CN112949473A - Intelligent weight recognizing image recognition system based on deep learning algorithm - Google Patents
Intelligent weight recognizing image recognition system based on deep learning algorithm Download PDFInfo
- Publication number
- CN112949473A CN112949473A CN202110222190.1A CN202110222190A CN112949473A CN 112949473 A CN112949473 A CN 112949473A CN 202110222190 A CN202110222190 A CN 202110222190A CN 112949473 A CN112949473 A CN 112949473A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- electrically connected
- output end
- input end
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent weight-identifying image identification system based on a deep learning algorithm, which belongs to the technical field of image identification and comprises an image acquisition module, an image processing module, an image identification module and a central processing unit, wherein the output end of the image acquisition module is electrically connected with the input end of the image processing module, the output end of the image processing module is electrically connected with the input end of the image identification module, and the image identification module is electrically connected with the central processing unit in a bidirectional mode. According to the invention, through the arrangement of the image processing module, when the image sending module A sends information to the image receiving module A, the image recognition module can more effectively and accurately recognize the image information, so that the situation that the subsequent recognition and authentication work cannot be well carried out due to the fact that the image recognition technology is difficult to extract the features in the image when the image acquired and shot by the image acquisition is not clear enough or the image is damaged is avoided, and the use of people is facilitated.
Description
Technical Field
The invention belongs to the technical field of image recognition, and particularly relates to an intelligent weight recognizing image recognition system based on a deep learning algorithm.
Background
With the development and progress of society, the image recognition technology is more advanced and widely applied, the image recognition is to take the image of an object and recognize the features of the object from the acquired image of the object, and is mainly used for extracting the features of important parts from the image of the object and judging whether the extracted features are consistent with the stored information through a recognition mechanism, so as to carry out the recognition and authentication of the image, the image recognition system in the prior art has certain defects, when the image acquired and shot by the image acquisition is not clear enough, the image recognition technology is difficult to extract the features in the image, so that the subsequent recognition and authentication work cannot be well carried out, further the use of people is not facilitated, and when the image is damaged, the image recognition module cannot recognize the damaged image, so that the applicability is reduced, moreover, the image recognition system in the prior art does not have the function of autonomous learning improvement, so that the recognition accuracy is poor, the authentication cannot be rapidly carried out, and meanwhile, the image recognition system cannot be applied to different situations.
Disclosure of Invention
The invention aims to: the intelligent recognition system based on the deep learning algorithm is provided for solving the problems that recognition and authentication cannot be well carried out when an image is damaged or not clear in shooting and autonomous learning improvement is not available.
In order to achieve the purpose, the invention adopts the following technical scheme:
an intelligent weight-identifying image recognition system based on a deep learning algorithm comprises an image acquisition module, an image processing module, an image recognition module and a central processing unit, wherein the output end of the image acquisition module is electrically connected with the input end of the image processing module, the output end of the image processing module is electrically connected with the input end of the image recognition module, the image recognition module is electrically connected with the central processing unit in a bidirectional mode, and the output end of the central processing unit is electrically connected with the input ends of the image acquisition module and the image processing module respectively;
the image acquisition module comprises an infrared detection module, an image scanning module, a data sorting module and an image sending module A, wherein the output end of the infrared detection module is electrically connected with the input end of the image scanning module, the output end of the image scanning module is electrically connected with the input end of the data sorting module, the output end of the data sorting module is electrically connected with the input end of the image sending module A, and the output end of the image sending module A is electrically connected with the input end of the image processing module.
As a further description of the above technical solution:
the image processing module comprises an image receiving module A, the input end of the image receiving module A is electrically connected with the output end of the image sending module A, the output end of the image receiving module A is electrically connected with the input end of the image smoothness repairing module, and the output end of the image smoothness repairing module is electrically connected with the input end of the edge detection module.
As a further description of the above technical solution:
the output end of the edge detection module is electrically connected with the input end of the edge restoration module, the output end of the edge restoration module is electrically connected with the input end of the image noise reduction module, the output end of the image noise reduction module is electrically connected with the input end of the image enhancement module, the output end of the image enhancement module is electrically connected with the input end of the image sending module B, and the output end of the image sending module B is electrically connected with the input end of the image identification module.
As a further description of the above technical solution:
the image recognition module comprises an image receiving module B, the input end of the image receiving module B is electrically connected with the output end of the image sending module B, the output end of the image receiving module B is electrically connected with the input end of the image feature extraction module, and the output end of the image feature extraction module is electrically connected with the input end of the image information extraction module.
As a further description of the above technical solution:
the output end of the image information extraction module is electrically connected with the input end of the image sound extraction module, the output end of the image sound extraction module is electrically connected with the input end of the information classification module, and the output end of the information classification module is electrically connected with the input end of the central processing unit.
As a further description of the above technical solution:
the central processing unit comprises an intelligent analysis module, the input end of the intelligent analysis module is electrically connected with the output end of the information classification module, and the output end of the intelligent analysis module is electrically connected with the input ends of the learning database and the image database respectively.
As a further description of the above technical solution:
the output end of the learning database is respectively electrically connected with the input ends of the storage module A, the storage module B and the storage module C, and the output ends of the storage module A, the storage module B and the storage module C are electrically connected with the input end of the timing retrieval module.
As a further description of the above technical solution:
the output end of the timing retrieval module is electrically connected with the input end of the learning database.
As a further description of the above technical solution:
the output end of the central processing unit is electrically connected with the input end of the timing retrieval module.
In summary, due to the adoption of the technical scheme, the invention has the beneficial effects that:
1. in the invention, by arranging the image processing module, when the image sending module A transmits information to the image receiving module A, the image receiving module A can transmit the information to the image smoothness restoring module, the image smoothness restoring module can restore the smoothness of the image information, the restored image information can be transmitted to the edge detecting module, the edge detecting module detects the edge of the image information, after the detection is finished, the edge detecting module transmits the detected image information to the edge restoring module, the edge restoring module can restore the incomplete information detected by the edge detecting module, the restored image information can be transmitted to the image noise reducing module, the image noise reducing module performs noise reduction on the image information, and then the image noise reducing module can transmit the noise-reduced image information to the image enhancing module, the image enhancement module can enhance and amplify partial features of the image information, and finally the image information which is well repaired and the features of which are amplified is transmitted to the image recognition module through the image sending module, so that the image recognition module can more effectively and accurately recognize the image information, and the problem that the image recognition technology is difficult to extract the features in the image when the image shot by image acquisition is not clear enough or the image is damaged is avoided, thereby causing the condition that the subsequent recognition and authentication work can not be well carried out, and being beneficial to the use of people.
2. In the invention, the central processor is arranged, so that the identified and classified image information can be transmitted to the intelligent analysis module, the intelligent analysis module transmits the image information to the image database, the original image information in the image database is used for identifying and authenticating, the intelligent analysis module can transmit the image information to the learning database, the learning database can integrate the received image information and sequentially transmit the information with different characteristics to the storage module A, the storage module B and the storage module C, the storage module A, the storage module B and the storage module C can store the extracted different characteristics, the subsequent retrieval work is convenient, the timing retrieval module can transmit the information to the learning database at regular time, the learning database transmits the information to the storage module A, the storage module B and the storage module C, therefore, the storage module A, the storage module B and the storage module C can transmit information to the timing retrieval module, so that the timing retrieval module can learn the characteristics in the storage module A, the storage module B and the storage module C, and then the timing retrieval module can transmit the retrieved information to the central processing unit, thereby facilitating the subsequent work of identification and authentication, enabling the system to have the function of timing autonomous learning improvement, and being higher in accuracy of identification and authentication and applicable to different identification conditions.
Drawings
FIG. 1 is a schematic view of an overall flow structure of an intelligent weight-identifying image recognition system based on a deep learning algorithm according to the present invention;
FIG. 2 is a schematic view of a sub-module structure of an image acquisition module of the intelligent weight-identifying image identification system based on the deep learning algorithm;
FIG. 3 is a schematic view of a sub-module structure of an image processing module of the intelligent weight-identifying image recognition system based on the deep learning algorithm;
FIG. 4 is a schematic view of a sub-module structure of an image recognition module of the intelligent recognition system based on the deep learning algorithm;
fig. 5 is a schematic structural diagram of sub-modules of a central processing unit of the intelligent recognition image recognition system based on the deep learning algorithm.
Illustration of the drawings:
1. an image acquisition module; 11. an infrared detection module; 12. an image scanning module; 13. a data sorting module; 14. an image sending module A; 2. an image processing module; 21. an image acceptance module A; 22. an image smoothness restoration module; 23. an edge detection module; 24. an edge repair module; 25. an image noise reduction module; 26. an image enhancement module; 27. an image sending module B; 3. an image recognition module; 31. an image acceptance module B; 32. an image feature extraction module; 33. an image information extraction module; 34. an image and sound extraction module; 35. an information classification module; 4. a central processing unit; 41. an intelligent analysis module; 42. a learning database; 43. a storage module A; 44. a storage module B; 45. a storage module C; 46. an image database; 47. and a timing retrieval module.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-5, the present invention provides a technical solution: an intelligent weight-identifying image recognition system based on a deep learning algorithm comprises an image acquisition module 1, an image processing module 2, an image recognition module 3 and a central processing unit 4, wherein the output end of the image acquisition module 1 is electrically connected with the input end of the image processing module 2, the output end of the image processing module 2 is electrically connected with the input end of the image recognition module 3, the image recognition module 3 is electrically connected with the central processing unit 4 in a bidirectional mode, and the output end of the central processing unit 4 is electrically connected with the input ends of the image acquisition module 1 and the image processing module 2 respectively;
the image acquisition module 1 comprises an infrared detection module 11, an image scanning module 12, a data sorting module 13 and an image sending module A14, wherein the output end of the infrared detection module 11 is electrically connected with the input end of the image scanning module 12, the output end of the image scanning module 12 is electrically connected with the input end of the data sorting module 13, the output end of the data sorting module 13 is electrically connected with the input end of the image sending module A14, and the output end of the image sending module A14 is electrically connected with the input end of the image processing module 2;
the image processing module 2 comprises an image receiving module A21, an input end of the image receiving module A21 is electrically connected with an output end of the image sending module A14, an output end of the image receiving module A21 is electrically connected with an input end of the image smoothness restoration module 22, the image smoothness restoration module 22 can restore smoothness of image information of the image information by the aid of the image smoothness restoration module 22, subsequent identification work is facilitated, and an output end of the image smoothness restoration module 22 is electrically connected with an input end of the edge detection module 23;
the output end of the edge detection module 23 is electrically connected to the input end of the edge restoration module 24, the output end of the edge restoration module 24 is electrically connected to the input end of the image noise reduction module 25, the output end of the image noise reduction module 25 is electrically connected to the input end of the image enhancement module 26, the output end of the image enhancement module 26 is electrically connected to the input end of the image sending module B27, and by setting the image enhancement module 26, the image enhancement module 26 can enhance and amplify the features in the image information, so that the subsequent feature extraction work is more convenient, and the output end of the image sending module B27 is electrically connected to the input end of the image recognition module 3;
the image recognition module 3 comprises an image receiving module B31, an input end of an image receiving module B31 is electrically connected with an output end of an image sending module B27, an output end of an image receiving module B31 is electrically connected with an input end of an image feature extraction module 32, and an output end of the image feature extraction module 32 is electrically connected with an input end of an image information extraction module 33;
the output end of the image information extraction module 33 is electrically connected with the input end of the image sound extraction module 34, the output end of the image sound extraction module 34 is electrically connected with the input end of the information classification module 35, and by arranging the information classification module 35, the extracted different information can be classified by the information classification module 35, so that the identification and authentication work can be more conveniently and rapidly carried out, and the output end of the information classification module 35 is electrically connected with the input end of the central processing unit 4;
the central processing unit 4 comprises an intelligent analysis module 41, the input end of the intelligent analysis module 41 is electrically connected with the output end of the information classification module 35, and the output end of the intelligent analysis module 41 is electrically connected with the input ends of a learning database 42 and an image database 46 respectively;
the output end of the learning database 42 is electrically connected to the input ends of the storage module a43, the storage module B44 and the storage module C45, and by setting the storage module a43, the storage module B44 and the storage module C45, the storage module a43, the storage module B44 and the storage module C45 can store the extracted different features, so that the subsequent operation of the timing retrieval module 47 is facilitated, and the output ends of the storage module a43, the storage module B44 and the storage module C45 are electrically connected to the input end of the timing retrieval module 47;
the output end of the timing retrieval module 47 is electrically connected with the input end of the learning database 42;
the output end of the central processing unit 4 is electrically connected with the input end of the timing retrieval module 47, and the input end of the timing retrieval module 47 is electrically connected with the output end of the central processing unit 4, so that the information retrieved by the timing retrieval module 47 can be transmitted to the central processing unit 4, and the subsequent identification and authentication work of the central processing unit 4 is facilitated.
The working principle is as follows: when in use, the infrared detection module 11 can transmit the detected image information to the image scanning module 12, the image scanning module 12 scans the image information, then transmits the image information to the data arrangement module 13, the data arrangement module 13 arranges the image information and transmits the arranged image information to the image sending module, at this time, the image sending module a14 transmits the information to the image receiving module a21, the image receiving module a21 can transmit the information to the image smoothness repair module 22, the image smoothness repair module 22 can repair the image information, the repaired image information is transmitted to the edge detection module 23, the edge detection module 23 detects the edges of the image information, after the detection, the edge detection module 23 transmits the detected image information to the edge repair module 24, the edge repair module 24 can repair the image information according to the incomplete information detected by the edge detection module 23, the restored image information can be transmitted to the image denoising module 25, the image denoising module 25 performs denoising on the image information, then the image denoising module 25 can transmit the denoised image information to the image enhancement module 26, the image enhancement module 26 can enhance and amplify part of the features of the image information, finally the restored and feature-amplified image information is transmitted to the image receiving module B31 through the image transmitting module, the image receiving module B31 transmits the image information to the image feature extraction module 32, the image feature extraction module 32 can extract the features in the image information and transmit the extracted features and the image information to the image sound extraction module 34, the image sound extraction module 34 extracts the sound in the image information and transmits the extracted information and the image information to the information classification module 35, the information classification module 35 can classify the extracted different information and transmit the information to the intelligent analysis module 41, after the identified and classified image information is transmitted to the intelligent analysis module 41, the intelligent analysis module 41 transmits the image information to the image database 46, so that the identification and authentication work is performed through the original image information in the image database 46, meanwhile, the intelligent analysis module 41 can transmit the image information to the learning database 42, the learning database 42 can integrate the received image information and sequentially transmit the information with different characteristics to the storage module a43, the storage module B44 and the storage module C45, the storage module a43, the storage module B44 and the storage module C45 can store the extracted different characteristics, thereby facilitating the subsequent retrieval work, meanwhile, the timing retrieval module 47 can transmit the information to the learning database 42 in a timing manner, the learning database 42 transfers the information to the storage module a43, the storage module B44 and the storage module C45, so that the storage module a43, the storage module B44 and the storage module C45 can transfer the information to the timing retrieval module 47, so that the timing retrieval module 47 can learn the characteristics in the storage module a43, the storage module B44 and the storage module C45 thereof, and then the timing retrieval module 47 can transfer the retrieved information to the central processing unit 4.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (9)
1. An intelligent weight-identifying image recognition system based on a deep learning algorithm comprises an image acquisition module (1), an image processing module (2), an image recognition module (3) and a central processing unit (4), and is characterized in that the output end of the image acquisition module (1) is electrically connected with the input end of the image processing module (2), the output end of the image processing module (2) is electrically connected with the input end of the image recognition module (3), the image recognition module (3) is electrically connected with the central processing unit (4) in a bidirectional mode, and the output end of the central processing unit (4) is electrically connected with the input ends of the image acquisition module (1) and the image processing module (2) respectively;
the image acquisition module (1) comprises an infrared detection module (11), an image scanning module (12), a data sorting module (13) and an image sending module A (14), wherein the output end of the infrared detection module (11) is electrically connected with the input end of the image scanning module (12), the output end of the image scanning module (12) is electrically connected with the input end of the data sorting module (13), the output end of the data sorting module (13) is electrically connected with the input end of the image sending module A (14), and the output end of the image sending module A (14) is electrically connected with the input end of the image processing module (2).
2. The image recognition system for intelligent weight recognition based on deep learning algorithm as claimed in claim 1, wherein the image processing module (2) comprises an image receiving module a (21), an input of the image receiving module a (21) is electrically connected to an output of the image sending module a (14), an output of the image receiving module a (21) is electrically connected to an input of the image smoothness restoring module (22), and an output of the image smoothness restoring module (22) is electrically connected to an input of the edge detecting module (23).
3. The image recognition system based on the intelligent weight recognition of the deep learning algorithm as claimed in claim 2, wherein the output end of the edge detection module (23) is electrically connected to the input end of the edge restoration module (24), the output end of the edge restoration module (24) is electrically connected to the input end of the image denoising module (25), the output end of the image denoising module (25) is electrically connected to the input end of the image enhancement module (26), the output end of the image enhancement module (26) is electrically connected to the input end of the image sending module B (27), and the output end of the image sending module B (27) is electrically connected to the input end of the image recognition module (3).
4. The intelligent heavy-identification image recognition system based on the deep learning algorithm as claimed in claim 1, wherein the image recognition module (3) comprises an image receiving module B (31), an input end of the image receiving module B (31) is electrically connected with an output end of the image sending module B (27), an output end of the image receiving module B (31) is electrically connected with an input end of the image feature extraction module (32), and an output end of the image feature extraction module (32) is electrically connected with an input end of the image information extraction module (33).
5. The image recognition system based on the deep learning algorithm for intelligent weight recognition as claimed in claim 4, wherein the output end of the image information extraction module (33) is electrically connected to the input end of the image sound extraction module (34), the output end of the image sound extraction module (34) is electrically connected to the input end of the information classification module (35), and the output end of the information classification module (35) is electrically connected to the input end of the central processing unit (4).
6. The image recognition system based on the deep learning algorithm for intelligent weight recognition as claimed in claim 1, wherein the central processing unit (4) comprises an intelligent analysis module (41), an input end of the intelligent analysis module (41) is electrically connected with an output end of the information classification module (35), and an output end of the intelligent analysis module (41) is electrically connected with an input end of the learning database (42) and an input end of the image database (46), respectively.
7. The system for intelligently recognizing the weight of the person based on the deep learning algorithm as claimed in claim 6, wherein the output end of the learning database (42) is electrically connected to the input ends of the storage module A (43), the storage module B (44) and the storage module C (45), respectively, and the output ends of the storage module A (43), the storage module B (44) and the storage module C (45) are electrically connected to the input end of the timing retrieval module (47).
8. The system for intelligently recognizing the heavy object based on the deep learning algorithm as claimed in claim 7, wherein the output end of the timing retrieval module (47) is electrically connected with the input end of the learning database (42).
9. The intelligent heavy image recognition system based on the deep learning algorithm as claimed in claim 1, wherein the output end of the central processing unit (4) is electrically connected with the input end of the timing retrieval module (47).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110222190.1A CN112949473A (en) | 2021-02-28 | 2021-02-28 | Intelligent weight recognizing image recognition system based on deep learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110222190.1A CN112949473A (en) | 2021-02-28 | 2021-02-28 | Intelligent weight recognizing image recognition system based on deep learning algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112949473A true CN112949473A (en) | 2021-06-11 |
Family
ID=76246712
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110222190.1A Withdrawn CN112949473A (en) | 2021-02-28 | 2021-02-28 | Intelligent weight recognizing image recognition system based on deep learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112949473A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114789870A (en) * | 2022-05-20 | 2022-07-26 | 深圳市信成医疗科技有限公司 | Innovative modular drug storage management implementation mode |
-
2021
- 2021-02-28 CN CN202110222190.1A patent/CN112949473A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114789870A (en) * | 2022-05-20 | 2022-07-26 | 深圳市信成医疗科技有限公司 | Innovative modular drug storage management implementation mode |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8867828B2 (en) | Text region detection system and method | |
| WO2018166116A1 (en) | Car damage recognition method, electronic apparatus and computer-readable storage medium | |
| CN110008909B (en) | Real-name system business real-time auditing system based on AI | |
| WO2015188556A1 (en) | Multi-cue fusion based ticket positioning recognition method and system | |
| US8842880B2 (en) | Information processing apparatus, method of controlling information processing apparatus, and storage medium | |
| CN103778409A (en) | Human face identification method based on human face characteristic data mining and device | |
| WO2020164278A1 (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN109145742A (en) | A kind of pedestrian recognition method and system | |
| US11967176B2 (en) | Facial recognition method, facial recognition system, and electronic device | |
| CN103824091A (en) | Vehicle license plate recognition method for intelligent transportation system | |
| CN101587485A (en) | Face information automatic login method based on face recognition technology | |
| CN104021397A (en) | Face identifying and comparing method and device | |
| CN114898466A (en) | Video motion recognition method and system for smart factory | |
| CN114155445A (en) | SAR image target detection method based on improved YOLOv3 | |
| CN112949473A (en) | Intelligent weight recognizing image recognition system based on deep learning algorithm | |
| CN106407966A (en) | Face identification method applied to checking attendance | |
| CN201698456U (en) | Real-time face detecting and recognizing device | |
| CN111898555B (en) | Book checking identification method, device, equipment and system based on images and texts | |
| WO2015030689A2 (en) | A tool and method for robust, scale and orientation invariant object detection and classification | |
| CN103886303A (en) | Palmprint recognition method and device | |
| Mathew et al. | Person re-identification through face detection from videos using Deep Learning | |
| CN112069898A (en) | Method and device for recognizing human face group attribute based on transfer learning | |
| TWI430187B (en) | License plate number identification method | |
| CN204496527U (en) | A kind of novel three-dimensional objects recognition device | |
| CN106326882A (en) | Fingerprint identification system and fingerprint identification method based on image quality assessment technology |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210611 |
|
| WW01 | Invention patent application withdrawn after publication |