• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.106-109
• /
• 2009

Recently, image matching becomes important in Computer Aided Diagnosis (CAD) due to the huge amount of medical images. Specially, texture feature is useful in medical image matching. However, texture features such as co-occurrence matrices can't describe well the spatial distribution of gray levels of the neighborhood pixels. In this paper we propose a frequency domain-based texture feature extractor that describes the local spatial distribution for medical image retrieval. This method is based on 2D Local Discrete Fourier transform of local images. The features are extracted from local Fourier histograms that generated by four Fourier images. Experimental results using 40 classes Brodatz textures and 1 class of Emphysema CT images show that the average accuracy of retrieval is about 93%.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.303-310
• /
• 2007

Named Entity Recognition (NER) is always limited by its lower recall resulting from the asymmetric data distribution where the NONE class dominates the entity classes. This paper presents an approach that exploits non-local information to improve the NER recall. Several kinds of non-local features encoding entity token occurrence, entity boundary and entity class are explored under Conditional Random Fields (CRFs) framework. Experiments on SIGHAN 2006 MSRA (CityU) corpus indicate that non-local features can effectively enhance the recall of the state-of-the-art NER systems. Incorporating the non-local features into the NER systems using local features alone, our best system achieves a 23.56% (25.26%) relative error reduction on the recall and 17.10% (11.36%) relative error reduction on the F1 score; the improved F1 score 89.38% (90.09%) is significantly superior to the best NER system with F1 of 86.51% (89.03%) participated in the closed track.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4060-4079
• /
• 2020

Blur is an important type of image distortion. How to evaluate the quality of blurred image accurately and efficiently is a research hotspot in the field of image processing in recent years. Inspired by the multi-scale perceptual characteristics of the human visual system (HVS), this paper presents a no-reference image blur/sharpness assessment method based on multi-scale local features in the spatial domain. First, considering various content has different sensitivity to blur distortion, the image is divided into smooth, edge, and texture regions in blocks. Then, the Gaussian scale space of the image is constructed, and the categorized contrast features between the original image and the Gaussian scale space images are calculated to express the blur degree of different image contents. To simulate the impact of viewing distance on blur distortion, the distribution characteristics of local maximum gradient of multi-resolution images were also calculated in the spatial domain. Finally, the image blur assessment model is obtained by fusing all features and learning the mapping from features to quality scores by support vector regression (SVR). Performance of the proposed method is evaluated on four synthetically blurred databases and one real blurred database. The experimental results demonstrate that our method can produce quality scores more consistent with subjective evaluations than other methods, especially for real burred images.

• Journal of Environmental Science International
• /
• v.21 no.3
• /
• pp.297-303
• /
• 2012

Slope is the geographic factor reflecting the 3-dimensional features of basin and it can be considered as the important geomorphological factor which governs the morphology of basin and the dynamics of water movement. In this study the approach to the 3-dimensional structures of basin is attempted with statistical analysis of local slope which can be defined and measured in easy and objective manner by means of DEM. As a result local slope is confirmed to be a highly variable spatial factor in basin. And distribution map of local slope based on spatial autocorrelation length in this study would be a useful tool in the further research of hydrology and geomorphology.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.721-724
• /
• 2000

This paper presents fingerprint authentication method based on minutiae quadrangle definded by neighboring two Delaunay triangles. In this method, we first make minutiae triangle through Delaunay triangulation which adaptively connect neighboring minutiae according to the local minutiae density distribution, and then use feature vectors in authentication which is extracted from the minutiae quadrangle formed by neighboring two minutiae triangles. This prevents the degradation of matching ratio caused by the errors in image processing or local deformation of the fingerprint, and we can authenticate more discriminately as this method reflects wider local area's topological features than the features extracted from the individual minutiae triangles. To evaluate the proposed algorithm's performance, experiment are conducted on 120 fingerprints, of which size is 256 ${\times}$ 364 with 500dpi resolution. Robust authentications are possible with low FRR.

• Journal of Species Research
• /
• v.3 no.1
• /
• pp.17-26
• /
• 2014

The number of features related to morphology, distribution of habitats, biotopical distribution, and biology of species reproduction (within the territory described) of the Mongolian toad (Bufo raddei) which inhabits western shore of Lake Baikal were described. In this paper on the basis of the results of field studies in 1997, 2001, 2005, 2012 the original data on reproduction and chemical composition of the spawning ponds, used by frogs for reproduction, is presented. It was found that reproduction of species occurs in the salty steppe (14-45 g/L) lakes in the west part of the Baikal basin.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.28B no.11
• /
• pp.904-912
• /
• 1991

Automatic recognition of seal imprint has been required in the oriental countries. In this paper, a hierarchical approach for seal imprint verification is presented. Global features are used for seal imprint description in the first step. In the second step, conventional and several proposed local features are used to detect useful informations such as size, distribution and relative position of stroke length from seal imprint. In the last step, seal imprints are classified into one of three categories 'accept', 'ambiguous' and reject', based on the hierarchical classification. Experimental results show good performance on classification and recognition.

• Earthquakes and Structures
• /
• v.9 no.1
• /
• pp.93-109
• /
• 2015

Based on the reconnaissance of buildings in Dujiangyan City during 2008 Wenchuan earthquake, China, structural damage characteristics and the spatial distribution of structural damage are investigated, and the possible reasons for the extraordinary features are discussed with consideration of the influence of urban historical evolution and spatial variation of earthquake motions. Firstly, the urban plan and typical characteristics of structural seismic damage are briefly presented and summarized. Spatial distribution of structural damage is then comparatively analyzed by classifying all surveyed buildings in accordance with different construction age, considering the influence of seismic design code on urban buildings. Finally, the influences of evolution of seismic design code, topographic condition, local site and distance from fault rupture on spatial distribution of structural damage are comprehensively discussed. It is concluded that spatial variation of earthquake motions, resulting from topography, local site effect and fault rupture, are very important factor leading to the extraordinary spatial distribution of building damage except the evolution of seismic design codes. It is necessary that the spatial distribution of earthquake motions should be considered in seismic design of structures located in complicated topography area and near active faults.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.9
• /
• pp.1203-1208
• /
• 2001

Linzhi Native Pig is a unique local breed recently discovered in the hinterland of Tibet. Its geological distribution, natural environment and ecological conditions have been explored. Using random sampling in typical colony of classification and standard animal-scientific and biogenetic techniques, we examined its contour features, size and weight, reproductive performances, carcass characters, meat quality, fresh-keeping features and the frequency distribution in the 19 structural gene loci encoding enzymes and proteins; according to folklores and Tibetan, Chinese and English history books, the materials and literature of Tibetan Studies, we have analyzed its origin and affirmed the fact that its products have been consumed as Tibetan medicine resources. Our findings make certain that Linzhi Native Pig holds great potential value in economy and culture.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.16 no.2
• /
• pp.104-110
• /
• 2016

Dense local image descriptors like SIFT are fruitful for capturing salient information about image, shown to be successful in various image-related tasks when formed in bag-of-words representation (i.e., histograms). In this paper we consider to utilize these dense local descriptors in the object tracking problem. A notable aspect of our tracker is that instead of adopting a point estimate for the target model, we account for uncertainty in data noise and model incompleteness by maintaining a distribution over plausible candidate models within the Bayesian framework. The target model is also updated adaptively by the principled Bayesian posterior inference, which admits a closed form within our Dirichlet prior modeling. With empirical evaluations on some video datasets, the proposed method is shown to yield more accurate tracking than baseline histogram-based trackers with the same types of features, often being superior to the appearance-based (visual) trackers.