• Journal of applied mathematics & informatics
• /
• v.9 no.2
• /
• pp.793-806
• /
• 2002

Feature-based similarity retrieval become an important research issue in image database systems. The features of image data are useful to discrimination of images. In this paper, we propose the highspeed k-Nearest Neighbor search algorithm based on Self-Organizing Maps. Self-Organizing Maps (SOM) provides a mapping from high dimensional feature vectors onto a two-dimensional space. The mapping preserves the topology of the feature vectors. The map is called topological feature map. A topological feature map preserves the mutual relations (similarity) in feature spaces of input data. and clusters mutually similar feature vectors in a neighboring nodes. Each node of the topological feature map holds a node vector and similar images that is closest to each node vector. In topological feature map, there are empty nodes in which no image is classified. We experiment on the performance of our algorithm using color feature vectors extracted from images. Promising results have been obtained in experiments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.185-187
• /
• 2018

This paper presents an aircraft detection on panchromatic image using densely connected convolutional network. This algorithm connects all preceding feature-maps to all subsequent layers. It is encouraged to reuse feature-maps and enhance feature-maps representation. This algorithm is driven to learn aircraft feature to detect aircraft objects on panchromatic imagery. Based on the experimental result, it can yield accuracy of 92%.

• Journal of Korea Multimedia Society
• /
• v.23 no.2
• /
• pp.127-134
• /
• 2020

In this paper, we propose a map alignment method for maps generated by point-line monocular SLAM. In the proposed method, the information of feature lines as well as feature points extracted from multiple maps are fused into a single map. To this end, the proposed method first searches for similar areas between maps via Bag-of-Words-based image matching. Thereafter, it calculates the similarity transformation between the maps in the corresponding areas to align the maps. Finally, we merge the overlapped information of multiple maps into a single map by removing duplicate information from similar areas. Experimental results show that maps created by different users are combined into a single map, and the accuracy of the fused map is similar with the one generated by a single user. We expect that the proposed method can be utilized for fast imagery map generation.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.31-39
• /
• 2023

In this paper, we propose an Internal/External Knowledge Distillation (IEKD), which utilizes both external correlations between feature maps of heterogeneous models and internal correlations between feature maps of the same model for transferring knowledge from a teacher model to a student model. To achieve this, we transform feature maps into a sequence format and extract new feature maps suitable for knowledge distillation by considering internal and external correlations through a transformer. We can learn both internal and external correlations by distilling the extracted feature maps and improve the accuracy of the student model by utilizing the extracted feature maps with feature matching. To demonstrate the effectiveness of our proposed knowledge distillation method, we achieved 76.23% Top-1 image classification accuracy on the CIFAR-100 dataset with the "ResNet-32×4/VGG-8" teacher and student combination and outperformed the state-of-the-art KD methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.12-21
• /
• 2006

In this paper, we propose a technique for extracting attentive objects in images using feature maps, regardless of the complexity of images and the position of objects. The proposed method uses feature maps with edge and color information in order to extract attentive objects. We also propose a reference map which is created by integrating feature maps. In order to create a reference map, feature maps which represent visually attentive regions in images are constructed. Three feature maps including edge map, CbCr map and H map are utilized. These maps contain the information about boundary regions by the difference of intensity or colors. Then the combination map which represents the meaningful boundary is created by integrating the reference map and feature maps. Since the combination map simply represents the boundary of objects we extract the candidate object regions including meaningful boundaries from the combination map. In order to extract candidate object regions, we use the convex hull algorithm. By applying a segmentation algorithm to the area of candidate regions to separate object regions and background regions, real object regions are extracted from the candidate object regions. Experiment results show that the proposed method extracts the attentive regions and attentive objects efficiently, with 84.3% Precision rate and 81.3% recall rate.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.2
• /
• pp.131-139
• /
• 2008

This paper presents a new saliency map which is constructed by providing dynamic weights on individual features in an input image to search ROI(Region Of Interest) or FOA(Focus Of Attention). To construct a saliency map on there is no a priori information, three feature-maps are constructed first which emphasize orientation, color, and intensity of individual pixels, respectively. From feature-maps, conspicuity maps are generated by using the It's algorithm and their information quantities are measured in terms of entropy. Final saliency map is constructed by summing the conspicuity maps weighted with their individual entropies. The prominency of the proposed algorithm has been proved by showing that the ROIs detected by the proposed algorithm in ten different images are similar with those selected by one-hundred person's naked eyes.

• Journal of Biomedical Engineering Research
• /
• v.28 no.1
• /
• pp.8-16
• /
• 2007

Finite element analysis (FEA) is an effective means for the analysis of bioelectromagnetism. It has been successfully applied to various problems over conventional methods such as boundary element analysis and finite difference analysis. However, its utilization has been limited due to the overwhelming computational load despite of its analytical power. We have previously developed a novel mesh generation scheme that produces FE meshes that are content-adaptive to given MR images. MRI content-adaptive FE meshes (cMeshes) represent the electrically conducting domain more effectively with far less number of nodes and elements, thus lessen the computational load. In general, the cMesh generation is affected by the quality of feature maps derived from MRI. In this study, we have tested various feature maps created based on the improved differential geometry measures for more effective cMesh head models. As performance indices, correlation coefficient (CC), root mean squared error (RMSE), relative error (RE), and the quality of cMesh triangle elements are used. The results show that there is a significant variation according to the characteristics of specific feature maps on cMesh generation, and offer additional choices of feature maps to yield more effective and efficient generation of cMeshes. We believe that cMeshes with specific and improved feature map generation schemes should be useful in the FEA of bioelectromagnetic problems.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.1
• /
• pp.131-146
• /
• 2021

Multimodal biometric-based recognition has been an active topic because of its higher convenience in recent years. Due to high user convenience of finger, finger-based personal identification has been widely used in practice. Hence, taking Finger-Print (FP), Finger-Vein (FV) and Finger-Knuckle-Print (FKP) as the ingredients of characteristic, their feature representation were helpful for improving the universality and reliability in identification. To usefully fuse the multimodal finger-features together, a new robust representation algorithm was proposed based on hierarchical model. Firstly, to obtain more robust features, the feature maps were obtained by Gabor magnitude feature coding and then described by Local Binary Pattern (LBP). Secondly, the LGBP-based feature maps were processed hierarchically in bottom-up mode by variable rectangle and circle granules, respectively. Finally, the intension of each granule was represented by Local-invariant Gray Features (LGFs) and called Hierarchical Local-Gabor-based Gray Invariant Features (HLGGIFs). Experiment results revealed that the proposed algorithm is capable of improving rotation variation of finger-pose, and achieving lower Equal Error Rate (EER) in our homemade database.

• Spatial Information Research
• /
• v.10 no.3
• /
• pp.455-468
• /
• 2002

Toward the systematic and efficient management of national land, National Geography Institute(NGI, National mapping agency) has been producing national basemap in automated process since middle of 1980's. Under the National Geographic Information System(NGIS) Development Plan, NGI began to produce digital maps in the scales of 1:1,000, 1:5,000, 1:25,000 since 1995. However, those of digital maps that have been generated under NGIS Development Plan need to be modified and corrected due to lack of technology and experience in making digital maps. In this context, those digital maps generated are currently in great need for improving the data dictionary. It is fully appreciated in previous research that data dictionary will be a key element far users and generators of digital maps to rectify the existing problems in digital maps as well as to maximize the application of digital maps. In this paper, we analyzed existing problems in digital maps based on previous researches and interviews with engineers in different fields of geospatial engineering. And then, the existing data dictionary has been redefined and modified. In the line of modification process, a relational matrix was established fur each topographic feature defined in the existing feature classification system. This paper presents newly proposed data dictionary which conforms to newly defined feature classification system from previous research performed by NGI.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.31 no.3
• /
• pp.41-51
• /
• 2006

Clustering is to group similar objects into clusters. Until now there are a lot of approaches using Self-Organizing feature Maps (SOFMS) But they have problems with a small output-layer nodes and initial weight. For example, one of them is a one-dimension map of c output-layer nodes, if they want to make c clusters. This approach has problems to classify elaboratively. This Paper suggests one-dimensional output-layer nodes in SOFMs. The number of output-layer nodes is more than those of clusters intended to find and the order of output-layer nodes is ascending in the sum of the output-layer node's weight. We un find input data in SOFMs output node and classify input data in output nodes using Euclidean distance. The proposed algorithm was tested on well-known IRIS data and TSPLIB. The results of this computational study demonstrate the superiority of the proposed algorithm.