• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.4
• /
• pp.187-194
• /
• 2015

In this paper, we present an effective visual odometry estimation system to track the real-time pose of a camera moving in 3D space. In order to meet the real-time requirement as well as to make full use of rich information from color and depth images, our system adopts a feature-based sparse odometry estimation method. After matching features extracted from across image frames, it repeats both the additional inlier set refinement and the motion refinement to get more accurate estimate of camera odometry. Moreover, even when the remaining inlier set is not sufficient, our system computes the final odometry estimate in proportion to the size of the inlier set, which improves the tracking success rate greatly. Through experiments with TUM benchmark datasets and implementation of the 3D scene reconstruction application, we confirmed the high performance of the proposed visual odometry estimation method.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.1-7
• /
• 2021

In this paper, we propose a feature selection technique for multi-label classification. Many existing feature selection techniques have selected features by calculating the relation between features and labels such as a mutual information scale. However, since the mutual information measure requires a joint probability, it is difficult to calculate the joint probability from an actual premise feature set. Therefore, it has the disadvantage that only a few features can be calculated and only local optimization is possible. Away from this regional optimization problem, we propose a feature selection technique that constructs a low-rank space in the entire given feature space and selects features with sparsity. To this end, we designed a regression-based objective function using Nuclear norm, and proposed an algorithm of gradient descent method to solve the optimization problem of this objective function. Based on the results of multi-label classification experiments on four data and three multi-label classification performance, the proposed methodology showed better performance than the existing feature selection technique. In addition, it was showed by experimental results that the performance change is insensitive even to the parameter value change of the proposed objective function.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.49-56
• /
• 2024

There have been emerging many use-cases applying recommendation systems especially in online platform. Although the performance of recommendation systems is affected by a variety of factors, selecting appropriate features is difficult since most of recommendation systems have sparse data. Conventional matrix factorization (MF) method is a basic way to handle with problems in the recommendation systems. However, the MF based scheme cannot reflect non-linearity characteristics well. As deep learning technology has been attracted widely, a deep neural network (DNN) framework based collaborative filtering (CF) was introduced to complement the non-linearity issue. However, there is still a problem related to feature embedding for use as input to the DNN. In this paper, we propose an effective method using singular value decomposition (SVD) based feature embedding for improving the DNN performance of recommendation algorithms. We evaluate the performance of recommendation systems using MovieLens dataset and show the proposed scheme outperforms the existing methods. Moreover, we analyze the performance according to the number of latent features in the proposed algorithm. We expect that the proposed scheme can be applied to the generalized recommendation systems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.12
• /
• pp.5464-5484
• /
• 2016

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.302-320
• /
• 2017

In this paper, an innovative robust feature detection and matching strategy for visual odometry based on stereo image sequence is proposed. First, a sparse multiscale 2D local invariant feature detection and description algorithm AKAZE is adopted to extract the interest points. A robust feature matching strategy is introduced to match AKAZE descriptors. In order to remove the outliers which are mismatched features or on dynamic objects, an improved random sample consensus outlier rejection scheme is presented. Thus the proposed method can be applied to dynamic environment. Then, geometric constraints are incorporated into the motion estimation without time-consuming 3-dimensional scene reconstruction. Last, an iterated sigma point Kalman Filter is adopted to refine the motion results. The presented ego-motion scheme is applied to benchmark datasets and compared with state-of-the-art approaches with data captured on campus in a considerably cluttered environment, where the superiorities are proved.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.246-254
• /
• 2020

In this paper, we propose a learning based compressive sensing algorithm for the purpose of side scan sonar image denoising. The proposed method is based on Iterative Shrinkage and Thresholding Algorithm (ISTA) framework and incorporates a powerful strategy that reinforces the non-linearity of deep learning network for improved performance. The proposed method consists of three essential modules. The first module consists of a non-linear transform for input and initialization while the second module contains the ISTA block that maps the input features to sparse space and performs inverse transform. The third module is to transform from non-linear feature space to pixel space. Superiority in noise removal and memory efficiency of the proposed method is verified through various experiments.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.369-384
• /
• 2021

In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.30-41
• /
• 2020

Lines and textures are natural properties of the surface of natural objects, and their images can be sparsely represented in suitable frames such as wavelets, curvelets and wave atoms. Based on characteristics that the curvelets framework is good at expressing the line feature and wavesat is good at representing texture features, we propose a model for the weighted sparsity constraints of the two frames. Furtherly, a multi-step iterative fast algorithm for solving the model is also proposed based on the split Bergman method. By introducing auxiliary variables and the Bergman distance, the original problem is transformed into an iterative solution of two simple sub-problems, which greatly reduces the computational complexity. Experiments using standard images show that the split-based Bergman iterative algorithm in hybrid domain defeats the traditional Wavelets framework or curvelets framework both in terms of timeliness and recovery accuracy, which demonstrates the validity of the model and algorithm in this paper.

• Journal of the Korea Computer Graphics Society
• /
• v.22 no.3
• /
• pp.21-29
• /
• 2016

Cell segmentation is an important but time-consuming and laborious task in biological image analysis. An automated, robust, and fast method is required to overcome such burdensome processes. These needs are, however, challenging due to various cell shapes, intensity, and incomplete boundaries. A precise cell segmentation will allow to making a pathological diagnosis of tissue samples. A vast body of literature exists on cell segmentation in microscopy images [1]. The majority of existing work is based on input images and predefined feature models only - for example, using a deformable model to extract edge boundaries in the image. Only a handful of recent methods employ data-driven approaches, such as supervised learning. In this paper, we propose a novel data-driven cell segmentation algorithm for bright-field microscopy images. The proposed method minimizes an energy formula defined by two dictionaries - one is for input images and the other is for their manual segmentation results - and a common sparse code, which aims to find the pixel-level classification by deploying the learned dictionaries on new images. In contrast to deformable models, we do not need to know a prior knowledge of objects. We also employed convolutional sparse coding and Alternating Direction of Multiplier Method (ADMM) for fast dictionary learning and energy minimization. Unlike an existing method [1], our method trains both dictionaries concurrently, and is implemented using the GPU device for faster performance.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.248-257
• /
• 2002

Clustering is a method for grouping objects with similar properties into a same cluster. SVD(Singular Value Decomposition) is known as an efficient preprocessing method for clustering because of dimension reduction and noise elimination for a high dimensional and sparse data set like E-Commerce data set. However, it is hard to evaluate the worth of original attributes because of information loss of a converted data set by SVD. This research proposes a cluster feature selection method, called ENTROPY-SVD, to find important attributes for each cluster based on entropy weighting and SVD. Using SVD, one can take advantage of the latent structures in the association of attributes with similar objects and, using entropy weighting one can find highly dense attributes for each cluster. This paper also proposes a model-based collaborative filtering recommendation system with ENTROPY-SVD, called CFS-CF and evaluates its efficiency and utilization.