• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3121-3143
• /
• 2019

Segmentation plays an important role in the field of image processing and computer vision. Intuitionistic fuzzy C-means (IFCM) clustering algorithm emerged as an effective technique for image segmentation in recent years. However, standard fuzzy C-means (FCM) and IFCM algorithms are sensitive to noise and initial cluster centers, and they ignore the spatial relationship of pixels. In view of these shortcomings, an improved algorithm based on IFCM is proposed in this paper. Firstly, we propose a modified non-membership function to generate intuitionistic fuzzy set and a method of determining initial clustering centers based on grayscale features, they highlight the effect of uncertainty in intuitionistic fuzzy set and improve the robustness to noise. Secondly, an improved nonlinear kernel function is proposed to map data into kernel space to measure the distance between data and the cluster centers more accurately. Thirdly, the local spatial-gray information measure is introduced, which considers membership degree, gray features and spatial position information at the same time. Finally, we propose a new measure of intuitionistic fuzzy entropy, it takes into account fuzziness and intuition of intuitionistic fuzzy set. The experimental results show that compared with other IFCM based algorithms, the proposed algorithm has better segmentation and clustering performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.771-789
• /
• 2019

Text detection has been a popular research topic in the field of computer vision. It is difficult for prevalent text detection algorithms to avoid the dependence on datasets. To overcome this problem, we proposed a novel unsupervised text detection algorithm inspired by bootstrap learning. Firstly, the text candidate in a novel form of superpixel is proposed to improve the text recall rate by image segmentation. Secondly, we propose a unique text sample selection model (TSSM) to extract text samples from the current image and eliminate database dependency. Specifically, to improve the precision of samples, we combine maximally stable extremal regions (MSERs) and the saliency map to generate sample reference maps with a double threshold scheme. Finally, a multiple kernel boosting method is developed to generate a strong text classifier by combining multiple single kernel SVMs based on the samples selected from TSSM. Experimental results on standard datasets demonstrate that our text detection method is robust to complex backgrounds and multilingual text and shows stable performance on different standard datasets.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.158-161
• /
• 2003

A cascade structured neural network called Sigma-Pi$_{t}$ Cascaded Hybrid Neural Network ($\sigma$$\pi$$_{t}$-CHNN) is Proposed. It is an extended version of the Sigma-Pi Cascaded extended Hybrid Neural Network ($\sigma$$\pi$-CHNN), where the classical multiplicative neuron ($\pi$-neuron) is replaced by the translated multiplicative ($\pi$$_{t}$-neuron) model. The learning algorithm of $\sigma$$\pi$$_{t}$-CHNN is composed of an evolutionary programming method, responsible for determining the network architecture, and of a Levenberg-Marquadt algorithm, responsible for tuning the weights of the network. The $\sigma$$\pi$$_{t}$-CHNN is evaluated in 2 pattern classification problems: the 2 spirals and the sonar problems. In the 2 spirals problem, $\sigma$$\pi$$_{t}$-CHNN can generate neural networks with 10％ less hidden neurons than that in previous neural models. In the sonar problem, $\sigma$$\pi$$_{t}$-CHNN can find the optimal solution for the problem i.e., a network with no hidden neurons. These results confirm the expanded information processing capabilities of $\sigma$$\pi$$_{t}$-CHNN, when compared to previous neural network models. network models.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권1호
• /
• pp.38-42
• /
• 2002

A fast iterative solving method of fuzzy relational equation is proposed. It is derived by eliminating a redundant comparison process in the conventional iterative solving method (Pedrycz, 1983). The proposed method is applied to image reconstruction, and confirmed that the computation time is decreased to 1 / 40 with the compression rate of 0.0625. Furthermore, in order to make any initial solution converge on a reconstructed image with a good quality, a new cost function is proposed. Under the condition that the compression rate is 0.0625, it is confirmed that the root mean square error of the proposed method decreases to 27.34% and 86.27% compared with those of the conventional iterative method and a non iterative image reconstruction method, respectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권9호
• /
• pp.3685-3700
• /
• 2015

To avoid influences caused by pose, illumination and facial expression variations, we propose a robust three-step algorithm based on ASM and POEM for facial landmark localization. Firstly, Model Selection Factor is utilized to achieve a pose-free initialized shape. Then, we use the global shape model of ASM to describe the whole face and the texture model POEM to adjust the position of each landmark. Thirdly, a second localization is presented to discriminatively refine the subtle shape variation for some organs and contours. Experiments are conducted in four main face datasets, and the results demonstrate that the proposed method accurately localizes facial landmarks and outperforms other state-of-the-art methods.

• 전산구조공학
• /
• 제33권1호
• /
• pp.20-22
• /
• 2020

• 전산구조공학
• /
• 제32권4호
• /
• pp.11-16
• /
• 2019

• 전산구조공학
• /
• 제34권3호
• /
• pp.4-9
• /
• 2021

• 정보교육학회논문지
• /
• 제25권6호
• /
• pp.927-934
• /
• 2021

인공지능은 우리의 삶에 점차 많은 부분을 차지하고 있으며, 발전하는 속도도 빨라지고 있다. 학생들의 컴퓨팅 사고력을 인공지능이 학습하는 방법대로 길러주는 것을 ACT(AI based Computational Thinking)라고 한다. ACT 중 패턴 인식은 문제를 효율적으로 해결하기 위해 필수적인 요소이다. 패턴 분석은 패턴 인식 과정의 일부로 볼 수 있다. 실제로 넷플릭스의 개인 맞춤 영화 추천, 반복된 증상을 분석하여 코로나 바이러스로 명명하는 것 등이 모두 패턴 분석의 결과이다. 패턴인식을 포함한 ACT의 중요성이 부각되는 것에 반면, 유치원과 초등학교 저학년을 대상으로 한 소프트웨어 교육은 국외에 비해 많이 부족한 실정이다. 따라서 본 연구에서는 유치원 학생들을 대상으로 하여 패턴 분석을 통한 인공지능 기반 컴퓨팅 사고력 계발을 위한 교재를 설계하고 개발하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제14권4호
• /
• pp.256-267
• /
• 2014

An automatic switch among ensembles of clustering algorithms is proposed as a part of the bibliographic big data retrieval system by utilizing a fuzzy inference engine as a decision support tool to select the fastest performing clustering algorithm between fuzzy C-means (FCM) clustering, Newman-Girvan clustering, and the combination of both. It aims to realize the best clustering performance with the reduction of computational complexity from O($n^3$) to O(n). The automatic switch is developed by using fuzzy logic controller written in Java and accepts 3 inputs from each clustering result, i.e., number of clusters, number of vertices, and time taken to complete the clustering process. The experimental results on PC (Intel Core i5-3210M at 2.50 GHz) demonstrates that the combination of both clustering algorithms is selected as the best performing algorithm in 20 out of 27 cases with the highest percentage of 83.99%, completed in 161 seconds. The self-adapted FCM is selected as the best performing algorithm in 4 cases and the Newman-Girvan is selected in 3 cases.The automatic switch is to be incorporated into the bibliographic big data retrieval system that focuses on visualization of fuzzy relationship using hybrid approach combining FCM and Newman-Girvan algorithm, and is planning to be released to the public through the Internet.