scholarly journals An Attention-based Text Detection and Recognition Method for Terminals of Current Transformer’s Secondary Circuit

2021 ◽  
Vol 2137 (1) ◽  
pp. 012022
Author(s):  
Da Lu ◽  
Jia Liu ◽  
Helong Li
Keyword(s):  
Positional Information ◽  
Text Detection ◽  
Text Recognition ◽  
Secondary Circuit ◽  
Recognition Method ◽  
Fine Grained ◽  
Actual Working ◽  
Background Clutter ◽  
Detection And Recognition

Abstract Recognizing irregular text in real industrial scenes is a challenging task due to the background clutter, low resolutions or distortions. In this work, an attention-based text detection and recognition method for terminals of current transformer’s secondary circuit is proposed. It consists of three major components: pre-processing, text detection and text recognition. In text recognition module, a novel spatial temporal embedding is designed to better utilize the positional information. During training, the proposed framework only requires sequence-level annotations, instead of extra fine-grained character-level boxes or segmentation masks as in previous work. Despite its simplicity, the proposed method achieves good performance on the dataset collected in actual working scene.

scholarly journals DetReco: Object-Text Detection and Recognition Based on Deep Neural Network

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Fan Zhang ◽  
Jiaxing Luan ◽  
Zhichao Xu ◽  
Wei Chen
Keyword(s):  
Intelligent Transportation Systems ◽  
Research Effort ◽  
Recognition Task ◽  
Autonomous Driving ◽  
Transportation Systems ◽  
Text Detection ◽  
Text Recognition ◽  
Test Time ◽  
Average Precision ◽  
Detection And Recognition

Deep learning-based object detection method has been applied in various fields, such as ITS (intelligent transportation systems) and ADS (autonomous driving systems). Meanwhile, text detection and recognition in different scenes have also attracted much attention and research effort. In this article, we propose a new object-text detection and recognition method termed “DetReco” to detect objects and texts and recognize the text contents. The proposed method is composed of object-text detection network and text recognition network. YOLOv3 is used as the algorithm for the object-text detection task and CRNN is employed to deal with the text recognition task. We combine the datasets of general objects and texts together to train the networks. At test time, the detection network detects various objects in an image. Then, the text images are passed to the text recognition network to derive the text contents. The experiments show that the proposed method achieves 78.3 mAP (mean Average Precision) for general objects and 72.8 AP (Average Precision) for texts in regard to detection performance. Furthermore, the proposed method is able to detect and recognize affine transformed or occluded texts with robustness. In addition, for the texts detected around general objects, the text contents can be used as the identifier to distinguish the object.

scholarly journals Improvement of the end-to-end scene text recognition method for “text-to-speech” conversion

2020 ◽  
Vol 18 (06) ◽  
pp. 2050052
Author(s):  
Fazliddin Makhmudov ◽  
Mukhriddin Mukhiddinov ◽  
Akmalbek Abdusalomov ◽  
Kuldoshbay Avazov ◽  
Utkir Khamdamov ◽  
...  
Keyword(s):  
Text Detection ◽  
Text Recognition ◽  
Natural Scenes ◽  
Natural Scene ◽  
Text To Speech ◽  
Convolutional Network ◽  
Full Color ◽  
Active Research ◽  
Natural Scene Images ◽  
Detection And Recognition

Methods for text detection and recognition in images of natural scenes have become an active research topic in computer vision and have obtained encouraging achievements over several benchmarks. In this paper, we introduce a robust yet simple pipeline that produces accurate and fast text detection and recognition for the Uzbek language in natural scene images using a fully convolutional network and the Tesseract OCR engine. First, the text detection step quickly predicts text in random orientations in full-color images with a single fully convolutional neural network, discarding redundant intermediate stages. Then, the text recognition step recognizes the Uzbek language, including both the Latin and Cyrillic alphabets, using a trained Tesseract OCR engine. Finally, the recognized text can be pronounced using the Uzbek language text-to-speech synthesizer. The proposed method was tested on the ICDAR 2013, ICDAR 2015 and MSRA-TD500 datasets, and it showed an advantage in efficiently detecting and recognizing text from natural scene images for assisting the visually impaired.

scholarly journals Inferring object properties from human interaction and transferring them to new motions

2021 ◽  
Author(s):  
Qian Zheng ◽  
Weikai Wu ◽  
Hanting Pan ◽  
Niloy Mitra ◽  
Daniel Cohen-Or ◽  
...  
Keyword(s):  
Human Interaction ◽  
Strongly Correlated ◽  
Recognition Method ◽  
Fine Grained ◽  
Object Property ◽  
Correlated Motions ◽  
Object Properties ◽  
New Synthesis ◽  
Related Object ◽  
Highly Correlated

AbstractHumans regularly interact with their surrounding objects. Such interactions often result in strongly correlated motions between humans and the interacting objects. We thus ask: “Is it possible to infer object properties from skeletal motion alone, even without seeing the interacting object itself?” In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone. This inference allows us to disentangle the motion from the object property and transfer object properties to a given motion. We collected a large number of videos and 3D skeletal motions of performing actors using an inertial motion capture device. We analyzed similar actions and learned subtle differences between them to reveal latent properties of the interacting objects. In particular, we learned to identify the interacting object, by estimating its weight, or its spillability. Our results clearly demonstrate that motions and interacting objects are highly correlated and that related object latent properties can be inferred from 3D skeleton sequences alone, leading to new synthesis possibilities for motions involving human interaction. Our dataset is available at http://vcc.szu.edu.cn/research/2020/IT.html.

A new detection and recognition method for optical fiber pre-warning system

Optik ◽  
2017 ◽  
Vol 137 ◽  
pp. 209-219 ◽  
Author(s):  
Hongquan Qu ◽  
Tong Zheng ◽  
Liping Pang ◽  
Xuelian Li
Keyword(s):  
Optical Fiber ◽  
Warning System ◽  
Recognition Method ◽  
Detection And Recognition
Sign in / Sign up

Export Citation Format

Share Document