CN103093206A - Car logo recognition method and device - Google Patents
Car logo recognition method and device Download PDFInfo
- Publication number
- CN103093206A CN103093206A CN201310022654XA CN201310022654A CN103093206A CN 103093206 A CN103093206 A CN 103093206A CN 201310022654X A CN201310022654X A CN 201310022654XA CN 201310022654 A CN201310022654 A CN 201310022654A CN 103093206 A CN103093206 A CN 103093206A
- Authority
- CN
- China
- Prior art keywords
- car
- hash
- image
- cryptographic hash
- mark
- 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 68
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000008447 perception Effects 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 19
- 238000010606 normalization Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 abstract 1
- 101150060512 SPATA6 gene Proteins 0.000 description 90
- 238000010586 diagram Methods 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 241001270131 Agaricus moelleri Species 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a car logo recognition method and a device. The method comprises the steps: carrying out preprocessing of gray equalization on a collected car logo images set; carrying out hash processing on the pre-processed images through a perceptual hash method; classifying hash values obtained from the hash processing and obtaining a hash value set; and carrying out car logo recognition on to-be-recognized images. Through the car logo recognition method and the device, accuracy of car logo recognition is improved.
Description
Technical field
The present invention relates to a kind of computer image processing technology field, particularly a kind of car other method of sign and device.
Background technology
Along with socioeconomic development, increasing of vehicle becomes inevitable by computer information, intelligentized management vehicle.License plate recognition technology is widely used in traffic flow monitoring, and the charge of highway bayonet socket is in red light violation vehicle monitoring and residential quarter automatic fare collection system.The most popular method of tracing at present the deck vehicle is to go out license plate number by Computer Automatic Recognition, and then whether Query Database is the deck suspected vehicles.But car plate is changed when waiting greatly factor to affect by partial occlusion, stain, distortion and ambient lighting, accuracy of identification reduces greatly, error is large, make troubles for traffic police and car owner, therefore it is inadequate relying on the identification vehicle license to trace the deck vehicle, present treatment technology can only be identified, but can not identify concrete vehicle car plate and large-scale, medium-sized, dilly in addition.
Summary of the invention
In order to achieve the above object, the present embodiment provides a kind of car other method of sign and device.
According to an aspect of the present invention, the invention provides the other method of a kind of car sign, the method comprises: the car that the gathers image set of marking on a map is carried out the pre-service of gray balance; Adopting the perception hash method to carry out Hash to described pretreated image processes; The cryptographic hash that processing obtains to Hash is classified and is obtained the cryptographic hash set; Image to be identified is carried out the car sign not.
Preferably, the pre-service that image set carries out gray balance of marking on a map comprises to the car that gathers: morphology is processed, target is extracted, the normalization of image.
Preferably Hash being processed the cryptographic hash obtain classifies and obtains the cryptographic hash set and comprise:
Utilize the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
Preferably image to be identified being carried out the car sign does not comprise:
The image of testing is carried out the car mark cut apart pre-service;
Adopt the perception hash algorithm to process the acquisition cryptographic hash to it, with described car mark template base contrast, carry out the car sign not.
The present embodiment provides not device of a kind of car sign, comprising: the first processing module is used for the car of the collection image set of marking on a map is carried out the pre-service of gray balance; The second processing module is used for adopting the perception hash method to carry out Hash to described pretreated image and processes; Sort module is used for that Hash is processed the cryptographic hash that obtains and classifies and obtain the cryptographic hash set; The first identification module is used for image to be identified is carried out the car sign not.
Preferably, the Hash processing is carried out in described the second processing in the following way: morphology is processed, target is extracted and the normalization of image.
Preferably, described sort module is used for utilizing the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
Preferably, described identification module comprises: pretreatment module, and the image that is used for testing carries out the car mark cuts apart pre-service; The second identification module is used for adopting the perception hash algorithm to process the acquisition cryptographic hash to it, with described car mark template base contrast, carries out the car sign not.
Description of drawings
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, the below will do one to the accompanying drawing of required use in embodiment or description of the Prior Art and introduce simply, apparently, accompanying drawing in the following describes is some embodiments of the present invention, for those of ordinary skills, under the prerequisite of not paying creative work, can also obtain according to these accompanying drawings other accompanying drawing.
Fig. 1 is the process flow diagram according to the other method of car sign of the embodiment of the present invention;
Fig. 2 be according to the car of embodiment of the present invention sign not Zhuan Zhi structured flowchart; And
Fig. 3 is the other process flow diagram of car sign according to the perception hash algorithm of the embodiment of the present invention.
Embodiment
For the purpose, technical scheme and the advantage that make the embodiment of the present invention clearer, below in conjunction with the accompanying drawing in the embodiment of the present invention, technical scheme in the embodiment of the present invention is clearly and completely described, obviously, described embodiment is the present invention's part embodiment, rather than whole embodiment.Based on the embodiment in the present invention, those of ordinary skills belong to the scope of protection of the invention not making the every other embodiment that obtains under the creative work prerequisite.
The present embodiment provides a kind of car sign other method, and Fig. 1 is that as shown in Figure 1, the method comprises the steps that S102 is to step S108 according to the process flow diagram of the other method of car sign of the embodiment of the present invention.
Step S102: the car that the gathers image set of marking on a map is carried out the pre-service of gray balance.
Step S104: adopt the perception hash method to carry out Hash to pretreated image and process.
Step S106: the cryptographic hash that processing obtains to Hash is classified and is obtained the cryptographic hash set.
Step S108: image to be identified is carried out the car sign not.
Preferably, the pre-service that image set carries out gray balance of marking on a map comprises to the car that gathers: morphology is processed, target is extracted, the normalization of image.
Preferably, Hash being processed the cryptographic hash obtain classifies and obtains the cryptographic hash set and comprise:
Utilize the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
Preferably image to be identified being carried out the car sign does not comprise: the image of testing is carried out the car mark cut apart pre-service; Adopt the perception hash algorithm to process the acquisition cryptographic hash to it, with the contrast of car mark template base, carry out the car sign not.
The present embodiment provides a kind of car sign Zhuan Zhi not, Fig. 2 be according to the car of embodiment of the present invention sign not Zhuan Zhi structured flowchart, as shown in Figure 2, this device comprises: the first processing module 22, carry out the pre-service of gray balance for image set that the car that gathers is marked on a map; The second processing module 24 is used for adopting the perception hash method to carry out Hash to pretreated image and processes; Sort module 26 is used for that Hash is processed the cryptographic hash that obtains and classifies and obtain the cryptographic hash set; The first identification module 28 is used for image to be identified is carried out the car sign not.
Preferably, the second processing module 24 is carried out the Hash processing in the following way: morphology is processed, target is extracted and the normalization of image.
Preferably, sort module 26 is used for utilizing the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
Preferably, identification module 28 comprises: pretreatment module, and the image that is used for testing carries out the car mark cuts apart pre-service; The second identification module is used for adopting the perception hash algorithm to process the acquisition cryptographic hash to it, with the contrast of car mark template base, carries out the car sign not.
The present embodiment provides a kind of car sign other method, and the method comprises the steps:
The first step: at first the car that the gathers image set of marking on a map is carried out pre-service, make the gray processing equalization of image.
Second step: adopt the perception hash method to carry out Hash to the pretreated image of the first step and process, obtain cryptographic hash.
The 3rd step: with the cryptographic hash that the obtains processing of classifying, set up the cryptographic hash template base.
The 4th step: image pre-service to be identified is identified.
Preferably, the pre-treatment step of acquisition image is:
(1) morphology is processed, and removes the cavity that binary image exists, and obtains more excellent segmentation effect;
(2) target is extracted, and utilizes the method for 8 connected component analyses to extract the simply connected car picture of marking on a map, removes residual noise, thereby obtains more excellent two-value profile diagram;
(3) normalization of image: cut out the car picture of marking on a map according to car mark type, obtain the size normalized image, the size of image is unified is the 16*16 pixel;
Preferably, the step of described acquisition cryptographic hash set is:
Utilize the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
Preferably, described car identifies other step and is: the image of testing is carried out the car mark cut apart pre-service, then adopt the perception hash algorithm to process the acquisition cryptographic hash to it, with the contrast of car mark template base, obtain last recognition result.
Preferred embodiment one
This preferred embodiment proposes a kind of effective fixation and recognition Automobile calibration method, at first carry out car target coarse positioning according to the car plate locating information stage, then adopt morphology to process and obtain car target fine positioning, use the perception hash algorithm that the car mark is processed and obtain the Hash sequence, to the method that the car mark is identified, this method speed is fast, and cryptographic hash is not subjected to high wide, the even impact of color of brightness of picture, improved car and identified other accuracy, and visual angle change has been had good robustness.
Preferred embodiment two
This preferred embodiment provides a kind of other method of car sign based on the perception Hash, the step of the method comprises car mark on a map pre-service, the feature extraction of picture, according to the Hash sequence, the test sample car is marked on a map at last and identify as being grouped in corresponding class, concrete steps are as follows:
Step 1: morphology pre-service
Car mark area image to car mark coarse positioning carries out the morphology processing, and the cavity that exists to remove binary image obtains more excellent segmentation effect.
Target is extracted
Utilize the method for 8 connected component analyses to extract a simply connected car heading mark, remove noise and obtain more excellent two-value profile diagram;
Image normalization
The car that cuts out standard according to the car mark profile coordinate picture of marking on a map obtains the size normalized image, and wherein the size of image is unified is the 16*16 pixel.
Step 2: obtain the Hash sequence
The image of the method that adopts the perception Hash after to normalization carries out Hash to be processed.
Step 3: Classification and Identification
Preferred embodiment three
This preferred embodiment provides a kind of other method of car sign based on the perception hash algorithm, comprises the following step:
(1) filming apparatus is installed on the position of highway crossing, charge station, parking lot or other requirement, vehicle is carried out image acquisition, obtain containing mark on a map the original image of picture of car;
(2) make car mark template image, concrete grammar is taken in advance the car mark that contains whole vehicles being carried out high definition, the car mark part in the cut-away view picture, and car mark type is arranged, form car mark template image;
(a) target is extracted
After morphology is processed, still may exist the part clutter noise to form piece not of uniform size, image is further carried out connected domain analysis, utilize the method that 8 connected components are analyzed to extract the car cursor position, obtain more excellent two-value profile diagram.
(b) position of objective contour image is mapped to coloured image and intercepts, obtain the target area.
(c) image normalization
For the impact of removal of images size on identification, should make the car mark placed in the middle, then the unification of image size is the 16*16 pixel.
(3) the perception Hash is processed
(a) simplify color: the picture after dwindling transfers 128 grades of gray scales to.That is to say, all pixels only have 128 kinds of colors altogether.
(b) calculate DCT:DCT and picture has been divided into the set of frequency and scale.When JPEG used the DCT of 16x16d, algorithm just used the DCT of 32X32.
(c) reduce DCT: when DCT is 32x32, only keep the left 8x8 in top, this part has represented the lowest frequency of picture.
(d) calculate the average gray of all 256 pixels
(e) with the gray scale of each pixel, compare with mean value.More than or equal to mean value, be designated as 1; Less than mean value, be designated as 0.
(f) with the previous step comparative result, combine, just formed the integer of 256, the fingerprint of Here it is car marks on a map picture.
(4) the car mark of car mark template base is all carried out the corresponding fingerprint that arrives of Hash processing, set up the Hash sequence sets.
The image to be identified that (5) will obtain carries out the Hash of step (3) to be processed, and obtains corresponding fingerprint.
(6) the Hash sequence of the acquisition in (5) and the Hash sequence of template base are compared, obtain corresponding car mark classification.
Preferred embodiment four
This preferred embodiment provides a kind of car sign other method, and Fig. 3 is the other process flow diagram of car sign according to the perception hash algorithm of the embodiment of the present invention, and as shown in Figure 3, the method comprises:
Step S302: car mark image library.
Step S304: Perception Features is extracted.
Step S306: the perception Hash sequence that generates every width image.
Step S308: set up hash database.
Step S310: the band coupling car picture of marking on a map.
Step S312: Perception Features is extracted.
Step S314: perception Hash sequence.
Step S316: the Hash contrast, if result is yes, carry out at S318.Otherwise, execution in step S320.
Step S318: differentiate result.
Step S320: refusal.
One of ordinary skill in the art will appreciate that: all or part of step that realizes said method embodiment can be completed by the hardware that programmed instruction is correlated with, aforesaid program can be stored in a computer read/write memory medium, this program is carried out the step that comprises said method embodiment when carrying out; And aforesaid storage medium comprises: the various media that can be program code stored such as ROM, RAM, magnetic disc or CD.
It should be noted that at last: above embodiment only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to previous embodiment, the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme that aforementioned each embodiment puts down in writing, and perhaps part technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the spirit and scope of various embodiments of the present invention technical scheme.
Claims (8)
1. the other method of car sign, is characterized in that, comprising:
The car that the gathers image set of marking on a map is carried out the pre-service of gray balance;
Adopting the perception hash method to carry out Hash to described pretreated image processes;
The cryptographic hash that processing obtains to Hash is classified and is obtained the cryptographic hash set;
Image to be identified is carried out the car sign not.
2. method according to claim 1, is characterized in that, the pre-service that image set carries out gray balance of marking on a map comprises to the car that gathers:
Morphology is processed, target is extracted, the normalization of image.
3. method according to claim 1, is characterized in that, Hash processed the cryptographic hash obtain classify and obtain the cryptographic hash set and comprise:
Utilize the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
4. method according to claim 3, is characterized in that, image to be identified carried out the car sign do not comprise:
The image of testing is carried out the car mark cut apart pre-service;
Adopt the perception hash algorithm to process the acquisition cryptographic hash to it, with described car mark template base contrast, carry out the car sign not.
Car sign not Zhuan Zhi, it is characterized in that, comprising:
The first processing module is carried out the pre-service of gray balance for image set that the car that gathers is marked on a map;
The second processing module is used for adopting the perception hash method to carry out Hash to described pretreated image and processes;
Sort module is used for that Hash is processed the cryptographic hash that obtains and classifies and obtain the cryptographic hash set;
The first identification module is used for image to be identified is carried out the car sign not.
6. device according to claim 5, is characterized in that, described the second processing module is carried out in the following way Hash and processed:
Morphology is processed, target is extracted and the normalization of image.
7. device according to claim 5, it is characterized in that, described sort module is used for utilizing the perception hash method to obtain mark on a map the cryptographic hash of picture of each width car, the car mark cryptographic hash that obtains is classified, obtain car mark template base, give a label in order to identify the car mark of this cryptographic hash representative for each cryptographic hash, obtain all car target classification results.
8. device according to claim 7, is characterized in that, described identification module comprises:
Pretreatment module, the image that is used for testing carries out the car mark cuts apart pre-service;
The second identification module is used for adopting the perception hash algorithm to process the acquisition cryptographic hash to it, with described car mark template base contrast, carries out the car sign not.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310022654XA CN103093206A (en) | 2013-01-21 | 2013-01-21 | Car logo recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310022654XA CN103093206A (en) | 2013-01-21 | 2013-01-21 | Car logo recognition method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103093206A true CN103093206A (en) | 2013-05-08 |
Family
ID=48205754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310022654XA Pending CN103093206A (en) | 2013-01-21 | 2013-01-21 | Car logo recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103093206A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103854488A (en) * | 2014-03-19 | 2014-06-11 | 浙江宇视科技有限公司 | Blacklist distributed identification method and blacklist distributed identification device |
| CN104457758A (en) * | 2014-12-19 | 2015-03-25 | 哈尔滨工业大学 | Video-acquisition-based Visual Map database establishing method and indoor visual positioning method using database |
| CN111009074A (en) * | 2018-10-04 | 2020-04-14 | 富士电机株式会社 | Management server, vending machine, and device identification information providing method |
| CN111680895A (en) * | 2020-05-26 | 2020-09-18 | 中国平安财产保险股份有限公司 | Data automatic labeling method and device, computer equipment and storage medium |
| CN113920605A (en) * | 2021-10-18 | 2022-01-11 | 北京中交国通智能交通系统技术有限公司 | Highway free flow charging data processing and verifying method and device |
| CN115550634A (en) * | 2022-09-19 | 2022-12-30 | 深圳市新龙鹏科技有限公司 | Video frame detection method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1997018525A1 (en) * | 1995-11-15 | 1997-05-22 | Cognitronics Imaging Systems, Inc. | Enhanced batched character image processing |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
| CN101719217A (en) * | 2009-12-15 | 2010-06-02 | 中国地质大学（武汉） | Elastic relaxation algorithm-based vehicle type identification system and elastic relaxation algorithm-based vehicle type identification method |
| CN102609713A (en) * | 2011-01-20 | 2012-07-25 | 索尼公司 | Method and equipment for classifying images |
-
2013
- 2013-01-21 CN CN201310022654XA patent/CN103093206A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5852685A (en) * | 1993-07-26 | 1998-12-22 | Cognitronics Imaging Systems, Inc. | Enhanced batched character image processing |
| WO1997018525A1 (en) * | 1995-11-15 | 1997-05-22 | Cognitronics Imaging Systems, Inc. | Enhanced batched character image processing |
| CN101630361A (en) * | 2008-12-30 | 2010-01-20 | 北京邮电大学 | Plate number, body color and mark identification-based equipment and plate number, body color and mark identification-based method for identifying fake plate vehicles |
| CN101719217A (en) * | 2009-12-15 | 2010-06-02 | 中国地质大学（武汉） | Elastic relaxation algorithm-based vehicle type identification system and elastic relaxation algorithm-based vehicle type identification method |
| CN102609713A (en) * | 2011-01-20 | 2012-07-25 | 索尼公司 | Method and equipment for classifying images |
Non-Patent Citations (1)
| Title |
|---|
| 曾勇: "图像感知哈希算法及应用", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103854488A (en) * | 2014-03-19 | 2014-06-11 | 浙江宇视科技有限公司 | Blacklist distributed identification method and blacklist distributed identification device |
| CN103854488B (en) * | 2014-03-19 | 2016-03-09 | 浙江宇视科技有限公司 | A kind of distributed discrimination method of blacklist and device |
| CN104457758A (en) * | 2014-12-19 | 2015-03-25 | 哈尔滨工业大学 | Video-acquisition-based Visual Map database establishing method and indoor visual positioning method using database |
| CN104457758B (en) * | 2014-12-19 | 2017-04-12 | 哈尔滨工业大学 | Video-acquisition-based Visual Map database establishing method and indoor visual positioning method using database |
| CN111009074A (en) * | 2018-10-04 | 2020-04-14 | 富士电机株式会社 | Management server, vending machine, and device identification information providing method |
| CN111009074B (en) * | 2018-10-04 | 2021-12-14 | 富士电机株式会社 | Management server, vending machine, and device identification information providing method |
| CN111680895A (en) * | 2020-05-26 | 2020-09-18 | 中国平安财产保险股份有限公司 | Data automatic labeling method and device, computer equipment and storage medium |
| CN113920605A (en) * | 2021-10-18 | 2022-01-11 | 北京中交国通智能交通系统技术有限公司 | Highway free flow charging data processing and verifying method and device |
| CN113920605B (en) * | 2021-10-18 | 2024-08-13 | 北京中交国通智能交通系统技术有限公司 | Highway free flow charging data processing and verifying method and device |
| CN115550634A (en) * | 2022-09-19 | 2022-12-30 | 深圳市新龙鹏科技有限公司 | Video frame detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109993056B (en) | Method, server and storage medium for identifying vehicle illegal behaviors | |
| CN101334836B (en) | License plate positioning method incorporating color, size and texture characteristic | |
| Xie et al. | A robust license plate detection and character recognition algorithm based on a combined feature extraction model and BPNN | |
| CN109726717B (en) | A vehicle comprehensive information detection system | |
| Sulaiman et al. | Development of automatic vehicle plate detection system | |
| CN103093201B (en) | Vehicle-logo location recognition methods and system | |
| CN103093206A (en) | Car logo recognition method and device | |
| CN105005989B (en) | A kind of vehicle target dividing method under weak contrast | |
| CN109215364B (en) | Traffic signal recognition method, system, device and storage medium | |
| CN102915433B (en) | Character combination-based license plate positioning and identifying method | |
| CN104392205A (en) | Abnormal vehicle license plate recognition method and system | |
| CN110991221B (en) | Dynamic traffic red light running recognition method based on deep learning | |
| CN104036241A (en) | License plate recognition method | |
| CN104361359A (en) | Vehicle recognition method based on image detection | |
| CN103310231A (en) | Auto logo locating and identifying method | |
| CN102799879A (en) | Method for identifying multi-language multi-font characters from natural scene image | |
| CN110909598A (en) | Deep learning-based method for recognizing illegal traffic driving of non-motor vehicle lane | |
| Azad et al. | New method for optimization of license plate recognition system with use of edge detection and connected component | |
| Sugiharto et al. | Traffic sign detection based on HOG and PHOG using binary SVM and k-NN | |
| CN102750530B (en) | Character recognition method and device | |
| CN111950469A (en) | Road sign detection method, system, equipment and medium | |
| CN108960055A (en) | A kind of method for detecting lane lines based on local line's stage mode feature | |
| CN111008554B (en) | Deep learning-based method for identifying pedestrians without giving away in dynamic traffic zebra stripes | |
| CN112396638A (en) | Image processing method, terminal and computer readable storage medium | |
| CN104182728A (en) | Vehicle logo automatic location and recognition method based on pattern recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130508 |