• Journal of Electrical Engineering and Technology
• /
• v.13 no.6
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.

• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.643-646
• /
• 2006

This paper addresses the approach to extract linear features from satellite imagery using an efficient segmentation method. The extraction of linear features from satellite images has been the main concern of many scientists. There is a need to develop a more capable and cost effective method for the Iranian map revision tasks. The conventional approaches for producing, maintaining, and updating GIS map are time consuming and costly process. Hence, this research is intended to investigate how to obtain linear features from SPOT satellite imagery. This was accomplished using a discontinuity-based segmentation technique that encompasses four stages: low level bottom-up, middle level bottom-up, edge thinning and accuracy assessment. The first step is geometric correction and noise removal using suitable operator. The second step includes choosing the appropriate edge detection method, finding its proper threshold and designing the built-up image. The next step is implementing edge thinning method using mathematical morphology technique. Lastly, the geometric accuracy assessment task for feature extraction as well as an assessment for the built-up result has been carried out. Overall, this approach has been applied successfully for linear feature extraction from SPOT image.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.272-275
• /
• 2016

This paper presents a method of single image dehazing and surface-based feature detection for remote sensing images. In the conventional dark channel prior (DCP) algorithm, the resulting transmission map invariably includes some block artifacts because of patch-based processing. This also causes image blur. Therefore, a refined transmission map based on a hidden Markov random field and expectation-maximization algorithm can reduce the block artifacts and also increase the image clarity. Also, the proposed algorithm enhances the accuracy of image matching surface-based features in an remote sensing image. Experimental results confirm that the proposed algorithm is superior to conventional algorithms in image haze removal. Moreover, the proposed algorithm is suitable for the problem of image matching based on feature extraction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4587-4605
• /
• 2019

High Efficiency Video Coding (HEVC) suffers from high computational complexity due to its quad-tree structure in motion estimation (ME). This paper exposes an adaptive search range decision algorithm for accelerating HEVC integer-pel ME on GPU which estimates the optimal search range (SR) using a MAP (Maximum A Posteriori) estimator. There are three main contributions; First, we define the motion feature as the standard deviation of motion vector difference values in a CTU. Second, a MAP estimator is proposed, which theoretically estimates the motion feature of the current CTU using the motion feature of a temporally adjacent CTU and its SR without any data dependency. Thus, the SR for the current CTU is parallelly determined. Finally, the values of the prior distribution and the likelihood for each discretized motion feature are computed in advance and stored at a look-up table to further save the computational complexity. Experimental results show in conventional HEVC test sequences that the proposed algorithm can achieves high average time reductions without any subjective quality loss as well as with little BD-bitrate increase.

• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.2
• /
• pp.65-76
• /
• 1994

The most effective computer algorithms for facility layout that have been found are mainly based on the improvement heuristic such as CRAFT. In this paper, we present a new algorithm which is based on the Kohonen neual network. The algorithm firstly forms a self-organizing feature map where the most important similarity relationships among the facilities are converted into their spatial relationships. A layout is then obtained by a minor adjustment to the map. Some simulation results are given to show the performance of the algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.42.6-42
• /
• 2002

Kohonen's self organizing feature map (SOFM) converts arbitrary dimensional patterns into one or two dimensional arrays of nodes. Among the many competitive learning algorithms, SOFM proposed by Kohonen is considered to be powerful in the sense that it not only clusters the input pattern adaptively but also organize the output node topologically. SOFM is usually used for a preprocessor or cluster. It can perform dimensional reduction of input patterns and obtain a topology-preserving map that preserves neighborhood relations of the input patterns. The traditional SOFM algorithm[1] is a competitive learning neural network that maps inputs to discrete points that are called nodes on a lattice...

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.39.1-39.20
• /
• 2019

Analyzing patterns in data points embedded in linear and non-linear feature spaces is considered as one of the common research problems among different research areas, for example: data mining, machine learning, pattern recognition, and multivariate analysis. In this paper, data points are heterogeneous sets of biosequences (composite data points). A composite data point is a set of ordinary data points (e.g., set of feature vectors). We theoretically extend the derivation of the largest generalized eigenvalue-based distance metric D_ij(γ₁) in any linear and non-linear feature spaces. We prove that D_ij(γ₁) is a metric under any linear and non-linear feature transformation function. We show the sufficiency and efficiency of using the decision rule $\bar{{\delta}}_{{\Xi}i}$(i.e., mean of D_ij(γ₁)) in classification of heterogeneous sets of biosequences compared with the decision rules min_𝚵iand median_𝚵i. We analyze the impact of linear and non-linear transformation functions on classifying/clustering collections of heterogeneous sets of biosequences. The impact of the length of a sequence in a heterogeneous sequence-set generated by simulation on the classification and clustering results in linear and non-linear feature spaces is empirically shown in this paper. We propose a new concept: the limiting dispersion map of the existing clusters in heterogeneous sets of biosequences embedded in linear and nonlinear feature spaces, which is based on the limiting distribution of nucleotide compositions estimated from real data sets. Finally, the empirical conclusions and the scientific evidences are deduced from the experiments to support the theoretical side stated in this paper.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.369-377
• /
• 2023

In the industrial manufacturing sector, quality control is pivotal for minimizing defect rates; inadequate management can result in additional costs and production delays. This study underscores the significance of detecting texture defects in manufactured goods and proposes a more precise defect detection technique. While the DFR(Deep Feature Reconstruction) model adopted an approach based on feature map amalgamation and reconstruction, it had inherent limitations. Consequently, we incorporated a new loss function using statistical methodologies, integrated a skip connection structure, and conducted parameter tuning to overcome constraints. When this enhanced model was applied to the texture category of the MVTec-AD dataset, it recorded a 2.3% higher Defect Segmentation AUC compared to previous methods, and the overall defect detection performance was improved. These findings attest to the significant contribution of the proposed method in defect detection through the reconstruction of feature map combinations.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11a
• /
• pp.127-130
• /
• 2005

There are many methods in feature extraction have been developed. Recently, principal components analysis (PCA) and independent components analysis (ICA) is introduced for doing feature extraction. PCA and ICA linearly transform the original input into new uncorrelated and independent features space respectively In this paper, the feasibility of using nonlinear feature extraction will be studied. This method will employ the PCA and ICA procedure and adopt the kernel trick to nonlinearly map the data into a feature space. The goal of this study is to seek effectively useful feature for faults classification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.3
• /
• pp.381-387
• /
• 2009

This paper is presented simultaneous localization and mapping (SLAM) based on feature map and path-planning using modified genetic algorithm for efficient driving of autonomous vehicle. The biggest problem for autonomous vehicle from now is environment adaptation. There are two cases that its new location is recognized in the new environment and is identified under unknown or new location in the map related kid-napping problem. In this paper, SLAM based on feature map using ultrasonic sensor is proposed to solved the environment adaptation problem in autonomous driving. And a modified genetic algorithm employed to optimize path-planning. We designed and built an autonomous vehicle. The proposed algorithm is applied the autonomous vehicle to show the performance. Experimental result, we verified that fast optimized path-planning and efficient SLAM is possible.