• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.661-664
• /
• 1998

Since the region segmentation at high resolution contains most of viable semantic object contours in an image, the bottom-up approach for image segmentation is appropriate for the application such as MPEG-4 which needs to preserve semantic object contours. However, the conventioal region merging methods, that follow the region segmentation, have poor performance in keeping low-contrast semantic object contours. In this paper, we propose an image segmentation algorithm based on classified region merging. The algorithm pre-segments an image with a large number of small regions, and also classifies it into several classes having similar gradient characteristics. Then regions only in the same class are merged according to the boundary weakness or statisticsal similarity. The simulation result shows that the proposed image segmentation preserves semantic object contours very well even with a small number of regions.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1260-1263
• /
• 2002

This paper takes the region segmentation in image processing and the semantic importance in an image analysis into consideration for digital image watermarking. A semantic importance for an object region, which is segmented by specific features, is determined according to the contents of the region. In this paper, face images are the targets of watermarking for their increasing importance, the use of frequency and strong necessity of protection. A face region is detected and segmented as an object region and encoded watermark information is embedded into the region. Employing a masking and filtering method, experiments are carried out and the results show the usefulness of the proposed method even when there are high compression and a synthesis as a case of copyright infringement.

• Journal of Korean Neurosurgical Society
• /
• v.47 no.1
• /
• pp.17-25
• /
• 2010

Objective: The focus of this study is brain plasticity associated with semantic aspects of language function in patients with medial temporal lobe epilepsy (mTLE) Methods: Using longitudinal functional magnetic resonance imaging (fMRI), patterns of brain activation were observed in twelve left and seven right unilateral mTLE patients during a word-generation task relative to a pseudo-word reading task before and after anterior temporal section surgery. Results: No differences were observed in precentral activations in patients relative to normal controls (n = 12), and surgery did not alter the phonological-associated activations. The two mTLE patient groups showed left inferior prefrontal activations associated with semantic processing (word-generation>pseudo-word reading), as did control subjects. The amount of semantic-associated activation in the left inferior prefrontal region was negatively correlated with epilepsy duration in both patient groups. Following temporal resection, semantic-specific activations in inferior prefrontal region became more bilateral in left mTLE patients, but more left-lateralized in right mTLE patients. The longer the duration of epilepsy in the patients, the larger the increase in the left inferior prefrontal semantic-associated activation after surgery in both patient groups. Semantic activation of the intact hippocampus, which had been negatively correlated with seizure frequency, normalized after the epileptic side was removed. Conclusion: These results indicate alternation of semantic language network related to recruitment of left inferior prefrontal cortex and functional recovery of the hippocampus contralateral to the epileptogenic side, suggesting an intra- and inter-hemispheric reorganization following surgery.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.545-558
• /
• 2007

This paper presents an efficient semantic service discovery scheme called UbiSearch for a large-scale ubiquitous computing environment. A semantic service discovery network in the semantic vector space is proposed where services that are semantically close to each other are mapped to nearby positions so that the similar services are registered in a cluster of resolvers. Using this mapping technique, the search space for a query is efficiently confined within a minimized cluster region while maintaining high accuracy in comparison to the centralized scheme. The proposed semantic service discovery network provides a number of novel features to evenly distribute service indexes to the resolvers and reduce the number of resolvers to visit. Our simulation study shows that UbiSearch provides good semantic searchability as compared to the centralized indexing system. At the same time, it supports scalable semantic queries with low communication overhead, balanced load distribution among resolvers for service registration and query processing, and personalized semantic matching.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06b
• /
• pp.29-33
• /
• 1998

In this paper, we propose a hierarchical segmentation method for tracking a semantic video object using a watershed algorithm based on morphological filtering. In the proposed method, each hierarchy consists of three steps: First, markers are extracted on the simplified current frame. Second, region growing by a modified watershed algorithm is performed for segmentation. Finally, the segmented regions are classified into 3 categories, i.e., inside, outside, and uncertain regions according to region probability values, which are acquired by the probability map calculated from a estimated motion field. Then, for the remaining uncertain regions, the above three steps are repeated at lower hierarchies with less simplified frames until every region is decided to a certain region. The proposed algorithm provides prospective results in video sequences such as Miss America, Clair, and Akiyo.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.3B
• /
• pp.529-540
• /
• 2000

This is paper presents the semantic based rate-control method which is based on very low bit rate video coding standards H.263 plus, applied on very low bit rate applications. Previous rate control methods control the generated bit rates by setting the optimum quantization parameters per macro block unit on frame. But, in this paper, we added the pre-processing algorithm, semantic region recognition and assignment of priority algorithm, to obtain the subjective quality enhancement. This work aims to improve the subjective quality of skin color region or face by using unimportant background region's bit resources.

• Journal of KIBIM
• /
• v.11 no.3
• /
• pp.22-33
• /
• 2021

In order to maximize the use of BIM, all data related to individual elements in the model must be correctly assigned, and it is essential to check whether it corresponds to the IFC entity classification. However, as the BIM modeling process is performed by a large number of participants, it is difficult to achieve complete integrity. To solve this problem, studies on semantic integrity verification are being conducted to examine whether elements are correctly classified or IFC mapped in the BIM model by applying an artificial intelligence algorithm to the 2D image of each element. Existing studies had a limitation in that they could not correctly classify some elements even though the geometrical differences in the images were clear. This was found to be due to the fact that the geometrical characteristics were not properly reflected in the learning process because the range of the region to be learned in the image was not clearly defined. In this study, the CRF-RNN-based semantic segmentation was applied to increase the clarity of element region within each image, and then applied to the MVCNN algorithm to improve the classification performance. As a result of applying semantic segmentation in the MVCNN learning process to 889 data composed of a total of 8 BIM element types, the classification accuracy was found to be 0.92, which is improved by 0.06 compared to the conventional MVCNN.

• ETRI Journal
• /
• v.29 no.5
• /
• pp.700-702
• /
• 2007

We present a relevance feedback approach based on multi-class support vector machine (SVM) learning and cluster-merging which can significantly improve the retrieval performance in region-based image retrieval. Semantically relevant images may exhibit various visual characteristics and may be scattered in several classes in the feature space due to the semantic gap between low-level features and high-level semantics in the user's mind. To find the semantic classes through relevance feedback, the proposed method reduces the burden of completely re-clustering the classes at iterations and classifies multiple classes. Experimental results show that the proposed method is more effective and efficient than the two-class SVM and multi-class relevance feedback methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3976-3990
• /
• 2022

Currently, cross-attention is widely used in Siamese trackers to replace traditional correlation operations for feature fusion between template and search region. The former can establish a similar relationship between the target and the search region better than the latter for robust visual object tracking. But existing trackers using cross-attention only focus on rich semantic information of high-level features, while ignoring the appearance information contained in low-level features, which makes trackers vulnerable to interference from similar objects. In this paper, we propose a Multi-level Cross-attention Siamese network(MCSiam) to aggregate the semantic information and appearance information at the same time. Specifically, a multi-level cross-attention module is designed to fuse the multi-layer features extracted from the backbone, which integrate different levels of the template and search region features, so that the rich appearance information and semantic information can be used to carry out the tracking task simultaneously. In addition, before cross-attention, a target-aware module is introduced to enhance the target feature and alleviate interference, which makes the multi-level cross-attention module more efficient to fuse the information of the target and the search region. We test the MCSiam on four tracking benchmarks and the result show that the proposed tracker achieves comparable performance to the state-of-the-art trackers.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1195-1214
• /
• 2018

Typical search engines may not be the most efficient means of returning images in accordance with user requirements. With the help of semantic web technology, it is possible to search through images more precisely in any required domain, because the images are annotated according to a custom-built ontology. With appropriate annotations, a search can then, return images according to the context. This paper reports on the design of a tourism ontology relevant to touristic images. In particular, the image features and the meaning of the images are described using various properties, along with other types of information relevant to tourist attractions using the OWL language. The methodology used is described, commencing with building an image and tourism corpus, creating the ontology, and developing the search engine. The system was tested through a case study involving the western region of Thailand. The user can search specifying the specific class of image or they can use text-based searches. The results are ranked using weighted scores based on kinds of properties. The precision and recall of the prototype system was measured to show its efficiency. User satisfaction was also evaluated, was also performed and was found to be high.