• Journal of Korean Academy of Oral and Maxillofacial Radiology
• /
• v.28 no.1
• /
• pp.299-309
• /
• 1998

This case was diagnosed as multiple cementoosseous dysplasia on the basis of clinical & radiological features but was diagnosed as ossifying fibroma on the basis of histopathological feature. The histopathologic features of the multiple cementoosseous dysplasia and cementoossifying fibroma have common features of cementum, fibrous network and bone. Multiple cementoosseous dysplasia is reactive lesion and shows restricted lesion size, occurred on anterior and posterior tooth of the mandible and needs no treatement except periodic follow up. But Cementoossifying fibroma is the true neoplasm and grows continuously and needs surgical removal. The final diagnosis of the multiple cementoosseous dysplasia requires good correlation of the clinical, histopathological, and radiological features.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.272-287
• /
• 2016

Recently, various and effective contrast based salient object detection models to focus on a single target have been proposed. However, there is a lack of research on detection of multiple objects, and also it is a more challenging task than single target process. In the multiple target problem, we are confronted by new difficulties caused by distinct difference between properties of objects. The characteristic of existing models depending on the global maximum distribution of data point would become a drawback for detection of multiple objects. In this paper, by analyzing limitations of the existing methods, we have devised three main processes to detect multiple salient objects. In the first stage, regional features are extracted from over-segmented regions. In the second stage, the regional features are categorized into homogeneous cluster using the mean-shift algorithm with the kernel function having various sizes. In the final stage, we compute saliency scores of the categorized regions using only spatial features without the contrast features, and then all scores are integrated for the final salient regions. In the experimental results, the scheme achieved superior detection accuracy for the SED2 and MSRA-ASD benchmarks with both a higher precision and better recall than state-of-the-art approaches. Especially, given multiple objects having different properties, our model significantly outperforms all existing models.

• The Journal of the Korean dental association
• /
• v.56 no.12
• /
• pp.707-713
• /
• 2018

Multiple myeloma is a lymphohematopoietic disorder leading to abnormal hemostasis and significant pathologic changes of skeletal system. It induces multiple circular or oval-shaped radiolucent lesions which are characterized by 'punched-out appearance'. The surrounding trabecular bone normally shows no significant sclerotic reaction. Multiple myeloma patients may visit dental clinics, without perception of the disease themselves, due to discomfort from edema of orofacial region, oral ulcers, tooth mobility, pain or gingival bleeding. Multiple myeloma is susceptible to various complications, including delayed hemostasis and infection, which could occur during routine dental treatment such as periodontal and surgical operation. For radiographic diagnosis of multiple myeloma, common radiologic features of this tumor could be visualized by panoramic radiographs in the dental clinics, and further medical examinations and treatment can be recommended as a result.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.12C
• /
• pp.1231-1238
• /
• 2005

This paper presents a new fast encoding algorithm for image vector quantization that incorporates the partial distances of multiple features with a multidimensional look-up table (LUT). Although the methods which were proposed earlier use the multiple features, they handles the multiple features step by step in terms of searching order and calculating process. On the other hand, the proposed algorithm utilizes these features simultaneously with the LUT. This paper completely describes how to build the LUT with considering the boundary effect for feasible memory cost and how to terminate the current search by utilizing partial distances of the LUT Simulation results confirm the effectiveness of the proposed algorithm. When the codebook size is 256, the computational complexity of the proposed algorithm can be reduced by up to the $70\%$ of the operations required by the recently proposed alternatives such as the ordered Hadamard transform partial distance search (OHTPDS), the modified $L_2-norm$ pyramid ($M-L_2NP$), etc. With feasible preprocessing time and memory cost, the proposed algorithm reduces the computational complexity to below the $2.2\%$ of those required for the exhaustive full search (EFS) algorithm while preserving the same encoding quality as that of the EFS algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5C
• /
• pp.514-522
• /
• 2003

Contrary to the previous methods, in this paper, we propose an enhanced shot change detection method using multiple features and binary decision tree. The previous methods usually used single feature and fixed threshold between consecutive frames. However, contents such as color, shape, background, and texture change simultaneously at shot change points in a video sequence. Therefore, in this paper, we detect the shot changes effectively using multiple features, which are supplementary each other, rather than using single feature. In order to classify the shot changes, we use binary classification tree. According to this classification result, we extract important features among the multiple features and obtain threshold value for each feature. We also perform the cross-validation and droop-case to verify the performance of our method. From an experimental result, it was revealed that the EI of our method performed average of 2% better than that of the conventional shot change detection methods.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.6
• /
• pp.700-711
• /
• 2019

Objective : The treatment of multiple thoracolumbar spine fractures according to fracture continuity has rarely been reported. Herein we evaluate the clinical features and outcomes of multiple thoracolumbar fractures depending on continuous or noncontinuous status. Methods : From January 2010 to January 2016, 48 patients with acute thoracic and lumbar multiple fractures who underwent posterior fusion surgery were evaluated. Patients were divided into two groups (group A : continuous; group B : noncontinuous). We investigated the causes of the injuries, the locations of the injuries, the range of fusion levels, and the functional outcomes based on the patients' general characteristics. Results : A total of 48 patients were enrolled (group A : 25 patients; group B : 23 patients). Both groups had similar pre-surgical clinical and radiologic features. The fusion level included three segments (group A : 4; group B : 5) or four segments (group A : 19; group B : 5). Group B required more instrumented segments than did group A. Group A scored 23.5 and group B scored 33.4 on the Korean Oswestry Disability Index (KODI) at the time of last follow-up. In both groups, longer fusion was associated with worse KODI score. Conclusion : In this study, due to the assumption of similar initial clinical and radiologic features in both group, the mechanism of multiple fractures is presumed to be the same between continuous and noncontinuous fractures. The noncontinuous fracture group had worse KODI scores in long-term follow-up, thought to be due to long fusion level. Therefore, we recommend minimizing the number of segments that are fused in multiple thoracolumbar and lumbar fractures when decompression is not necessary.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.651-662
• /
• 2010

This paper describes a method to identify objects for autonomous navigation of an outdoor mobile robot. To identify objects, the robot recognizes the object from an image taken by moving robot on outdoor environment. As a beginning, this paper presents the candidates for a segment of region to building of artificial object, sky and trees of natural objects. Then we define their characteristics individually. In the process, we segment the regions of the objects included by preprocessing using multiple features. Multiple features are HSI, line segments, context information, hue co-occurrence matrix, principal components and vanishing point. An analysis of building identifies the geometrical properties of building facet such as wall region, windows and entrance. The building as intersection in vertical and horizontal line segment of vanishing point extracts the mesh. The wall region of building detect by merging the mesh of the neighbor parallelograms that have similar colors. The property estimates the number of story and rooms in the same floors by merging skewed parallelograms of the same color. We accomplish the result of image segmentation using multiple features and the geometrical properties analysis of object through experiments.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.3
• /
• pp.84-95
• /
• 2005

This paper presents solution heuristics to solving optimal multiple-viewpoint location problems that are based on topographic features. The visibility problem is to maximise the viewshed area for a set of viewpoints on digital elevation models (DEM). For this analysis, five areas are selected, and fundamental topographic features (peak, pass, and pit) are extracted from the DEMs of the study areas. To solve the visibility problem, at first, solution approaches based on the characteristics of the topographic features are explored, and then, a benchmark test is undertaken that solution performances of the solution methods, such as computing times, and visible area sizes, are compared with the performances of traditional spatial heuristics. The feasibility of the solution methods, then, are discussed with the benchmark test results. From the analysis, this paper can conclude that fundamental topographic features based solution methods suggest a new sight of visibility analysis approach which did not discuss in traditional algorithmic approaches. Finally, further research avenues are suggested such as exploring more sophisticated selection process of topographic features related to visibility analysis, exploiting systematic methods to extract topographic features, and robust spatial analytical techniques and optimization techniques that enable to use the topographic features effectively.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.83-88
• /
• 2010

This study is going to suggest the technology to recognize a starfish by judging various starfish images. In case of recognition of single objects of the asterias amurensis, a starfish can be judged by using concave features and short line features but in case of multiple objects, it is impossible to extract the features of a starfish using concave features or short line so that it can't be recognized as a starfish. Accordingly, it is going to suggest the recognition technology using the features such as numbers of standard deviation, relative degree standard deviation and valid deviation of a long line by using the region central moment and a long line of multiple objects. As a result of experiments of the suggested technology, there were cases that recognition failed because the conditions of the standard deviation of a long line or the numbers of valid deviation of the relative degree couldn't satisfy the conditions but around 95% of a high recognition rate was shown.