Intelligent object identification method

Abstract

The invention discloses an intelligent object identification method. The method comprises the following steps: step 1, carrying out data acquisition on an object needing to be identified through camera shooting; 2, preprocessing the data acquired in the step 1; 3, performing feature extraction on the data preprocessed in the step 2; 4, identifying the features extracted in the step 3; step 5, model training: selecting a proper artificial intelligence model for training; step 6, comparing the features extracted in the step 4 with features in a database; and step 7, outputting a result after comparison in the step 5. The intelligent object identification method has relatively high accuracy and flexibility, is suitable for various application scenes, and can play a role in automatically identifying objects in places such as supermarkets and the like, so that the working intensity of supermarket workers is reduced; along with the increase of the identification frequency of the article, the accuracy and speed of the intelligent article identification method provided by the invention are continuously improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent object recognition, and specifically relates to an intelligent object recognition method. Background Art

[0002] The development of the modern warehousing industry is of great significance for optimizing logistics and supply chain systems, transforming the growth model of the national economy, and improving the quality of national economic operations. To improve the storage capacity and turnover efficiency of logistics warehousing in large supermarkets, more and more warehouses are beginning to adopt unmanned electronic warehousing models. The storage and retrieval of all materials are controlled by electronic monitoring systems. Especially in the electronics industry, which uses a large amount of materials and a wide variety of materials, material management personnel or material delivery personnel often cannot fully understand and identify every material being transported. For materials with similar shapes or structures, storage and retrieval errors are prone to occur. Therefore, it is necessary to provide an intelligent object recognition method to solve the above problems. Summary of the Invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an intelligent object recognition method, which effectively solves the problems raised by the background technology.

[0004] To achieve the above objectives, the present invention provides the following technical solution: an intelligent object recognition method, comprising the following steps:

[0005] Step 1: Collect data of the items to be identified by video recording;

[0006] Step 2: pre-process the data collected in step 1;

[0007] Step 3: Extract features from the data preprocessed in step 2;

[0008] Step 4: Identify the features extracted in step 3;

[0009] Step 5: Model training: select a suitable artificial intelligence model for training;

[0010] Step 6: Compare the features extracted in step 4 with those in the database;

[0011] Step seven, output the comparison result of step five.

[0012] Preferably, the data collected in step 1 includes image or video data of the object, and the location of the object in each image or video is marked.

[0013] Preferably, the preprocessing in step 2 includes operations such as cropping, scaling, normalization, noise removal, and image enhancement of the image or video.

[0014] Preferably, the feature extraction in step three includes performing feature extraction on the preprocessed data using a deep learning model to extract a feature vector for each item.

[0015] Preferably, the identification in step 4 includes inputting the extracted feature vector into a classifier to classify and identify the object.

[0016] Preferably, the classifier includes a support vector machine, a decision tree, etc.

[0017] Preferably, the feature comparison in step six includes comparing the feature vector of the item to be identified with the feature vectors of the items stored in the database, and finding the most similar matching result, which is the result of item identification.

[0018] Preferably, the output in step seven includes outputting the comparison result to the user.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] During operation, the intelligent object recognition method of the present invention has high accuracy and flexibility, is applicable to a variety of application scenarios, and can automatically identify objects in places such as supermarkets, thereby reducing the workload of supermarket staff; as the number of identifications of objects increases, the accuracy and speed of the intelligent object recognition method of the present invention will continue to improve. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0022] In the attached figure:

[0023] Figure 1 This is a flow chart of an intelligent object recognition method of the present invention; DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0025] Embodiment 1, by Figure 1 The present invention relates to an intelligent object recognition method, comprising the following steps:

[0026] Step 1: Collect data of the items to be identified by video recording;

[0027] Step 2: pre-process the data collected in step 1;

[0028] Step 3: Extract features from the data preprocessed in step 2;

[0029] Step 4: Identify the features extracted in step 3;

[0030] Step 5: Model training: select a suitable artificial intelligence model for training;

[0031] Step 6: Compare the features extracted in step 4 with those in the database;

[0032] Step seven, output the comparison result of step five.

[0033] The data collection in step 1 includes image or video data of the object, and the location of the object in each image or video is marked.

[0034] The preprocessing in step 2 includes operations such as cropping, scaling, normalization, noise removal, and image enhancement of images or videos.

[0035] The feature extraction in step three involves using a deep learning model to perform feature extraction on the preprocessed data to extract the feature vector of each item.

[0036] The recognition in step 4 includes inputting the extracted feature vector into the classifier to classify and identify the objects.

[0037] Classifiers include support vector machines, decision trees, etc.

[0038] The feature comparison in step six includes comparing the feature vector of the item to be identified with the feature vectors of the items stored in the database to find the most similar matching result, which is the result of item identification.

[0039] The output in step seven includes outputting the comparison result to the user.

[0040] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0041] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent object recognition method comprising the following steps: Step 1: Collect data of the items to be identified by video recording; Step 2: pre-process the data collected in step 1; Step 3: Extract features from the data preprocessed in step 2; Step 4: Identify the features extracted in step 3; Step 5: Model training: select a suitable artificial intelligence model for training; Step 6: Compare the features extracted in step 4 with those in the database; Step seven, output the comparison result of step six.

2. The intelligent object recognition method according to claim 1, characterized in that: The data collected in step 1 includes image or video data of the object, and the location of the object in each image or video is marked.

3. The intelligent object recognition method according to claim 1, characterized in that: The preprocessing in step 2 includes operations such as cropping, scaling, normalization, noise removal, and image enhancement of images or videos.

4. The intelligent object recognition method according to claim 1, characterized in that: The feature extraction in step three includes using a deep learning model to perform feature extraction on the preprocessed data to extract the feature vector of each item.

5. The intelligent object recognition method according to claim 1, characterized in that: The identification in step 4 includes inputting the extracted feature vector into a classifier to classify and identify the object.

6. The intelligent object recognition method according to claim 5, characterized in that: The classifier includes a support vector machine, a decision tree, etc.

7. The intelligent object recognition method according to claim 1, characterized in that: The feature comparison in step six includes comparing the feature vector of the item to be identified with the feature vectors of the items stored in the database, and finding the most similar matching result, which is the result of item identification.

8. The intelligent object recognition method according to claim 1, characterized in that: The output in step seven includes outputting the comparison result to the user.

Images