• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.

• The Magazine of the IEIE
• /
• v.23 no.12
• /
• pp.115-125
• /
• 1996

This paper presents a new algorithm for the self-localization of a mobile robot using one degree perspective Invariant(Cross Ratio). Most of conventional model-based self-localization methods have some problems that data structure building, map updating and matching processes are very complex. Use of a simple cross ratio can be effective to the above problems. The algorithm is based on two basic assumptions that the ground plane is flat and two locally parallel sloe-lines are available. Also it is assumed that an environmental map is available for matching between the scene and the model. To extract an accurate steering angle for a mobile robot, we take advantage of geometric features such as vanishing points. Feature points for cross ratio are extracted robustly using a vanishing point and intersection points between two locally parallel side-lines and vertical lines. Also the local position estimation problem has been treated when feature points exist less than 4points in the viewed scene. The robustness and feasibility of our algorithms have been demonstrated through real world experiments In Indoor environments using an indoor mobile robot, KASIRI-II(KAist Simple Roving Intelligence).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.1209-1213
• /
• 2005

It reflects well feature of slope that is characteristic of city river basin of Pusan local. Process various hydrological datas and basin details datas which is collected through basin basis data. weather satellite equipment(EMS-DEU) and automatic water level equipment(AWS-DEU) and use as basin input data of ILLUDAS model, SWMM model and HEC-HMS model In order to examine outflow feature of experiment basin and then use in reservoir design of experiment basin through calibration and verification about HEC-HMS model. Inserted design rainfall for 30 years that is design criteria of creek into HEC-HMS model and then calculated design floods according to change aspect of the impermeable rate. Capacity of reservoir was determined on the outflow mass curve. Designed imagination reservoir(volume $54,000m^3$) at last outlet upper stream of experiment basin, after designing reservoir. It could be confirmed that the peak flow was reduced resulting from examining outflow aspect. Designing reservoir must decrease outflow of urban areas.

• The Journal of the Korea Contents Association
• /
• v.7 no.1
• /
• pp.58-64
• /
• 2007

In pattern recognition field, there are many optimization problems having exponential search spaces. To solve of sequential search algorithms seeking sub-optimal solutions have been used. The algorithms have limitations of stopping at local optimums. Recently lots of researches attempt to solve the problems using genetic algorithms. This paper explains the huge search spaces of typical problems such as feature selection, classifier ensemble selection, neural network pruning, and clustering, and it reviews the genetic algorithms for solving them. Additionally we present several subjects worthy of noting as future researches.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.9
• /
• pp.902-907
• /
• 2011

In this paper, we deal with performance evaluation of visual path following using 2D and 3D information. Visual path follow first teaches driving path by selecting milestone images then follows the same route by comparing the milestone image and current image. We follow the visual path following algorithm of [8] and [10]. In [8], a robot navigated with 2D image information only. But in [10], local 3D geometries are reconstructed between the milestone images in order to achieve fast feature prediction which allows the recovery from tracking failures. Experimental results including diverse indoor cases show performance of each algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2109-2123
• /
• 2017

This paper presents a super-resolution reconstruction method based on sparse representation for two-dimensional bar code images. Considering the features of two-dimensional bar code images, Kirsch and LBP (local binary pattern) operators are used to extract the edge gradient and texture features. Feature extraction is constituted based on these two features and additional two second-order derivatives. By joint dictionary learning of the low-resolution and high-resolution image patch pairs, the sparse representation of corresponding patches is the same. In addition, the global constraint is exerted on the initial estimation of high-resolution image which makes the reconstructed result closer to the real one. The experimental results demonstrate the effectiveness of the proposed algorithm for two-dimensional bar code images by comparing with other reconstruction algorithms.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.385-399
• /
• 2007

In many image processing applications, a random noise makes some trouble since most video enhancement functions produce visual artifacts if a priori of the noise is incorrect. The basic difficulty is that the noise and the signal are difficult to be distinguished. Typical unsharp masking (UM) enhances the visual appearances of images, but it also amplifies the noise components of the image. Hence, the applications of a UM are limited when noises are presented. This paper proposed statistical algorithms based on parametric and nonparametric tests to adaptively enhance the image feature and the noise combining while applying UM. With the proposed algorithm, it is made possible to enhance the local contrast of an image without amplifying the noise.

• Speech Sciences
• /
• v.12 no.2
• /
• pp.171-182
• /
• 2005

An efficient GMM (Gaussian mixture modeling) method based on LPCA (local principal component analysis) with VQ (vector quantization) for speaker identification is proposed. To reduce the dimension and correlation of the feature vector, this paper proposes a speaker identification method based on principal component analysis. The proposed method firstly partitions the data space into several disjoint regions by VQ, and then performs PCA in each region. Finally, the GMM for the speaker is obtained from the transformed feature vectors in each region. Compared to the conventional GMM method with diagonal covariance matrix, the proposed method requires less storage and complexity while maintaining the same performance requires less storage and shows faster results.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.2
• /
• pp.69.2-69.2
• /
• 2010

We investigate the southeastern region of the Vela supernova remnant (SNR) in the multi-wavelength domains. This region is quite interesting because it includes the bullet feature D/D´ and another SNR (the Vela Jr.). The C IV $\lambda\lambda1548$, 1551 emission-line morphologies obtained from the FIMS/SPEAR data show that there are several local peaks of C IV on the bullet D/D´ and the Vela Jr. SNR. This may provide clues to direct interaction between both SNRs. Also, we found that the southeastern side of the Vela is in direct contact with an H-alpha ring feature whose central source seems to be a B-type star, HD 76161. The C IV emission peaks along this contact boundary. We investigate this interacting region in detail.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1570-1578
• /
• 2000

Object motion is an important feature of content in video sequences. By now, various methods to exact feature about the object motion have been reported[1,2]. However they are not suitable to index video using the motion, since a lot of bits and complex indexing parameters are needed for the indexing [3,4] In this paper, we propose object motion map which could provide efficient indexing method for object motion. The proposed object motion map has both global and local motion information during an object is moving. Furthermore, it requires small bit of memory for the indexing. to evaluate performance of proposed indexing technique, experiments are performed with video database consisting of MPEG-1 video sequence in MPEG-7 test set.