IP Library › Granted Patent US 10,777,076
Granted Patent B2
US 10,777,076 · App. 16/219,902 · Granted Sep 15, 2020

License plate recognition system and license plate recognition method

Inventors: Shu-Heng Chen (Kaohsiung, TW); Chih-Lun Liao (Taichung, TW); Cheng-Feng Shen (Taipei, TW); Li-Yen Kuo (Tainan, TW); Yu-Shuo Liu (Taoyuan, TW); Shyh-Jian Tang (Taoyuan, TW); Chia-Lung Yeh (Taoyuan, TW)
Assignee: National Chung-Shan Institute of Science and Technology
G08G1/0175G06K9/3241G06K9/3258G06K9/6226G06K2209/15G06K2209/23
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,777,076
App. No.
16/219,902
Granted
Sep 15, 2020
Kind
B2
Abstract

A license plate recognition system and a license plate recognition method are provided. The license plate recognition system includes an image capturing module, a determination module and an output module. The image capturing module is utilized for capturing an image of a target object. The determination module is utilized for dividing the image of the target object into a plurality of image blocks. The determination module utilizes the plurality of image blocks to generate feature data and perform a data sorting process on the feature data to generate a first sorting result. The output module outputs the sorting result.

Claims (20)

1. A license plate recognition system, comprising:

an image capturing module for capturing an image of a target object;

a determination module, comprising:

a vehicle detection module, for dividing the image of the target object into a plurality of image blocks, utilizing the plurality of image blocks to generate a plurality of information and obtaining an vehicle image through the plurality of information;

a license plate detection module, for performing a feature determination process on the vehicle image to obtain a license plate image; and

a license plate recognition module, for performing a feature extraction process on the license plate image to obtain a feature vector and performing a classifying process on the feature vector to generate corresponding probabilities and performing a data sorting process on the corresponding probabilities to generate a sorting result; and

an output module, for outputting the sorting result.

2. The license plate recognition system of claim 1 , wherein the vehicle detection module comprises a grid cell division operation and the network output.

3. The license plate recognition system of claim 1 , wherein the license plate recognition module comprises a feature extraction module and a character recognition module.

4. The license plate recognition system of claim 1 , wherein

the feature determination process comprises a feature extraction, a feature merging and an output layer.

5. A license plate recognition method, comprising:

utilizing an image capturing module to capture an image of a target object;

utilizing a vehicle detection module to perform a grid cell division operation to obtain a plurality of image blocks and calculating the plurality of image blocks to generate a plurality of information and arranging the plurality of information to obtain a vehicle image; and

utilizing a license plate detection module to perform a feature determination process on the vehicle image to obtain a license plate image, and utilizing a license plate recognition module to perform a feature extraction process on the license plate image to obtain a feature map, reshape the feature map to obtain a feature vector, perform a classifying process on the feature vector to generate a corresponding probability, perform a data sorting process on the corresponding probability to generate a sorting result, and utilizing an output module to output the sorting result.

6. The license plate recognition method of claim 5 , wherein the feature determination process comprises a feature extraction, a feature merging and an output layer.

7. A license plate recognition module using the method according to claim 6 , comprising:

a feature extraction module for performing a feature extraction operation on the license plate image to obtain a feature map and reshapes the feature map so as to obtain a feature vector; and

a character recognition module for classifying the feature vectors, obtaining corresponding probabilities of the feature vector accordingly and performing a data sort process on the corresponding probabilities of the feature vectors to generate a sorting result.

8. The license plate recognition module of claim 7 , wherein the character recognition module comprises a long short-term memory (LSTM) and a connectionist temporal classification (CTC).

Assignments (2)
CORRECTIVE ASSIGNMENT TO CORRECT THE SIXTH CONVEYING PARTY DATA PREVIOUSLY RECORDED AT REEL: 047773 FRAME: 0200. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Jun 8, 2020
From: CHEN, SHU-HENG; LIAO, CHIH-LUN; SHEN, CHENG-FENG; KUO, LI-YEN; LIU, YU-SHUO; TANG, SHYH-JIAN; YEH, CHIA-LUNG
To: NATIONAL CHUNG-SHAN INSTITUTE OF SCIENCE AND TECHNOLOGY
Reel/Frame 052874/0032 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 13, 2018
From: CHEN, SHU-HENG; LIAO, CHIH-LUN; SHEN, CHENG-FENG; KUO, LI-YEN; LIU, YU-SHUO; TANG, SHYH-JIANG; YEH, CHIA-LUNG
To: NATIONAL CHUNG-SHAN INSTITUTE OF SCIENCE AND TECHNOLOGY
Reel/Frame 047773/0200 →
Priority Claims (1)
TW 107133286 A · Sep 19, 2018 · national
Continuity (1)
Related Publication 20200090506A1 · Mar 19, 2020