Marathon athletes number recognition model with compound deep neural network
- PDF / 2,113,150 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 68 Downloads / 271 Views
ORIGINAL PAPER
Marathon athletes number recognition model with compound deep neural network Xin Wang1 · Junxiang Yang2 Received: 18 March 2019 / Revised: 11 March 2020 / Accepted: 18 March 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract A large number of photos are taken for each athlete during a marathon competition, therefore, how to classify photos of specific athletes accurately and effectively has become the focus of attention. In this paper, we propose a compound deep neural network for marathon athletes number recognition to make classification more efficient and accurate. The proposed model is divided into three modules: image preprocessing module, text detection module, and text recognition module. Firstly, in the preprocessing module, we make use of the You Only Look Once version 3, and set the detection threshold and similarity threshold to reduce unnecessary detection. Secondly, we combine the efficient text detector Connectionist Text Proposal Network and the excellent text recognition general framework Convolutional Recurrent Neural Network (CRNN) to recognize the athletes number plates. Besides, to improve the accuracy of detection, we use transfer learning to fine-tune the CRNN. Finally, we design an effective tree filtering algorithm to avoid the interference caused by the text detection module. It can filter out invalid results, thereby improving the accuracy of the model. Our model is capable of performing classification on photos of marathon athletes with high precision. The model is feasible and effective, as indicated by the experiment results. Keywords Image classification · Athlete number recognition · Compound deep neural network · Tree filtering algorithm
1 Introduction In recent years, the number of marathons around the world is increasing exponentially. Due to the huge number of participants, event services are faced with great challenges. Among these challenges, classifying and pushing photos of athletes taken during the marathon is the most challenging one. In November 2018, over 50,000 people participated in the 2018 New York marathon. Assume the service providers took more than 4 photos for each athlete, the number of photos would exceed 200,000. Consequently, it requires an efficient and accurate classification algorithm to accomplish the purpose of photos pushing service.
B
Xin Wang [email protected] Junxiang Yang [email protected]
1
College of Computer Science and Technology, Key Laboratory of Symbolic Computation and Knowledge, Jilin University, Changchun, China
2
College of Computer Science and Technology, Jilin University, Changchun, China
At present, classifying photos by recognizing athletes number plates is one of the commonly used methods. These methods are mainly divided into two categories: the traditional ones and the deep learning ones. When using the traditional methods, the first step is locating the human bodies, which is generally done by algorithms such as the Deformable Parts Model (DPM) method [1]. After that, the number plat
Data Loading...
