• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권1호
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권2호
• /
• pp.438-455
• /
• 2024

Recently, many unsupervised learning-based models have emerged for Just Noticeable Difference (JND) estimation, demonstrating remarkable improvements in accuracy. However, these models suffer from a significant drawback is that their heavy reliance on handcrafted priors for guidance. This restricts the information for estimating JND simply extracted from regions that are highly related to handcrafted priors, while information from the rest of the regions is disregarded, thus limiting the accuracy of JND estimation. To address such issue, on the one hand, we extract the information for estimating JND in an Adversarial Complementary Learning (ACoL) way and propose an ACoL-JND network to estimate the JND by comprehensively considering the handcrafted priors-related regions and non-related regions. On the other hand, to make the handcrafted priors richer, we take two additional priors that are highly related to JND modeling into account, i.e., Patterned Masking (PM) and Contrast Masking (CM). Experimental results demonstrate that our proposed model outperforms the existing JND models and achieves state-of-the-art performance in both subjective viewing tests and objective metrics assessments.

• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.277-283
• /
• 2021

This paper addresses the problem of vision-based mask filter inspection for mask production systems. Machine learning-based approaches can be considered to solve the problem, but they may not be applicable to mask filter inspection if normal and anomaly mask filter data are not sufficient. In such cases, handcrafted image processing methods have to be considered to solve the problem. In this paper, we propose a hierarchical correlation-based approach that combines handcrafted image processing methods to detect anomaly mask filters. The proposed approach combines image rotation, cropping and resizing, edge detection of mask filter parts, average blurring, and correlation-based decision. The proposed approach was tested and analyzed with real mask filters. The results showed that the proposed approach was able to successfully detect anomalies in mask filters.

• 복식문화연구
• /
• 제19권6호
• /
• pp.1259-1271
• /
• 2011

This study investigates and compares the changes of naturalism in fashion presented over a 30-year period to understand the diversity of naturalism in fashion. Data were collected from 59 volumes of the "Vogue" magazine for January and July in each year from 1980 to 2009. The data used for content analysis consists of 440 words and these were condensed into three periods according to decade(1980~1989, 1990~1999, and 2000~2009). The selected words were classified into four sub-themes according to the previous research definitions such as primitive look, natural look, eco look and handcrafted look. The results are as follows. First, naturalism of fashion was highly presented in the 1980s but the percentages of naturalism in three decades were all more or less similar. Especially, natural look appeared more in the 1980s and eco look was in the 1990s, while natural look, eco look and handcrafted look were found all together in the 2000s. Second, naturalism of fashion showed higher frequency of F/W seasons in the 1990s, while S/S seasons in the 1990s and 2000s. In particular, natural look was presented more at S/S seasons. The sub-themes coexistence were presented in the 24 seasons out of 59 seasons and showed more variously in the 2000s. Third, the words selected from sub-themes of naturalism in fashion demonstrated the differences by decade.

• 복식
• /
• 제50권7호
• /
• pp.75-96
• /
• 2000

Modern clothing is approached in the level of art, and it becomes the means of expressing individuality in modern society uniformed by the development of information society. In this modern society, modern men need the recovery of humanity and expectations of handcrafted skills for the succession of tradition culture. Prior to expressing individuality, we should examine our traditional culture and combine it with western culture. Quit started to be used for practical purpose such as life items, but it is expanded to the fields of art. Used in dress and its ornaments design, quilt is often applied to the addition of aesthetic factors or cubic material feelings by transforming its warming effect. Hereby, this study has a purpose to create high value added modern dross and its ornaments design by expressing the modern clothing is approached in the level of art, and it becomes the means of expressing individuality roe-dimensional characteristics of quilt, and applying the color combination and the surface of butterfly wings to dress and its ornaments design. The following are the results of this study. 1. The concept of quilt started for practical purposes, but it is expanded to decoration in modern times, and it is confirmed that quilt can be variously applied to handcrafted modern design. 2. Quilt removes the plane character of textile and it riches the three-dimensional material of dress and its ornaments. Applying these characteristics, the expression of transparent wings were possible with 3 transparent layers of textile. 3. The spledid color of butterfly wings are expressed by coloring oganza and felt, and the various colors of felt showed rich color gradation. 4. The form and pattern of butterfly wings are applied as modeling form and line, and the transformation. repetition and expansion of unit forms determined the form of quilting lines. By designing the characteristics of back wings for the composition line of clothing, the form characteristics of a motif could be emphasized. 5. By using felt, oganza, Damdam yarn and ostritch feathers in expressing butterfly wings, the warm material of Linbun is felt, and the tip hair of wings are expressed by croche techniques using Damdam yarn.

• ETRI Journal
• /
• 제44권2호
• /
• pp.286-299
• /
• 2022

Human activity recognition in real time is a challenging task. Recently, a plethora of studies has been proposed using deep learning architectures. The implementation of these architectures requires the high computing power of the machine and a massive database. However, handcrafted features-based machine learning models need less computing power and very accurate where features are effectively extracted. In this study, we propose a handcrafted model based on three-dimensional sequential skeleton data. The human body skeleton movement over a frame is computed through joint positions in a frame. The joints of these skeletal frames are projected into two-dimensional space, forming a "movement polygon." These polygons are further transformed into a one-dimensional space by computing amplitudes at different angles from the centroid of polygons. The feature vector is formed by the sampling of these amplitudes at different angles. The performance of the algorithm is evaluated using a support vector machine on four public datasets: MSR Action3D, Berkeley MHAD, TST Fall Detection, and NTU-RGB+D, and the highest accuracies achieved on these datasets are 94.13%, 93.34%, 95.7%, and 86.8%, respectively. These accuracies are compared with similar state-of-the-art and show superior performance.

• 인터넷정보학회논문지
• /
• 제20권4호
• /
• pp.91-102
• /
• 2019

자율주행 시스템에서, 카메라에 포착된 영상을 통하여 보행자를 분류하는 기능은 보행자 안전을 위하여 매우 중요하다. 기존에는 HOG(Histogram of Oriented Gradients)나 SIFT(Scale-Invariant Feature Transform) 등으로 보행자의 특징을 추출한 후 SVM(Support Vector Machine)으로 분류하는 기술을 사용했었으나, 보행자 특징을 위와 같이 수동(handcrafted)으로 추출하는 것은 많은 한계점을 가지고 있다. 따라서 본 논문에서는 CNN(Convolutional Neural Network)의 깊은 특징(deep features)과 전이학습(transfer learning)을 사용하여 보행자를 안정적이고 효과적으로 분류하는 방법을 제시한다. 본 논문은 2가지 대표적인 전이학습 기법인 고정특징추출(fixed feature extractor) 기법과 미세조정(fine-tuning) 기법을 모두 사용하여 실험하였고, 특히 미세조정 기법에서는 3가지 다른 크기로 레이어를 전이구간과 비전이구간으로 구분한 후, 비전이구간에 속한 레이어들에 대해서만 가중치를 조정하는 설정(M-Fine: Modified Fine-tuning)을 새롭게 추가하였다. 5가지 CNN모델(VGGNet, DenseNet, Inception V3, Xception, MobileNet)과 INRIA Person데이터 세트로 실험한 결과, HOG나 SIFT 같은 수동적인 특징보다 CNN의 깊은 특징이 더 좋은 성능을 보여주었고, Xception의 정확도(임계치 = 0.5)가 99.61%로 가장 높았다. Xception과 유사한 성능을 내면서도 80% 적은 파라메터를 학습한 MobileNet이 효율성 측면에서는 가장 뛰어났다. 그리고 3가지 전이학습 기법중 미세조정 기법의 성능이 가장 우수하였고, M-Fine 기법의 성능은 미세조정 기법과 대등하거나 조금 낮았지만 고정특징추출 기법보다는 높았다.

• 한국지역사회생활과학회지
• /
• 제22권1호
• /
• pp.103-113
• /
• 2011

The purpose of the study was to examine formative features of embroidered norigae in form, color, pattern and expressive technique through positive analysis of relics and various of collections of work and to consider expressive features of embroidered norigae. The results of the study were as follows. First, embroidered norigae has handcrafted decoration. it was made by being sewed for women longing for their family's happiness. Embroidered norigae is a dress worn by women that is hung on a coat string or the waist part of a skirt. Second, it is eco-environmental. Embroidered norigae applied things seen in nature such as flowers, butterflies and bees to its pattern. Third, it has practicality. Embroidered norigae has high practical value besides a decorative function. Needle case norigae and incense case norigae provide functions in accordance with women's wisdom and skill as well as practicality. Fourth, it is praying for good luck. Women embroidered patterns symbolizing their desires in life such as their family's happiness, wealth, many sons and a long life. Fifth, it has balance and harmony. The knot of embroidered norigae has a perfect symmetry in the front/back part and in the right/left part. And the main body and tassel are symetrical in the right/left part, which gives stability and comfortableness. Embroidered norigae is classified into knot, main body and decorative part in its form. The three kinds express their unique beauty by being harmonized together. Finally, it has a property of melody. Movement of the tassel has a property of melody shaken by the wind and movement of its wearer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• 한국의상디자인학회지
• /
• 제8권2호
• /
• pp.47-59
• /
• 2006

The purpose of this study is to grasp the meaning of retro-fashion, to research the formative feature characteristic and aesthetic values. Retro-fashion is one of the expression of spatiotemporal-eclecticism, The formative of modern Retro-fashion are as follows: First, Retro-fashion based on spatiotemporal-eclecticism have been come from 40s, 50s, 60s, 70s, 80s style of time, and the asia, africa, middle east, latin America in region. Second, the design inspiration and technique is used more primitive crafts and decoration like handcrafted material, handmade ornaments as dyeing and embroidery of bohemian, jacqwuard pattern, oriental beads, applique, new hippie touch, patchwork, smocking, primitive button, woods, ethnic motives. Third, modern Retro-fashion is reflection of human feelings as nostalgia from the past, it supplies the sense of fashion creativity and new ideas.