• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.929-944
• /
• 2019

Many critical applications require accurate real-time human action recognition. However, there are many hurdles associated with capturing and pre-processing image data, calculating features, and classification because they consume significant resources for both storage and computation. To circumvent these hurdles, this paper presents a recognition machine learning (ML) based system model which uses reduced data structure features by projecting real 3D skeleton modality on virtual 2D space. The MMU VAAC dataset is used to test the proposed ML model. The results show a high accuracy rate of 97.88% which is only slightly lower than the accuracy when using the original 3D modality-based features but with a 75% reduction ratio from using RGB modality. These results motivate implementing the proposed recognition model on an embedded system platform in the future.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.84-87
• /
• 2018

Handwritten letter recognition is important for numerous real-world applications and many topics like human-machine interaction, education, entertainment, and more. This paper describes the implementation of a real-time handwritten letters recognition system on a common embedded computer. Recognition is performed using a customized convolutional neural network, which was designed to work with low computational resources such as the Raspberry Pi platform. The experimental results show that the proposed real-time system achieves an outstanding performance in the accuracy rate and the response time for recognition of twenty-six handwritten letters.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.423-430
• /
• 2021

Aiming Graph convolutional networks (GCNs) have achieved outstanding performances on skeleton-based action recognition. However, several problems remain in existing GCN-based methods, and the problem of low recognition rate caused by single input data information has not been effectively solved. In this article, we propose a Dual-stream fusion method that combines video data and skeleton data. The two networks respectively identify skeleton data and video data and fuse the probabilities of the two outputs to achieve the effect of information fusion. Experiments on two large dataset, Kinetics and NTU-RGBC+D Human Action Dataset, illustrate that our proposed method achieves state-of-the-art. Compared with the traditional method, the recognition accuracy is improved better.

• Journal of Information Processing Systems
• /
• v.18 no.3
• /
• pp.311-318
• /
• 2022

Tobacco sales enterprises often need to summarize and verify the daily sales bills, which may consume substantial manpower, and manual verification is prone to occasional errors. The use of artificial intelligence technology to realize the automatic identification and verification of such bills offers important practical significance. This study presents a novel multi-branch residual network for tobacco sales bills to improve the efficiency and accuracy of tobacco sales. First, geometric correction and edge alignment were performed on the input sales bill image. Second, the multi-branch residual network recognition model is established and trained using the preprocessed data. The comparative experimental results demonstrated that the correct recognition rate of the proposed method reached 98.84% on the China Tobacco Bill Image dataset, which is superior to that of most existing recognition methods.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.811-821
• /
• 2023

We propose an adaptive unmanned aerial vehicle (UAV)-assisted object recognition algorithm for urban surveillance scenarios. For UAV-assisted surveillance, UAVs are equipped with learning-based object recognition models and can collect surveillance image data. However, owing to the limitations of UAVs regarding power and computational resources, adaptive control must be performed accordingly. Therefore, we introduce a self-adaptive control strategy to maximize the time-averaged recognition performance subject to stability through a formulation based on Lyapunov optimization. Results from performance evaluations on real-world data demonstrate that the proposed algorithm achieves the desired performance improvements.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.27-32
• /
• 2024

Recently, there has been a growing interest in integrating physical toys into video gaming within the game content business. This paper introduces a novel method that leverages low-cost camera as an alternative to using sensor attachments to meet this rising demand. We address the limitations associated with low-cost cameras and propose an optical design tailored to the specific environment of model car recognition. We overcome the inherent limitations of low-cost cameras by proposing an optical design specifically tailored for model car recognition. This approach primarily focuses on recognizing the underside of the car and addresses the challenges associated with this particular perspective. Our method employs a transfer learning model that is specifically trained for this task. We have achieved a 100% recognition rate, highlighting the importance of collecting data under various camera exposures. This paper serves as a valuable case study for incorporating low-cost cameras into vision systems.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.167-176
• /
• 2005

This paper describes how the state tying model based on the decision tree which is one of Acoustic models used for speech recognition optimizes the model by reducing the number of mixture Gaussians of the output probability distribution. The state tying modeling uses a finite set of questions which is possible to include the phonological knowledge and the likelihood based decision criteria. And the recognition rate can be improved by increasing the number of mixture Gaussians of the output probability distribution. In this paper, we'll reduce the number of mixture Gaussians at the highest point of recognition rate by clustering the Gaussians. Bhattacharyya and Euclidean method will be used for the distance measure needed when clustering. And after calculating the mean and variance between the pair of lowest distance, the new Gaussians are created. The parameters for the new Gaussians are derived from the parameters of the Gaussians from which it is born. Experiments have been performed using the STOCKNAME (1,680) databases. And the test results show that the proposed method using Bhattacharyya distance measure maintains their recognition rate at $97.2\%$ and reduces the ratio of the number of mixture Gaussians by $1.0\%$. And the method using Euclidean distance measure shows that it maintains the recognition rate at $96.9\%$ and reduces the ratio of the number of mixture Gaussians by $1.0\%$. Then the methods can optimize the state tying model.

• 재활복지
• /
• v.20 no.3
• /
• pp.105-124
• /
• 2016

The This study aims to verify the causal relationship among physically disability persons participation in exercise, heart rate variance, and facial expression recognition. To achieve such research goal, this study targeted 139 physically disability persons and as for sampling, purposive sampling method was applied. After visiting a sporting stadium and club facilities that sporting events were held and explaining the purpose of the research in detail, only with those who agreed to participate in the research, their heart rate variance and facial emotion awareness were measured. With the results of measurement, mean value, standard deviation, correlation analysis, and structural equating model were analyzed, and the results are as follows. The quantity of exercise positively affected sympathetic activity and parasympathetic activity of autonomic nervous system. Exercise history of physically disability persons was found to have a positive influence on LF/HF, and it had a negative influence on parasympathetic activity. Sympathetic activity of physically disability persons turned out to have a positive effect on the recognition of the emotion, happiness, while the quantity of exercise had a negative influence on the recognition of the emotion, sadness. These findings were discussed and how those mechanisms that are relevant to the autonomic nervous system, facial expression recognition of physical disability persons.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.3
• /
• pp.1-7
• /
• 2007

In order to recognize a vehicle license plate, the region of the license plate should be extracted from a vehicle image. Then, character region should be separated from the background image and characters are recognized using some neural networks with selected feature vectors. Of course, choice of feature vectors which serve as the basis of the character recognition has an important effect on recognition result as well as reduction of data amount. In this paper, we propose a novel feature extraction method in which number images are decomposed into linear combination of eigennumbers and show the validity of this method by applying to the recognition of numeric characters in license plates. The experimental results show the recognition rate of 95.3% for about 500 vehicle images with multi-layer perceptron neural network in the eigennumber space. Compared with the conventional mesh feature, it shows a better recognition rate by 5%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.313-319
• /
• 1999

We devise the 3 models of Multilayered Recurrent Prediction Neural Network(MLRPNN), which are obtained by modifying the Multilayered Perceptron(MLP) with 4 layers. We experimentally study the speech recognition performance of 3 models by a comparative method, according to the variation of the prediction order, the number of neurons in two hidden layers, initial values of connecting weights and transfer function, respectively. By the experiment, the recognition performance of each MLRPNN is better than that of MLP. At the model that returns the output of the upper hidden layer to the lower hidden layer, the recognition performance shows the best value. All MLRPNNs, which have 10 or 15 neurons in the upper and lower hidden layer and is predicted by 3rd or 4th order, show the improved speech recognition rate. On learning, these MLRPNNs have a better recognition rate when we set the initial weights between -0.5 and 0.5, and use the unipolar sigmoid transfer function in the lower hidden layer.