• 대한전자공학회논문지
• /
• 제27권1호
• /
• pp.137-142
• /
• 1990

A theory for the synthesis of a SDF including the filter modulation is suggested. In the filter synthesis, the iteration equation was used to iterate trial solution vectors. A computer simulation of the fSDF method using threshold binary images of the flight objects over a range of aspect angles was performed for POF and BPOF. The constructed fSDF filters are capable of obtaining the specified peak correlation response within a 1.7%-4.0% error range, after several iterations. However, the conventional pSDF/POFs, BPOFs are not. The results indicate POFs and BPOs can be made to perform well for distortion invariant optical pattern recognition using the fSDF method.

• 전자공학회논문지B
• /
• 제31B권4호
• /
• pp.1-8
• /
• 1994

In this paper, we propose an efficient two-step pattern matching method which promises shape distortion-tolerant recognition of handwritten of handwritten Hangul syllables. In the first step, nonlinear shape normalization is carried out to compensate for global shape distortions in handwritten characters, then a preliminary classification based on simple pattern matching is performed. In the next step, nonlinear pattern matching which achieves best matching between input and reference pattern is carried out to compensate for local shape distortions, then detailed classification which determines the final result of classification is performed. As the performance of recognition systems based on pattern matching methods is greatly effected by the quality of reference patterns. we construct reference patterns by combining the proposed nonlinear pattern matching method with a well-known averaging techniques. Experimental results reveal that recognition performance is greatly improved by the proposed two-step pattern matching method and the reference pattern construction scheme.

• Asian-Australasian Journal of Animal Sciences
• /
• 제18권6호
• /
• pp.868-872
• /
• 2005

Individual management of the animal is the first step towards reaching the goal of precision livestock farming that aids animal welfare. Accurate recognition of each individual animal is important for precise management. Electronic identification of cattle, usually referred to as RFID (Radio Frequency Identification), has many advantages for farm management. In practice, however, RFID implementations can cause several problems. Reading speed and distance must be optimized for specific applications. Image processing is more effective than RFID for the development of precision farming system in livestock. Therefore, the aim of this paper is to attempt the identification of cattle by using image processing. The majority of the research on the identification of cattle by using image processing has been for the black-and-white patterns of the Holstein. But, native Japanese and Korean cattle do not have a consistent pattern on the body, so that identification by pattern is impossible. This research aims to identify to Japanese black cattle, which does not have a black-white pattern on the body, by using image processing and a neural network algorithm. 12 Japanese black cattle were tested. Values of input parameter were calculated by using the face image values of 12 cows. The face was identified by the associate neural memory algorithm, and the algorithm was verified by the transformed face image, for example, of brightness, distortion, noise and angle. As a result, there was difference due to a transformation ratio of the brightness, distortion, noise, and angle. The algorithm could identify 100% in the range from -30 to +30 degrees of brightness, -20 to +40 degrees of distortion, 0 to 60% of noise and -20 to +30 degree of angle transformed images.

• 한국산업정보학회논문지
• /
• 제27권3호
• /
• pp.11-20
• /
• 2022

현재 광고 분야 등에 널리 사용되고 있는 흑백 QR코드의 정보 저장 용량을 증가시키기 위해 칼라 QR코드에 대한 연구가 활발히 진행되고 있다. 그러나 칼라 QR코드는 프린팅 또는 스캐닝 과정에 의해 복재가 될 수 있으며, 이 과정에서 불충분한 조도에 의한 색상 왜곡과 잡음, 카메라의 낮은 해상도와 기하학적 변형의 가능성이 있다. 이러한 일련의 복합적인 과정들은 품질 저하와 인식률 저하를 초래한다. 이러한 문제점을 극복하기 위해 본 논문에서는 칼라 QR코드에 패턴 삽입을 고려하고, 이를 위한 효과적인 인식 방법을 제안한다. 또한, 제안한 방법을 통해 기존에 다루어진 대표적인 패턴을 도입하고, 인식률 측면에서 실험을 수행하여 그 결과를 비교 분석한다. 즉, 인식과정에 있어서 쉽게 초래되는 가우시안 잡음과 블러링, 기하학적 변형 등의 잡음을 고려하여 성능을 비교 분석한다. 다양한 실험을 통해 가우시안 잡음과 블러 측면에서 단순한 패턴의 칼라 QR코드가 우수한 성능을 보이는 것을 확인할 수 있다.

• 대한가정학회지
• /
• 제50권1호
• /
• pp.29-39
• /
• 2012

The purpose of this research is to suggest a scarf design which reflects the traditional culture native to Korea by making use of the combined pattern of jokgakbo patchwork and ddeoksal(rice cake). For research methodology, the computer design programs of Adobe Illustrator CS3 and Adobe Photoshop CS3 were used along with the related literature. For the combined sets of motif pattern, the following were consider: first, a combination of jogakbo in square shape and chrysanthemum in a rice cake mold; second, a combination of radius jogakbo and geometrical pattern; third, a combination of vertical and horizontal forms of jogakbo and rice cake pattern; fourth, a combination of yeouijumunbo and butterfly pattern in rice cake mold. For the scarf design with these applications, technical skills such as repeat, rotation, symmetry, free setup, and distortion were used for the combination motif. In terms of the shape of the design, there are two, square and lengthwise tetragons.

• 치과방사선
• /
• 제21권2호
• /
• pp.415-423
• /
• 1991

This study was performed to evaluate the geometric standardization of periapical intraoral radiography. Image distortion was measured by analysing serial radiography obtained from dry skull using 5 types of bite registration device. After 16 weeks, the angular distortion of Pattern resin was 0.26±0.14 degree(Horizontal angle 0.17±0.14, Vertical angle 0.16±0.11) which was the lowest among the 5 registration device, and that of putty type Exaflex was 0.49±0.35 degree(Horizontal angle 0.42±0.35, Vertical angle 0.17±0.13) which was the highest. The mean amount of distortion variance of Tooth shade acrylic at each experimental period was 0.06±0.08 which was the lowest among the 5 registration device, and that of XCP alone was 0.ll±0.13 which was the highest.

• 디지털콘텐츠학회 논문지
• /
• 제3권2호
• /
• pp.197-209
• /
• 2002

다각형 기반 형상 부호화 기법은 정보량을 줄이기 위해 정점수를 줄일 경우, 근사 다각형 에지들 간의 연결이 원 윤곽선과는 다르게 급변함으로써 근사 오차가 급격히 증가한다. 반면에, 허용 왜곡을 작게 하여 근사 오차를 줄일 경우, 정점 수가 급격히 늘어나 정점을 부호화하기 위해 많은 정보량이 소요되는 문제점이 있다. 제안된 방법에 있어서, 부호기는 다각형 에지와 원 윤곽 세그먼트가 이루는 모양과 가장 유사한 왜곡 패턴의 유형을 찾아 부호화하고 복호기는 복호된 왜곡 패턴 정보로부터 근사 정점을 산술적으로 구해낸다. 이를 통해, 부가 정보의 증가를 효과적으로 억제시키면서도 전체적으로는 정점수가 늘어나 기존의 방법보다. 다각형 에지의 급속한 변화를 현저하게 완화시킴으로써 좀 더 부드러운 근사 모양 정보를 얻을 수 있다. 컴퓨터 시뮬레이션 결과를 통해 고찰할 때, 제안된 방법은 기존의 방식에 비해 왜곡이 적으며, 동일한 왜곡을 가지는 근사 모양 정보를 부호화하는데 필요한 비트량이 기존의 방법에 비해 대략 $10{\sim}20%$ 정도 감소함을 알 수 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.251-254
• /
• 2000

This paper proposes an enhanced algorithm for person identification system utilizing hand vein pattern. The conventional algorithm does not cope with distortion caused by image rotation caused by misplaced hands on the imaging device. A straightforward approach to consider the rotaional compensation required too much computational load, thus, we devised an approach to expect the rotation direction along with image translation, reducing the compuational requirement dramatically In this paper, we present the details of the algorithm with experimental results with the new algorithm.

• 전자공학회논문지B
• /
• 제29B권11호
• /
• pp.130-137
• /
• 1992

This paper presents the word recognition method using a neural-fuzzy pattern matching, in order to make a proper speech pattern for a spectrum sequence and to improve a recognition rate. In this method, a frequency variation is reduced by generating binary spectrum patterns through associative memory using a neural network, and a time variation is decreased by measuring the simillarity using a fuzzy pattern matching. For this method using binary spectrum patterns and logic algebraic operations to measure the simillarity, memory capacity and computation requirements are far less than those of DTW using a conventional distortion measure. To show the validity of the recognition performance for this method, word recognition experiments are carried out using 28 DDD city names and compared with DTW and a fuzzy pattern matching. The results show that our presented method is more excellent in the recognition performance than the other methods.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 A
• /
• pp.395-397
• /
• 2002

Recently, electric heating using midnight power has brought a rapid increase. Therefore, the increase of midnight power use has much influenced on midnight load pattern and share more than 20% of total midnight electricity consumption. Hence, the distortion of load by using midnight power apparatus is severe and made the usage pattern ineffective electricity usage pattern. This paper analyze the load pattern of midnight power apparatus and policies that can effectively build midnight load. In addition, it provides policies on shifting midnight power apparatus load.