• Journal of Korea Multimedia Society
• /
• v.18 no.7
• /
• pp.834-842
• /
• 2015

We propose a method to construct composite feature vector based on discriminant analysis for face recognition. For this, we first extract the holistic- and local-features from whole face images and local images, which consist of the discriminant pixels, by using a discriminant feature extraction method. In order to utilize both advantages of holistic- and local-features, we evaluate the amount of the discriminative information in each feature and then construct a composite feature vector with only the features that contain a large amount of discriminative information. The experimental results for the FERET, CMU-PIE and Yale B databases show that the proposed composite feature vector has improvement of face recognition performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2407-2424
• /
• 2022

Recently, Transformer has made great progress in video retrieval tasks due to its high representation capability. For the structure of a Transformer, the cascaded self-attention modules are capable of capturing long-distance feature dependencies. However, the local feature details are likely to have deteriorated. In addition, increasing the depth of the structure is likely to produce learning bias in the learned features. In this paper, an improved Transformer structure named TransDCS (Transformer with Dynamic Convolution and Shortcut) is proposed. A Multi-head Conv-Self-Attention module is introduced to model the local dependencies and improve the efficiency of local features extraction. Meanwhile, the augmented shortcuts module based on a dual identity matrix is applied to enhance the conduction of input features, and mitigate the learning bias. The proposed model is tested on MSRVTT, LSMDC and Activity-Net benchmarks, and it surpasses all previous solutions for the video-text retrieval task. For example, on the LSMDC benchmark, a gain of about 2.3% MdR and 6.1% MnR is obtained over recently proposed multimodal-based methods.

• Ocean Systems Engineering
• /
• v.2 no.2
• /
• pp.137-145
• /
• 2012

Recent developments in underwater image recognition methods have received large attention by the ocean engineering researchers. In this paper, an improved bi-dimensional empirical mode decomposition (BEMD) approach is employed to decompose the given underwater image into intrinsic mode functions (IMFs) and residual. We developed a joint algorithm based on BEMD and Canny operator to extract multi-pixel edge features at multiple scales in IMFs sub-images. So the multiple pixel edge extraction is an advantage of our approach; the other contribution of this method is the realization of the bi-dimensional sifting process, which is realized utilizing regional-based operators to detect local extreme points and constructing radial basis function for curve surface interpolation. The performance of the multi-pixel edge extraction algorithm for processing underwater image is demonstrated in the contrast experiment with both the proposed method and the phase congruency edge detection.

• Journal of Broadcast Engineering
• /
• v.7 no.3
• /
• pp.262-270
• /
• 2002

Although most image indexing schemes ate based on global image features, they have limited discrimination capability because they cannot capture local variations of the image. In this paper, we propose a new region-based image retrieval system that can extract important regions in the image using salient point extraction and image segmentation techniques. Our experimental results show that color and texture information in the region provide a significantly improved retrieval performances compared to the global feature extraction methods.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.3
• /
• pp.108-111
• /
• 2002

This paper proposes an new water mark embedding and extraction technique which extends the direct sequence spread spectrum technique. The proposed technique approximates the complexity of image and block in spatial domain using Laplacian filtering and watermark is adaptively embedded in the mid-frequency DCT components. Local parity bits are attached to higher-frequency DCT components and they are used to detect extraction errors and correct those errors. In extraction process the proposed method boosts the higher frequency components of image and extracts the watermark by demodulation and this information is verified and adjusted by parity bits. Experimental results show it is invisible and robust to several external attacks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.468-472
• /
• 2004

This paper presents an intelligent iris recognition system which consists of quality check, iris localization, feature extraction, and verification. For the quality check, the local statistics on the pupil boundary is used. Gaussian mixture model is used to segment and localized the iris region. The feature extraction method is based on an optimal waveform simplification. For the verification, we use an intelligent variable threshold.

• The Journal of Information Technology
• /
• v.12 no.4
• /
• pp.25-32
• /
• 2009

Iris recognition is a biometric technology which can identify a person using the iris pattern. It is important for the iris recognition system to extract the feature which is invariant to changes in iris patterns. Those changes can be occurred by the influence of lights, changes in the size of the pupil, and head tilting. This paper is appropriate for the embedded environment using local gradient histogram embedded system using iris feature extraction methods have implement. The proposed method enables high-speed feature extraction and feature comparison because it requires no additional processing to obtain the rotation invariance, and shows comparable performance to the well-known previous methods.

• ETRI Journal
• /
• v.37 no.5
• /
• pp.1023-1031
• /
• 2015

In infrared (IR) images, near targets have a transient distribution at the boundary region, as opposed to a steady one at the inner region. Based on this fact, this paper proposes a novel IR target extraction method that uses both a weighted information entropy (WIE) and an adaptive opening filter to extract near finely shaped targets in IR images. Firstly, the boundary region of a target is detected using a local variance WIE of an original image. Next, a coarse target region is estimated via a labeling process used on the boundary region of the target. From the estimated coarse target region, a fine target shape is extracted by means of an opening filter having an adaptive structure element. The size of the structure element is decided in accordance with the width information of the target boundary and mean WIE values of windows of varying size. Our experimental results show that the proposed method obtains a better extraction performance than existing algorithms.

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.767-775
• /
• 2022

Metal additive manufacturing (AM), also known as metal three-dimensional (3D) printing, produces 3D metal products by repeatedly adding and solidifying metal materials layer by layer. During the metal AM process, products experience repeated local melting and cooling using a laser or electron beam, resulting in product defects, such as warpage, cracks, and internal pores. Such defects adversely affect the final product. This paper proposes the in situ monitoring-based warpage prediction of metal AM products with experimental feature extraction. The temperature profile of the metal AM substrate during the process was experimentally collected. Time-domain features were extracted from the temperature profile, and their relationships to the warpage mechanism were investigated. The standard deviation showed a significant linear correlation with warpage. The findings from this study are expected to contribute to optimizing process parameters for metal AM warpage reduction.

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.55-63
• /
• 2017

One of the purposes of Information Technology (IT) is to support human response to natural and social problems such as natural disasters and spread of disease, and to improve the quality of human life. Recent climate change has happened worldwide, natural disasters threaten the quality of life, and human safety is no longer guaranteed. IT must be able to support tasks related to disaster response, and more importantly, it should be used to predict and minimize future damage. In South Korea, the data related to the damage is checked out by each local government and then federal government aggregates it. This data is included in disaster reports that the federal government discloses by disaster case, but it is difficult to obtain raw data of the damage even for research purposes. In order to obtain data, information extraction may be applied to disaster reports. In the field of information extraction, most of the extraction targets are web documents, commercial reports, SNS text, and so on. There is little research on information extraction for government disaster reports. They are mostly text, but the structure of each sentence is very different from that of news articles and commercial reports. The features of the government disaster report should be carefully considered. In this paper, information extraction method for South Korea government reports in the word format is presented. This method is based on patterns and dictionaries and provides some additional ideas for tokenizing the damage representation of the text. The experiment result is F1 score of 80.2 on the test set. This is close to cutting-edge information extraction performance before applying the recent deep learning algorithms.