Efficient Neural Network for Text Recognition in Natural Scenes Based on End-to-End Multi-Scale Attention Mechanism

Peng, Huiling; Yu, Jia; Nie, Yalin

doi:10.3390/electronics12061395

Cited by 6 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among them, TP represents the number of characters correctly recognized by OCR, and FP represents the number of characters incorrectly recognized by OCR [42].…”

Section: Ocr Evaluation Indexmentioning

confidence: 99%

Pointer Meter Recognition Method Based on Yolov7 and Hough Transform

et al. 2023

View full text Add to dashboard Cite

The current manual reading of substation pointer meters wastes human resources, and existing algorithms have limitations in accuracy and robustness for detecting various pointer meters. This paper proposes a method for recognizing pointer meters based on Yolov7 and Hough transform to improve their automatic readability. The proposed method consists of three main contributions: (1) Using Yolov7 object detection technology, which is the latest Yolo technology, to enhance instrument recognition accuracy. (2) Providing a formula for calculating the angle of a square pointer meter after Hough transformation. (3) Applying OCR recognition to the instrument dial to obtain the model and scale value. This information helps differentiate between meter models and determine the measuring range. Test results demonstrate that the proposed algorithm achieves high accuracy and robustness in detecting different types and ranges of instruments. The map of the Yolov7 model on the instrument dataset is as high as 99.8%. Additionally, the accuracy of pointer readings obtained using this method exceeds 95%, indicating promising applications for a wide range of scenarios.

show abstract

“…Among them, TP represents the number of characters correctly recognized by OCR, and FP represents the number of characters incorrectly recognized by OCR [42].…”

Section: Ocr Evaluation Indexmentioning

confidence: 99%

Pointer Meter Recognition Method Based on Yolov7 and Hough Transform

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Compared with the hyper-LPR model, the UNET-GWO-SVM model designed in this paper dramatically improves the positioning accuracy and recognition speed. On the other hand, there is still a gap compared with different end-to-end neural network recognition algorithms [41][42][43][44]. However, they consider the applicability of embedded hardware.…”

Section: License Plate Recognition Experimentsmentioning

confidence: 99%

Smart Parking Locks Based on Extended UNET-GWO-SVM Algorithm

Shen,

Xia,

Ding

et al. 2023

Sensors

View full text Add to dashboard Cite

Due to the rapid increase in private car ownership in China, most cities face the problem of insufficient parking spaces, leading to frequent occurrences of parking space conflicts. There is a wide variety of parking locks available on the market. However, most of them lack advanced intelligence and cannot cater to the growing diverse needs of people. The present study attempts to devise a smart parking lock to tackle this issue. Specifically, the smart parking lock uses a Raspberry Pi as the core controller, senses the vehicle with an ultrasonic ranging module, and collects the license plate image with a camera. In addition, algorithms for license plate recognition based on traditional image-processing methods typically require a high pixel resolution, but their recognition accuracy is often low. Therefore, we propose a new algorithm called UNET-GWO-SVM to achieve higher accuracy in embedded systems. Moreover, we developed a WeChat mini program to control the smart parking lock. Field tests were conducted on campus to evaluate the performance of the parking locks. The test results show that the corresponding effective unlocking rate is 99.0% when the recognition error is less than two license plate characters. The average time consumption is controlled at about 2 s. It can meet real-time requirements.

show abstract

“…Neural networks can still be applied to the realm of text recognition, but necessitate adjustments to network architecture. Numerous backbone networks for object recognition [35,36], including VggNet [37,38], ResNet [39,40], and DenseNet [41,42], are also highly applicable to text recognition, elevating the recognition accuracy of individual characters. Dataset training is an indispensable component of neural network training, but in the course of researching vehicular screen text recognition, we discovered an almost complete absence of mature datasets within this field.…”

Section: Introductionmentioning

confidence: 99%

A Non-Intrusive Automated Testing System for Internet of Vehicles App Based on Deep Learning

Zhang

Sun

2023

Electronics

View full text Add to dashboard Cite

In the non-intrusive automated testing system for Internet of Vehicles (IoV) applications, automatic recognition of text and icons on vehicle central control screens is of paramount importance. However, the detection and recognition of content on vehicle central control screens are inherently complex. Additionally, during non-intrusive vehicle central control screen image testing, there is a deficiency of suitable datasets and detection methods. This deficiency renders information within vehicle application images difficult to be accurately extracted by the detection network. To address this problem, this study first constructs a dataset tailored for text detection and recognition on vehicle screens. This dataset encompasses a variety of vehicle central control images, enabling the generic text detection and recognition network to more effectively identify and interpret text within vehicle screens. Subsequently, this research proposes an enhanced Fully Convolutional Networks for Text Detection (FOTS) method for vehicle central control screen text detection and recognition. This method elevates the semantic expression capabilities of features by sharing vehicle central control screen text detection and recognition features. Furthermore, it improves multi-scale feature processing capabilities through the utilization of a feature transformation module. Validation through visual and quantitative experiments demonstrates that the proposed method can effectively accomplish text detection and recognition tasks on vehicle screens. This achievement bears significant implications for the field of automated testing in IoV applications.

show abstract

Efficient Neural Network for Text Recognition in Natural Scenes Based on End-to-End Multi-Scale Attention Mechanism

Cited by 6 publications

References 39 publications

Pointer Meter Recognition Method Based on Yolov7 and Hough Transform

Pointer Meter Recognition Method Based on Yolov7 and Hough Transform

Smart Parking Locks Based on Extended UNET-GWO-SVM Algorithm

A Non-Intrusive Automated Testing System for Internet of Vehicles App Based on Deep Learning

Contact Info

Product

Resources

About