• Journal of KIISE:Databases
• /
• v.30 no.4
• /
• pp.362-371
• /
• 2003

In this paper, we propose an optimal interest point extraction method to support shape-base image classification and indexing for image database by applying a dynamic threshold that reflects the characteristics of the shape contour. The threshold is determined dynamically by comparing the contour length ratio of the original shape and the approximated polygon while the algorithm is running. Because our algorithm considers the characteristics of the shape contour, it can minimize the number of interest points. For n points of the contour, the proposed algorithm has O(nlogn) computational cost on an average to extract the number of m optimal interest points. Experiments were performed on the 70 synthetic shapes of 7 different contour types and 1100 fish shapes. It shows the average optimization ratio up to 0.92 and has 14% improvement, compared to the fixed threshold method. The shape features extracted from our proposed method can be used for shape-based image classification, indexing, and similarity search via normalization.

• 전자공학회논문지 IE
• /
• v.44 no.2
• /
• pp.32-40
• /
• 2007

In this paper, the crease extraction method is proposed to improve the accuracy of feature extraction within the fingerprint image. First of all, for each pixel in fingerprint image, it calculates the average grey level and variance to determine if the current pixel composes the crease, and estimates the direction of crease. Secondly, once the direction of every pixel in crease candidate area is estimated, it is decomposed into 8 different images, depending on their direction. The properties of crease consists of the length of the crease candidate area, the correspondence between the crease direction and the pixel distribution direction, the difference between the ridge direction and the pixel distribution direction, and finally the grey level of the candidate pixels. The proposed method finally extracts the crease from the crease clusters estimated from directional images. In conclusion, applying the proposed method improved the accuracy of overall feature extraction by 91.4% by accurately and precisely extracting the crease from fingerprint image.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.12-18
• /
• 2010

Automatic Target Detection (ATD) systems that use forward-looking infrared (FLIR) consists of three stages. preprocessing, detection, and clutter rejection. All potential targets are extracted in preprocessing and detection stages. But, this results in a high false alarm rates. To reduce false alarm rates of ATD system, true targets are extracted in the clutter rejection stage. This paper focuses on clutter rejection stage. This paper presents a new clutter rejection technique using PCA features and stochastic features of clutters and targets. PCA features are obtained from Euclidian distances using which potential targets are projected to reduced eigenspace selected from target eigenvectors. CV is used for calculating stochastic features of edges in targets and clutters images. To distinguish between target and clutter, LDA (Linear Discriminant Analysis) is applied. The experimental results show that the proposed algorithm accurately classify clutters with a low false rate compared to PCA method or CV method

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.1
• /
• pp.33-38
• /
• 2001

In this paper, we present an image retrieval system using shape features. The preprocessing to gain shape feature includes edge extraction using chain code. The shape features consist of center of mass, standard deviation, ratio of major axis and minor axis length. The similarity is estimated as comparing the features of query image with the features of images in database. Thus, the candidates of images are retrieved according to the order of similarity. The result of an experimentation is dullness for scale, rotation and translation. We evaluate the performance of shape features for image retrieval on a database with over 170 images. The Recall and the Precision is each 0.72 and 0.83 in the result of average experiment. So the proposed method is presented useful method.

• Journal of Biomedical Engineering Research
• /
• v.19 no.3
• /
• pp.233-242
• /
• 1998

In anatomical aspects, magnetic resonance image offers more accurate information than other medical images such as X ray ultrasonic and CT images. This paper introduces a method that recognizes disk diseases from spine MR images. In this method, image enhancement, image segmentation and feature extraction for sagittal plane and axial plane images are performed to separate the disk region. And then template matching method is used to extract disease region for axial plane imges. Finally, disease feature vectors are integrated and disease discrimination processes are performed. Experimental results show that the proposed method discriminates between normal and diseased disk with a considerable recognition ratio.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.425-427
• /
• 2000

얼굴 표정은 사람의 감정을 표현함과 동시에 그것을 이해할 수 있는 중요한 수단이다. 최근 이러한 얼굴 표정의 자동인식과 추적을 위한 연구가 많이 진행되고 있다. 본 연구에서는 대략적인 얼굴영역을 설정하여 얼굴의 표정을 나타내는 표정요소들을 찾아낸 후, 각 요소의 특징점을 추출하고 추적하는 방법을 제시한다. 제안하는 시스템의 개요는 입력영상의 첫 프레임에서 얼굴영역 및 특징점을 찾고, 연속되는 프레임에서 반복적으로 이를 추적한다. 특징점 추출과 추적에는 템플릿 매칭과 Canny 경계선 검출기, Gabor 웨이블릿 변환을 사용하였다.

• Proceedings of the KAIS Fall Conference
• /
• 2003.06a
• /
• pp.284-287
• /
• 2003

본 논문은 시각 장애인을 위해 양면 인쇄된 점자를 스캐너를 통해서 읽어 들인 후, 영상 내의 잡음과 같은 미세 정보를 제거하는 전처리과정을 거친다 스캔한 영상을 임계값을 이용한 클리핑으로 이진영상을 만든 후 영상의 특징을 추출한다. 추출된 특징은 점자의 앞면과 뒷면으로 분류할 수 있다. 점자 앞면의 특징이 아래반원으로 나타나며 이러한 특징을 이용한 검출필터를 만들어 점자의 앞면만을 추출해낸다. 영상을 각각 수직방향, 수평방향으로 투영시켜 점자영상 분할을 위한 거리를 계산, 자간격과 줄간격을 구해 ½되는 지점에 선을 그어 분할한다. 분할된 점자 형태소를 낱자로 인식한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.89-90
• /
• 2019

본 논문에서는 ultrasound image Right Parasagittal Liver에 edge detection을 적용한 후, 특징점 검출 알고리즘인 Scale Invarient Feature Transfom(SIFT)를 이용하여 특징점의 위치를 살펴보도록 한다. edge detection 알고리즘으로는 Canny edge detection과 Prewitt edge detection을 적용하기로 한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.90-97
• /
• 2007

For a highly reliable fingerprint recognition system, the precise and accurate feature extraction is indispensable. In this paper, We propose a highly efficient crease extraction method, which can improve the accuracy of feature extraction within the fingerprint image. The proposed method applies the 1-dimensional directional slit for each pixel in fingerprint image. And then it calculates the average grey level and variance to determine whether the current pixel composes the crease, and estimates the direction of crease. Once the direction of every pixel in crease candidate area is estimated, it is decomposed into 8 different images depending on their direction. From the 8 directional images, the crease clusters are estimated by utilizing the property of crease area. The proposed method finally extracts the crease from the crease clusters estimated from directional images. In conclusion, the proposed method highly improved the accuracy of overall feature extraction by accurate and precise extraction of the crease from fingerprint image.

• The Journal of the Korea Contents Association
• /
• v.5 no.5
• /
• pp.152-158
• /
• 2005

By using a combination of different feature sets extracted from input character patterns, we can improve the character recognition system performance. To reduce the dimensionality of the combined feature vector, we conduct the feature selection. This paper proposes a general framework for the feature combination and selection for character recognition problems. It also presents a specific design for the handwritten numeral recognition. Tn the design, DDD and AGD feature sets are extracted from handwritten numeral patterns, and a genetic algorithm is used for the feature selection. Experimental result showed a significant accuracy improvement by about 0.7% for the CENPARMI handwrittennumeral database.