• ETRI Journal
• /
• v.32 no.4
• /
• pp.596-602
• /
• 2010

This paper proposes a computationally efficient learning-based super-resolution algorithm using k-means clustering. Conventional learning-based super-resolution requires a huge dictionary for reliable performance, which brings about a tremendous memory cost as well as a burdensome matching computation. In order to overcome this problem, the proposed algorithm significantly reduces the size of the trained dictionary by properly clustering similar patches at the learning phase. Experimental results show that the proposed algorithm provides superior visual quality to the conventional algorithms, while needing much less computational complexity.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.11
• /
• pp.345-350
• /
• 2020

Based on the analysis of physical and learning characteristics and requirements of the silver generation, a video English dictionary was developed and evaluated as English learning contents. The video English dictionary was developed using OCR as an input method and video as an output method, and 17 silver generations were evaluated for academic achievement, learning satisfaction, and ease of use. As a result of the analysis, both the text English dictionary and the video English dictionary showed high learning satisfaction, but the video English dictionary showed higher results than the text English dictionary in an academic achievement and ease of use.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Journal of Auto-vehicle Safety Association
• /
• v.8 no.1
• /
• pp.19-25
• /
• 2016

As new car technology is developing, temporal interaction is needed in automotive. Rhythmic pattern is one of the practical examples of temporal interaction in vehicle. To recognize rhythmic pattern and its input medium, dictionary learning is applicable algorithm. In this paper, performance and memory requirement of the learning algorithm is tested and is sufficiently good for use this acoustic sound.

• Journal of Broadcast Engineering
• /
• v.20 no.5
• /
• pp.676-686
• /
• 2015

A 4D light field image is represented in traditional 2D spatial domain and additional 2D angular domain. The 4D light field has a resolution limitation both in spatial and angular domains since 4D signals are captured by 2D CMOS sensor with limited resolution. In this paper, we propose a dictionary learning-based superresolution algorithm in 4D light field domain to overcome the resolution limitation. The proposed algorithm performs dictionary learning using a large number of extracted 4D light field patches. Then, a high resolution light field image is reconstructed from a low resolution input using the learned dictionary. In this paper, we reconstruct a 4D light field image to have double resolution both in spatial and angular domains. Experimental result shows that the proposed method outperforms the traditional method for the test images captured by a commercial light field camera, i.e. Lytro.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.1-15
• /
• 2021

Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.12
• /
• pp.1122-1132
• /
• 2012

Compressed sensing has been applied to many fields such as images, speech signals, radars, etc. It has been mainly applied to stationary signals, and reconstruction error could grow as compression ratios are increased by decreasing measurements. To resolve the problem, speech signals are divided into frames and processed in parallel. The frames are made sparse by dictionary learning, and adaptive compressed sensing is applied which designs the compressed sensing reconstruction matrix adaptively by using the difference between the sparse coefficient vector and its reconstruction. Through the proposed method, we could see that fast and accurate reconstruction of non-stationary signals is possible with compressed sensing.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.1037-1048
• /
• 2022

A radioactive isotope identification algorithm is a prerequisite for a low-resolution scintillation detector applied to an unmanned radiation monitoring system. In this paper, a sparse representation with dictionary learning approach is proposed and applied to plastic gamma-ray spectra. Label-consistent K-SVD was used to learn a discriminative dictionary for the spectra corresponding to a mixture of four isotopes (¹³³Ba, ²²Na, ¹³⁷Cs, and ⁶⁰Co). A Monte Carlo simulation was employed to produce the simulated data as learning samples. Experimental measurement was conducted to obtain practical spectra. After determining the hyper parameters, two dictionaries tailored to the learning samples were tested by varying with the source position and the measurement time. They achieved average accuracies of 97.6% and 98.0% for all testing spectra. The average accuracy of each dictionary was above 96% for spectra measured over 2 s. They also showed acceptable performance when the spectra were artificially shifted. Thus, the proposed method could be useful for identifying radioisotopes in gamma-ray spectra from a plastic scintillation detector even when a dictionary is adapted to only simulated data. Furthermore, owing to the outstanding properties of sparse representation, the proposed approach can easily be built into an insitu monitoring system.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.1
• /
• pp.57-65
• /
• 2017

In this paper, we present a dictionary learning method for reducing errors in point cloud models and reconstructing their geometry. For this, 3D feature information is extracted from the models which have a similar shape characteristic as the target model. Then a dictionary is constructed and the geometry is reconstructed using the dictionary. The presented method in this paper consists of the following three steps. First, a geometric patch is constructed from a similar model. Second, a morphological 3D feature of the acquired patch is learned. Third, a geometry reconstruction is performed using the learned dictionary. Finally, the error between the original model and the reconstruction result is calculated, and the accuracy of the reconstruction result is checked.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.6
• /
• pp.549-557
• /
• 2001

Morphological analysis and POS tagging require a dictionary for the language at hand . In this fashion though it is impossible to analyze a language a dictionary. We also have difficulty if significant portion of the vocabulary is new or unknown . This paper explores the possibility of learning morphology of an agglutinative language. in particular Korean language, without any prior lexical knowledge of the language. We use unsupervised learning in that there is no instructor to guide the outcome of the learner, nor any tagged corpus. Here are the main characteristics of the approach: First. we use only raw corpus without any tags attached or any dictionary. Second, unlike many heuristics that are theoretically ungrounded, this method is based on statistical methods , which are widely accepted. The method is currently applied only to Korean language but since it is essentially language-neutral it can easily be adapted to other agglutinative languages.