• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2390-2406
• /
• 2022

Scene text recognition has important application value and attracted the interest of plenty of researchers. At present, many methods have achieved good results, but most of the existing approaches attempt to improve the performance of scene text recognition from the image level. They have a good effect on reading regular scene texts. However, there are still many obstacles to recognizing text on low-quality images such as curved, occlusion, and blur. This exacerbates the difficulty of feature extraction because the image quality is uneven. In addition, the results of model testing are highly dependent on training data, so there is still room for improvement in scene text recognition methods. In this work, we present a natural scene text recognizer to improve the recognition performance from the feature level, which contains feature representation and feature enhancement. In terms of feature representation, we propose an efficient feature extractor combined with Representative Batch Normalization and ResNet. It reduces the dependence of the model on training data and improves the feature representation ability of different instances. In terms of feature enhancement, we use a feature enhancement network to expand the receptive field of feature maps, so that feature maps contain rich feature information. Enhanced feature representation capability helps to improve the recognition performance of the model. We conducted experiments on 7 benchmarks, which shows that this method is highly competitive in recognizing both regular and irregular texts. The method achieved top1 recognition accuracy on four benchmarks of IC03, IC13, IC15, and SVTP.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.14-25
• /
• 2021

Change detection, which finds changes in remote sensing images of the same location captured at different times, is very important because it is used in various applications. However, registration errors, building displacement errors, and shadow errors cause false positives. To solve these problems, we propose a novle deep convolutional network called CADNet (Change Attention Dense Siamese Network). CADNet uses FPN (Feature Pyramid Network) to detect multi-scale changes, applies a Change Attention Module that attends to the changes, and uses DenseNet as a feature extractor to use feature maps that contain both low-level and high-level features for change detection. CADNet performance measured from the Precision, Recall, F1 side is 98.44%, 98.47%, 98.46% for WHU datasets and 90.72%, 91.89%, 91.30% for LEVIR-CD datasets. The results of this experiment show that CADNet can offer better performance than any other traditional change detection method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2101-2123
• /
• 2023

Recent studies have shown that the neural network-based binary code similarity detection technology performs well in vulnerability mining, plagiarism detection, and malicious code analysis. However, existing cross-architecture methods still suffer from insufficient feature characterization and low discrimination accuracy. To address these issues, this paper proposes a cross-architecture binary function similarity detection method based on composite feature model (SDCFM). Firstly, the binary function is converted into vector representation according to the proposed composite feature model, which is composed of instruction statistical features, control flow graph structural features, and application program interface calling behavioral features. Then, the composite features are embedded by the proposed hierarchical embedding network based on a graph neural network. In which, the block-level features and the function-level features are processed separately and finally fused into the embedding. In addition, to make the trained model more accurate and stable, our method utilizes the embeddings of predecessor nodes to modify the node embedding in the iterative updating process of the graph neural network. To assess the effectiveness of composite feature model, we contrast SDCFM with the state of art method on benchmark datasets. The experimental results show that SDCFM has good performance both on the area under the curve in the binary function similarity detection task and the vulnerable candidate function ranking in vulnerability search task.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.5
• /
• pp.48-55
• /
• 2009

Prior research works in indoor-outdoor classification have been conducted based on a simple combination of low-level features. However, since there are many challenging problems due to the extreme variability of the scene contents, most methods proposed recently tend to combine the low-level features with high-level information such as the presence of trees and sky. To extract these regions from videos, we need to conduct additional tasks, which may yield the increasing number of feature dimensions or computational burden. Therefore, an efficient indoor-outdoor scene classification method is proposed in this paper. First, the video is divided into the five same-sized blocks. Then we define and use the edge and color orientation histogram (ECOH) descriptors to represent each sub-block efficiently. Finally, all ECOH values are simply concatenated to generated the feature vector. To justify the efficiency and robustness of the proposed method, a diverse database of over 1200 videos is evaluated. Moreover, we improve the classification performance by using different weight values determined through the learning process.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.05a
• /
• pp.585-589
• /
• 2002

In this paper, hierarchical retrieval system based on efficient feature extraction is proposed. In order to retrieval the image with robustness for geometrical transformation such as translation, scaling, and rotation. After performing the 2-level wavelet transform on image, We extract moment in low-level subband which was subdivided into subimages and texture feature, contrast of GLCM(Gray Level Co-occurrence Matrix). At first we retrieve the candidate images in database by the ones of image. To perform a more accurate image retrieval, the edge information on the high-level subband was subdivided horizontally, vertically and diagonally. And then, the energy rate of edge per direction was determined and used to compare the energy rate of edge between images for higher accuracy.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.4
• /
• pp.85-93
• /
• 2008

This paper proposes a method for generating low-level geometric models with retaining salient features during decimation. Our method employs feature extraction technique for extracting feature lines defined via curvature derivatives on the model (we divide features into ridges and valleys). We add the extraction method to simplification technique (Feature Quadric Error Metric) for making coarse model with features. This paper clearly shows that experimental results have better quality and smaller geometric error than previous methods.

• Journal of Information Processing Systems
• /
• v.14 no.1
• /
• pp.176-190
• /
• 2018

This paper presents a novel convolutional neural network based multi-feature fusion learning method for non-rigid 3D model retrieval, which can investigate the useful discriminative information of the heat kernel signature (HKS) descriptor and the wave kernel signature (WKS) descriptor. At first, we compute the 2D shape distributions of the two kinds of descriptors to represent the 3D model and use them as the input to the networks. Then we construct two convolutional neural networks for the HKS distribution and the WKS distribution separately, and use the multi-feature fusion layer to connect them. The fusion layer not only can exploit more discriminative characteristics of the two descriptors, but also can complement the correlated information between the two kinds of descriptors. Furthermore, to further improve the performance of the description ability, the cross-connected layer is built to combine the low-level features with high-level features. Extensive experiments have validated the effectiveness of the designed multi-feature fusion learning method.

• 한국연소학회:학술대회논문집
• /
• 2001.11a
• /
• pp.42-50
• /
• 2001

An experimental study has been carried on high-preheated temperature air combustion. Because the flames with high-preheated temperature air combustion were much more stable and homogeneous(both temporally and spatially) as compared to the room-temperature combustion air. The global flame feature showed range of flame colors (yellow, blue, blurish-green) over the range of conditions. Low level of NOx along with low level of CO have been obtained under high-preheated air combustion conditions. The thermal and chemical behavior of high-preheated air combustion flames depends on preheated temperature and oxygen concentration air.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.794-802
• /
• 2022

The recovery of reasonable depth information from different scenes is a popular topic in the field of computer vision. For generating depth maps with better details, we present an efficacious monocular depth prediction framework with coordinate attention and feature fusion. Specifically, the proposed framework contains attention, multi-scale and feature fusion modules. The attention module improves features based on coordinate attention to enhance the predicted effect, whereas the multi-scale module integrates useful low- and high-level contextual features with higher resolution. Moreover, we developed a feature fusion module to combine the heterogeneous features to generate high-quality depth outputs. We also designed a hybrid loss function that measures prediction errors from the perspective of depth and scale-invariant gradients, which contribute to preserving rich details. We conducted the experiments on public RGBD datasets, and the evaluation results show that the proposed scheme can considerably enhance the accuracy of depth prediction, achieving 0.051 for log10 and 0.992 for δ<1.25³ on the NYUv2 dataset.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1039-1043
• /
• 2005

Despite the many significant advances made in robot architecture, the basic approaches are deliberative and reactive methods. They are quite different in recognizing outer environment and inner operating mechanism. For this reason, they have almost opposite characteristics. Later, researchers integrate these two approaches into hybrid architecture. In such architecture, Reactive module also called low-level motion control module have advantage in real-time reacting and sensing outer environment; Deliberative module also called high-level task planning module is good at planning task using world knowledge, reasoning and intelligent computing. This paper presents a framework of the integrated planning and control for mobile robot navigation. Unlike the existing hybrid architecture, it learns topological map from the world map by using MST (Minimum Spanning Tree)-based SOFM (Self-Organizing Feature Map) algorithm. High-level planning module plans simple tasks to low-level control module and low-level control module feedbacks the environment information to high-level planning module. This method allows for a tight integration between high-level and low-level modules, which provide real-time performance and strong adaptability and reactivity to outer environment and its unforeseen changes. This proposed framework is verified by simulation.