• 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 Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• Journal of the Chungcheong Mathematical Society
• /
• v.15 no.2
• /
• pp.85-96
• /
• 2003

An efficient algorithm for the multiplication in a binary finite filed using a normal basis representation of $F_{2^m}$ is discussed and proposed for software implementation of elliptic curve cryptography. The algorithm is developed by using the storage scheme of sparse matrices.

• Journal of Computing Science and Engineering
• /
• v.4 no.2
• /
• pp.110-127
• /
• 2010

In this study, we propose a method for encoding documents into string vectors, instead of numerical vectors. A traditional approach to text categorization usually requires encoding documents into numerical vectors. The usual method of encoding documents therefore causes two main problems: huge dimensionality and sparse distribution. In this study, we modify or create machine learning-based approaches to text categorization, where string vectors are received as input vectors, instead of numerical vectors. As a result, we can improve text categorization performance by avoiding these two problems.

• Journal of Information Processing Systems
• /
• v.4 no.2
• /
• pp.77-86
• /
• 2008

This research proposes a new neural network for text categorization which uses alternative representations of documents to numerical vectors. Since the proposed neural network is intended originally only for text categorization, it is called NTC (Neural Text Categorizer) in this research. Numerical vectors representing documents for tasks of text mining have inherently two main problems: huge dimensionality and sparse distribution. Although many various feature selection methods are developed to address the first problem, the reduced dimension remains still large. If the dimension is reduced excessively by a feature selection method, robustness of text categorization is degraded. Even if SVM (Support Vector Machine) is tolerable to huge dimensionality, it is not so to the second problem. The goal of this research is to address the two problems at same time by proposing a new representation of documents and a new neural network using the representation for its input vector.

• Journal of Electrical Engineering and Technology
• /
• v.10 no.4
• /
• pp.1851-1863
• /
• 2015

– In the paper, to handle the problem of traditional bag-of-features model ignoring the spatial relationship of local features in human action recognition, we proposed a Multiscale Spatial Position Coding under Locality Constraint method. Specifically, to describe this spatial relationship, we proposed a mixed feature combining motion feature and multi-spatial-scale configuration. To utilize temporal information between features, sub spatial-temporal-volumes are built. Next, the pooled features of sub-STVs are obtained via max-pooling method. In classification stage, the Locality-Constrained Group Sparse Representation is adopted to utilize the intrinsic group information of the sub-STV features. The experimental results on the KTH, Weizmann, and UCF sports datasets show that our action recognition system outperforms the classical local ST feature-based recognition systems published recently.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1412-1417
• /
• 2004

Sparse coding or independent component analysis (ICA) which is a holistic representation, was successfully applied to elucidate early auditor${\gamma}$ processing and to the task of sound classification. In contrast, parts-based representation is an alternative way o) understanding object recognition in brain. In this thesis we employ the non-negative matrix factorization (NMF) which learns parts-based representation in the task of sound classification. Methods of feature extraction from the spectro-temporal sounds using the NMF in the absence or presence of noise, are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.277-300
• /
• 2020

This paper presents a method for clustering short text documents, such as news headlines, social media statuses, or instant messages. Due to the characteristics of these documents, which are usually short and sparse, an appropriate technique is required to discover hidden knowledge. The objective of this paper is to identify the combination of document representation, document distance, and document clustering that yields the best clustering quality. Document representations are expanded by external knowledge sources represented by a Distributed Representation. To cluster documents, a K-means partitioning-based clustering technique is applied, where the similarities of documents are measured by word mover's distance. To validate the effectiveness of the proposed method, experiments were conducted to compare the clustering quality against several leading methods. The proposed method produced clusters of documents that resulted in higher precision, recall, F1-score, and adjusted Rand index for both real-world and standard data sets. Furthermore, manual inspection of the clustering results was conducted to observe the efficacy of the proposed method. The topics of each document cluster are undoubtedly reflected by members in the cluster.

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1495-1502
• /
• 2020

A new method of X-ray source spectrum estimation based on compressed sensing is proposed in this paper. The algorithm K-SVD is applied for sparse representation. Nonnegative constraints are added by modifying the L₁ reconstruction algorithm proposed by Rosset and Zhu. The estimation method is demonstrated on simulated spectra typical of mammography and CT. X-ray spectra are simulated with the Monte Carlo code Geant4. The proposed method is successfully applied to highly ill conditioned and under determined estimation problems with a good performance of suppressing noises. Results with acceptable accuracies (MSE < 5%) can be obtained with 10% Gaussian white noises added to the simulated experimental data. The biggest difference between the proposed method and the existing methods is that multiple prior knowledge of X-ray spectra can be included in one dictionary, which is meaningful for obtaining the true X-ray spectrum from the measurements.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.525-534
• /
• 2017

The open set recognition method should be used for the cases that the classes of test data are not known completely in the training phase. So it is required to include two processes of classification and the validation test. This kind of research is very necessary for commercialization of face recognition modules, but few domestic researches results about it have been published. In this paper, we propose an open set face recognition method that includes two sequential validation phases. In the first phase, with dummy classes we perform classification based on sparse representation. Here, when the test data is classified into a dummy class, we conclude that the data is invalid. If the data is classified into one of the regular training classes, for second validation test we extract four features and apply them for the proposed decision function. In experiments, we proposed a simulation method for open set recognition and showed that the proposed validation test outperform SCI of the well-known validation method