• Journal of information and communication convergence engineering
• /
• v.6 no.1
• /
• pp.94-99
• /
• 2008

Segmentation for the region of nucleus in the image of uterine cervical cytodiagnosis is known as the most difficult and important part in the automatic cervical cancer recognition system. In this paper, the region of nucleus is extracted from an image of uterine cervical cytodiagnosis using the HSI model. The characteristics of the nucleus are extracted from the analysis of morphemetric features, densitometric features, colormetric features, and textural features based on the detected region of nucleus area. The classification criterion of a nucleus is defined according to the standard categories of the Bethesda system. The fuzzy C-means clustering algorithm is employed to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

• The Journal of the Petrological Society of Korea
• /
• v.4 no.2
• /
• pp.168-177
• /
• 1995

Crystal boundaries in igneous rocks are genetically classified in order to predict the geometric patterns of the boundaries which may aid deciphering the textural code in igneous rocks. Crystal boundaries may be formed by two end-member processes;(1) mechanical and (2) chemical removal of interstitial melt. Mechanical removal of the melt will form displacement impingement boundaries, while chemical removal of the melt will form growth impingement boundaries. The positions of boundaries relative to the material points may be affected by secondary processes such as (1) migration and (2) dissolution. The geometric features of crystal boundaries, suggested in this study, may be useful when studying igneous textures and processes, although it may be impossible to determine the suggested features with the analytical techniques currently avilable.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1635-1648
• /
• 2008

The extraction of important features in cancer cell image analysis is a key process in grading renal cell carcinoma. In this study, we applied three-dimensional (3D) texture feature extraction methods to cell nuclei images and evaluated the validity of them for computerized cell nuclei grading. Individual images of 2,423 cell nuclei were extracted from 80 renal cell carcinomas (RCCs) using confocal laser scanning microscopy (CLSM). First, we applied the 3D texture mapping method to render the volume of entire tissue sections. Then, we determined the chromatin texture quantitatively by calculating 3D gray-level co-occurrence matrices (3D GLCM) and 3D run length matrices (3D GLRLM). Finally, to demonstrate the suitability of 3D texture features for grading, we performed a discriminant analysis. In addition, we conducted a principal component analysis to obtain optimized texture features. Automatic grading of cell nuclei using 3D texture features had an accuracy of 78.30%. Combining 3D textural and 3D morphological features improved the accuracy to 82.19%. As a comparative study, we also performed a stepwise feature selection. Using the 4 optimized features, we could obtain more improved accuracy of 84.32%. Three dimensional texture features have potential for use as fundamental elements in developing a new nuclear grading system with accurate diagnosis and predicting prognosis.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.5 s.153
• /
• pp.699-710
• /
• 2006

The objective of this study was to identify the texture-related components of woven fabrics and to develop a multidimensional perceptual structure map to represent the tactile textures. Eighty subjects in clothing and tektite industries were selected for multivariate data on each fabric of 30 using the questionnaire with 9 pointed semantic differential scales of 20 texture-related adjectives. Data were analyzed by factor analysis, hierarchical cluster analysis, and multidimensional scaling(MDS) using SPSS statistical package. The results showed that the five factors were selected and composed of density/warmth-coolness, stiffness, extensibility, drapeability, and surface/slipperiness. As a result of hierarchical cluster analysis, 30 fabrics were grouped by four clusters; each cluster was named with density/warmth-coolness, surface/slipperiness, stiffness, and extensibility, respectively. By MDS, three dimensions of tactile texture were obtained and a 3-dimensional perceptual structure map was suggested. The three dimensions were named as surface/slipperiness, extensibility, and stiffness. We proposed a positioning perceptual map of fabrics related to texture naming system(TNS). To classify the textural features of the woven fabrics, hierarchical cluster analysis containing all the data variations, even though it includes the errors, may be more desirable than texture-related multidimensional data analysis based on factor loading values in respect of the effective variables reduction without losing the critical variations.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.765-772
• /
• 1996

Objectives of this study were to develop an application method of a numerical retina using the finite element model and to investigate the performance of image features extraction in comparison to the textural analysis. Using a plant community of radish sprouts, excellent resolution of the finite element retina was revealed. The sensitivity analysis of the finite element retina from engineering point of view was discussed. The importance of sensitivity analysis of the finite element retina was pointed out in terms of extraction of effective image features of plant community . Technical details of maximizing the sensitivity of the finite element retina to populated plant canopy were also discussed.

• 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 Journal of the Petrological Society of Korea
• /
• v.19 no.3
• /
• pp.227-244
• /
• 2010

Abundant spinel lherzolite xenoliths showing distinctively different textural types such as protogranular, porphyroclastic, and mylonitic texture are trapped in the basaltic rocks from southeastern part of Jeju Island. These xenoliths show the textural spectrum from coarse-grained protogranular through porphyroclastic with bimodal grain size to fine-grained and foliated mylonitic texture. They tend to decrease in grain sizes and show more linear grain boundaries and more frequent triple junctions from protogranular through porphyroclastic to mylonitic. Spinel has different occurrence mode according the textural type. Spinel is always associated with orthopyroxene in protogranular texture, whereas it is scattered and independent of orthopyroxene in mylonitic texture. Additionally, porphyroblast from porphyroclastic and mylonitic textures has internal deformation features such as kink band, undulatory extinction and curved lamella, whereas neoblast is strain-free. These textural features indicate increasing degree of static/dynamic recrystallization from protogranular through porphyroclastic to mylonitic texture. The mg#[$=100{\times}Mg/(Mg+Fe_t)$] of olivine, orthopyroxene and clinopyroxene is relatively constant (ol: 88-91; opx: 89-92; cpx: 89-92) regardless of textural differences. The mg# of constituent minerals, NiO content (0.3~0.4 wt%) and MnO content (0.1~0.2 wt%) of olivine are similar to those of mantle xenoliths worldwide, also indicating that studied spinel lherzolite xenoliths were mantle residues having experienced 20~25% partial melting. The geochemical and textural characteristics have close relations showing that LREE and incompatible trace elements content of orthopyroxene and clinopyroxene increases from protogranular through porphyroclastic to mylonitic. These observations suggest that the studied mantle xenoliths experienced metasomatism by LREE enriched melt or fluid after partial melting, indicating a close relation between deformation and metasomatism. The metasomatism was possibly confined to narrow shear zones from where porphyroclastic and mylonitic textured xenoliths originated. These shear zones might favorably drive the percolation of LREE-enriched melts/fluids responsible for the metasomatism in the lithospheric mantle below the Jeju Island.

• International Journal of Contents
• /
• v.11 no.3
• /
• pp.47-53
• /
• 2015

Visual object tracking is a fundamental problem in the field of computer vision, as it needs a proper model to account for drastic appearance changes that are caused by shape, textural, and illumination variations. In this paper, we propose a feature-based visual-object-tracking method with a sparse representation. Generally, most appearance-based models use the gray-scale pixel values of the input image, but this might be insufficient for a description of the target object under a variety of conditions. To obtain the proper information regarding the target object, the following combination of features has been exploited as a corresponding representation: First, the features of the target templates are extracted by using the HOG (histogram of gradient) and LBPs (local binary patterns); secondly, a feature-based sparsity is attained by solving the minimization problems, whereby the target object is represented by the selection of the minimum reconstruction error. The strengths of both features are exploited to enhance the overall performance of the tracker; furthermore, the proposed method is integrated with the particle-filter framework and achieves a promising result in terms of challenging tracking videos.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.5
• /
• pp.519-524
• /
• 2006

Segmentation for the region of nucleus in the image of uterine cervical cytodiagnosis is known as the most difficult and important part in the automatic cervical cancer recognition system. In this paper, the region of nucleus is extracted from an image of uterine cervical cytodiagnosis using the fuzzy grey morphology operation. The characteristics of the nucleus are extracted from the analysis of morphemetric features, densitometric features, colormetric features, and textural features based on the detected region of nucleus area. The classification criterion of a nucleus is defined according to the standard categories of the Bethesda system. The enhanced fuzzy ART algorithm is used to the extracted nucleus and the results show that the proposed method is efficient in nucleus recognition and uterine cervical Pap-Smears extraction.

• International Journal of Computer Science & Network Security
• /
• v.21 no.11
• /
• pp.89-96
• /
• 2021

This work is an extension of my work presented a robust and economically efficient method for the Discrimination of four Mung-Beans [1] varieties based on quantitative parameters. Due to the advancement of technology, users try to find the solutions to their daily life problems using smartphones but still for computing power and memory. Hence, there is a need to find the best classifier to classify the Mung-Beans using already suggested features in previous work with minimum memory requirements and computational power. To achieve this study's goal, we take the experiments on various supervised classifiers with simple architecture and calculations and give the robust performance on the most relevant 10 suggested features selected by Fisher Co-efficient, Probability of Error, Mutual Information, and wavelet features. After the analysis, we replace the Artificial Neural Network and Deep learning with a classifier that gives approximately the same classification results as the above classifier but is efficient in terms of resources and time complexity. This classifier is easily implemented in the smartphone environment.