• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.2
• /
• pp.331-336
• /
• 2012

Red tide is a temporary natural phenomenon involving harmful algal blooms (HABs) in company with a changing sea color from normal to red or reddish brown, and which has a bad influence on coast environments and sea ecosystems. The HABs have inflicted massive mortality on fin fish and shellfish, damaging the economies of fisheries for almost every year from 1990 in South Korea. There have been many studies on red tide due to increasing damage from red tide on fishing and aquaculture industry. However, internal study of automatic red tide image classification is not enough. Especially, extraction of matching center features for recognizing algae image object is difficult because over 200 species of algae in the world have a different size and features. Previously studies used a few type of red tide algae for image classification. In this paper, we proposed the red tide image recognition method using NMF and revison of rotation angle for enhancing of recognition of red tide algae image.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.43 no.4 s.310
• /
• pp.11-20
• /
• 2006

This paper presents a method for detecting tumors on chicken carcasses by fusion of hyperspectral fluorescence and reflectance images. Classification of normal skin and tumor is performed by the image obtain 어 from optimal band ratio which minimizes the overlapping area of PDFs for normal skin and tumor. This method yields four feature images, each of them represents the ratio of two intensity values from a pixel. Classification is achieved by applying ISODATA to each pixel from the feature images. For the analysis of reflectance image, band selection method is proposed based on the information quantity, many effective features are acquired for the classification by defining the linear transformation selecting the projection axis, accordingly, accurate interpretation of images is possible in the reflectance image and automatic feature selection method is realized. Feature images from reflectance images are also classified by ISODATA and combined with the result from fluorescence images. Experimental result indicates that improved performance in term of reducing false detection rate is observed.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2262-2270
• /
• 1999

In this paper, we describe gesture recognition algorithm using computer vision sensor and HMM. The automatic hand region extraction has been proposed for initializing the tracking of the tele-operation gestures. For this, distance informations(disparity map) as results of stereo matching of initial left and right images are employed to isolate the hand region from a scene. PDOE(positive difference of edges) feature images adapted here have been found to be robust against noise and background brightness. The KNU/KAERI(K/K) gesture instruction set is defined for tele-operation in atomic electric power stations. The composite recognition model constructed by concatenating three gesture instruction models including pre-orders, basic orders, and post-orders has been proposed and identified by discrete HMM. Our experimental results showed that consecutive orders composed of more than two ones are correctly recognized at the rate of above 97%.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.79-86
• /
• 2008

As the rapid development of the Internet, the embedded images in HTML web pages nowadays become predominant. For its amazing function in describing the content and attracting attention, images become substantially important in web pages. All these images consist a considerable database. What's more, the semantic meanings of images are well presented by the surrounding text and links. But only a small minority of these images have precise assigned keyphrases. and manually assigning keyphrases to existing images is very laborious. Therefore it is highly desirable to automate the keyphrases extraction process. In this paper, we first introduce WWW image annotation methods, based on low level features, page tags, overall word frequency and local word frequency. Then we put forward our method of multi-cues integration image annotation. Also, show multi-cue image annotation method is more superior than other method through an experiment.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.1 no.3
• /
• pp.69-76
• /
• 2008

This paper concerns Fuzzy Radial Basis Function Neural Network (FRBFNN) and automatic rule generation of extraction of the FRBFNN by means of mountain clustering. In the proposed network, the membership functions of the premise part of fuzzy rules do not assume any explicit functional forms such as Gaussian, ellipsoidal, triangular, etc., so its resulting fitness values (degree of membership) directly rely on the computation of the relevant distance between data points. Also, we consider high-order polynomial as the consequent part of fuzzy rules which represent input-output characteristic of sup-space. The number of clusters and the centers of clusters are automatically generated by using mountain clustering method based on the density of data. The centers of cluster which are obtained by using mountain clustering are used to determine a degree of membership and weighted least square estimator (WLSE) is adopted to estimate the coefficients of the consequent polynomial of fuzzy rules. The effectiveness of the proposed model have been investigated and analyzed in detail for the representative nonlinear function.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1260-1274
• /
• 2016

To obtain good summarization algorithms, we need first understand how people summarize videos. 'Semantic gap' refers to the gap between semantics implied in video summarization algorithms and what people actually infer from watching videos. We hypothesized that ERP responses to real time videos will show either N400 effects to topic-irrelevant shots in the 300∼500ms time-range after stimulus on-set or P600 effects to topic-relevant shots in the 500∼700ms time range. We recruited 32 participants in the EEG experiment, asking them to focus on the topic of short videos and to memorize relevant shots to the topic of the video. After analysing real time videos based on the participants' rating information, we obtained the following t-test result, showing N400 effects on PF1, F7, F3, C3, Cz, T7, and FT7 positions on the left and central hemisphere, and P600 effects on PF1, C3, Cz, and FCz on the left and central hemisphere and C4, FC4, P8, and TP8 on the right. A further 3-way MANOVA test with repeated measures of topic-relevance, hemisphere, and electrode positions showed significant interaction effects, implying that the left hemisphere at central, frontal, and pre-frontal positions were sensitive in detecting topic-relevant shots while watching real time videos.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.3
• /
• pp.173-182
• /
• 2009

In this paper, we studied about the extraction of the parameter and implementation of speechreading system to recognize the Korean 8 vowel. Face features are detected by amplifying, reducing the image value and making a comparison between the image value which is represented for various value in various color space. The eyes position, the nose position, the inner boundary of lip, the outer boundary of upper lip and the outer line of the tooth is found to the feature and using the analysis the area of inner lip, the hight and width of inner lip, the outer line length of the tooth rate about a inner mouth area and the distance between the nose and outer boundary of upper lip are used for the parameter. 2400 data are gathered and analyzed. Based on this analysis, the neural net is constructed and the recognition experiments are performed. In the experiment, 5 normal persons were sampled. The observational error between samples was corrected using normalization method. The experiment show very encouraging result about the usefulness of the parameter.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.4
• /
• pp.103-109
• /
• 2007

Ortho images and Digital Elevation Model (DEM) have been applied in various fields. It is necessary to acquire Ground Control Points (GCPs) for processing high resolution satellite images. However surveying GCPs require many time and expense. This study was performed to investigate whether GCPs automatically extracted from ortho images and DTED Level 2 can be applied to sensor modeling for high resolution satellite images. We analyzed the performance of the sensor model established by GCPs extracted automatically. We acquired GCPs by matching satellite image against ortho images. We included the height acquired from DTED Level 2 data in these GCPs. The spatial resolution of the DTED Level 2 data is about 30m. Absolution accuracy of this data is below 18m above MSL. The spatial resolution of ortho image is 1m. We established sensor model from IKONOS images using GCPs extracted automatically and generated DEMs from the images. The accuracy of sensor modeling is about $4{\sim}5$ pixel. We also established sensor models using GCPs acquired based on GPS surveying and generated DEMs. Two DEMs were similar. The RMSE of height from the DEM by automatic GCPs and DTED Level 2 is about 9 m. So we think that GCPs by DTED Level 2 and ortho image can use for IKONOS sensor modeling.

• Korean Journal of Construction Engineering and Management
• /
• v.18 no.3
• /
• pp.63-73
• /
• 2017

In contemporary society, it is increasingly common to spend more time indoors. As such, there is a continually growing desire to build comfortable and safe indoor environments. Along with this trend, however, there are some serious indoor-environment challenges, such as the quality of indoor air and Sick House Syndrome. To address these concerns the government implements various systems to supervise and manage indoor environments. For example, green building certification is now compulsory for public buildings. There are three categories of green building certification related to indoor air in Korea: Health-Friendly Housing Construction Standards, Green Standard for Energy & Environmental Design(G-SEED), and Indoor Air Certification. The first two types of certification, Health-Friendly Housing Construction Standards and G-SEED, evaluate data in a drawing plan. In comparison, the Indoor Air Certification evaluates measured data. The certification using data from a drawing requires a considerable amount of time compared to other work. A 2D tool needs to be employed to measure the area manually. Thus, this study proposes an automatic assessment process using a Building Information Modeling(BIM) model based on 3D data. This process, using open source Industry Foundation Classes(IFC), exports data for the certification system, and extracts the data to create an Excel sheet for the certification. This is expected to improve the work process and reduce the workload associated with evaluating indoor air conditions.