covariance representations and temporal pruning
Lee et al. Learnable dynamic temporal pooling for time series classification
CN109858505B (zh) 分类识别方法、装置及设备
WO2019045802A1 (en) LEARNING DISTANCE MEASUREMENT USING PROXY MEMBERS
CN109871821B (zh) 自适应网络的行人重识别方法、装置、设备及存储介质
CN115564832B (zh) 物体抓取位姿的检测方法、装置、设备及存储介质
Simon et al. The whole is more than its parts? from explicit to implicit pose normalization
JP2021009645A (ja) 属性認識システム、学習サーバ、及び属性認識プログラム
Altintakan et al. Towards effective image classification using class-specific codebooks and distinctive local features
Zhang et al. Dataset-driven unsupervised object discovery for region-based instance image retrieval
CN113902944A (zh) 模型的训练及场景识别方法、装置、设备及介质
Delussu et al. Online domain adaptation for person re-identification with a human in the loop
Huang et al. Coarse-to-fine face alignment with multi-scale local patch regression
JP2019028700A (ja) 検証装置、方法、及びプログラム
WO2025011525A1 (zh) 图像的特征提取方法、装置、图像处理系统和存储介质
WO2025113058A1 (zh) 基于场景聚类的模型训练方法、装置、设备和存储介质
Shao et al. Learning deep representation from coarse to fine for face alignment
CN104778272B (zh) 一种基于区域挖掘和空间编码的图像位置估计方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19903296

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19903296

Country of ref document: EP

Kind code of ref document: A1