• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.252-259
• /
• 2000

In this paper, we propose a Fuzzy Classifier System(FCS) to find a set of fuzzy rules which can carry out the edge detection of a image. The FCS is based on the fuzzy logic system combined with machine learning. Therefore the antecedent and consequent of a classifier in FCS are the same as those of a fuzzy rule. There are two different approaches, Michigan and Pittsburgh approaches, to acquire appropriate fuzzy rules by evolutionary computation. In this paper, we use the Michigan style in which a single fuzzy if-then rule is coded as an individual. Also the FCS employs the Genetic Algorithms to generate new rules and modify rules when performance of the system needs to be improved. The proposed method is evaluated by applying it to the edge detection of a gray-level image that is a pre-processing step of the computer vision. the differences of average gray-level of the each vertical/horizontal arrays of neighborhood pixels are represented into fuzzy sets, and then the center pixel is decided whether it is edge pixel or not using fuzzy if-then rules. We compare the resulting image with a conventional edge image obtained by the other edge detection method such as Sobel edge detection.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.132-145
• /
• 2009

We present the framework for JND based Illumination and Color Restoration Using Edge-preserving filter for restoring distorted images taken under the arbitrary lighting conditions. The proposed method is effective for appropriate illumination compensation, vivid color restoration, artifacts suppression, automatic parameter estimation, and low computation cost for HW implementation. We show the efficiency of the mean shift filter and sigma filter for illumination compensation with small spread parameter while considering the processing time and removing the artifacts such as HALO and noise amplification. The suggested CRF (color restoration filter) can restore the natural color and correct color distortion artifact more perceptually compared with current solutions. For the automatic processing, the image statistics analysis finds suitable parameter using JND and all constants are pre-defined. We also introduce the ROI-based parameter estimation dealing with small shadow area against spacious well-exposed background in an image for the touch-screen camera. The object evaluation is performed by CMC, CIEde2000, PSNR, SSIM, and 3D CIELAB gamut with state-of-the-art research and existing commercial solutions.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.417-424
• /
• 2010

In this paper the real-time face region was detected by suggesting the rectangular feature-based classifier and the robust detection algorithm that satisfied the efficiency of computation and detection performance was suggested. By using the detected face region as a recognition input image, in this paper the face recognition method combined with PCA and the multi-layer network which is one of the intelligent classification was suggested and its performance was evaluated. As a pre-processing algorithm of input face image, this method computes the eigenface through PCA and expresses the training images with it as a fundamental vector. Each image takes the set of weights for the fundamental vector as a feature vector and it reduces the dimension of image at the same time, and then the face recognition is performed by inputting the multi-layer neural network.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.6C
• /
• pp.601-609
• /
• 2002

The efficient Viterbi decoder that supports full data-rate output of DAB system was proposed. Viterbi decoder consumes lots of computational load and should be designed to be fast specific hardware. In this paper, SST scheme was adopted for Viterbi decoder with puncturing to reduced the power consumption. Puncturing vector tables are modified and re-arranged to be designed by a hardwired logic to save the system area. New re-scaling scheme which uses the fact that the difference of the maximum and minimum of the path metric values is bounded is proposed. The proposed re-scaling scheme optimizes the wordlength of path metric memory and greatly reduces the computational load for re-scaling by controlling MSB of path metric memory. Another saving of computation is done by proposed algorithm for branch metric calculation, which makes use of pre-calculated metric values. The designed Viterbi decoder was synthesized using SAMSUNG 0.35$\mu$ standard cell library and occupied small area and showed lower power consumption.

• Journal of KIISE:Databases
• /
• v.32 no.2
• /
• pp.129-141
• /
• 2005

Although spatio-temporal databases have received considerable attention recently, there has been little work on processing range sum queries on the historical records of moving objects despite their importance. Since to answer range sum queries, the direct access to a huge amount of data incurs prohibitive computation cost, materialization techniques based on existing index structures are recently suggested. A simple but effective solution is to apply the materialization technique to the MVR-tree known as the most efficient structure for window queries with spatio-temporal conditions. However, the MVR-tree has a difficulty in maintaining pre-aggregated results inside its internal nodes due to cyclic paths between nodes. Aggregate structures based on other index structures such as the HR-tree and the 3DR-tree do not provide satisfactory query performance. In this paper, we propose a new indexing technique called the Adaptive Partitioned Aggregate R-Tree (APART) and query processing algorithms to efficiently process range sum queries in many situations. Experimental results show that the performance of the APART is typically above 2 times better than existing aggregate structures in a wide range of scenarios.

• Journal of Broadcast Engineering
• /
• v.9 no.4 s.25
• /
• pp.434-445
• /
• 2004

Motion Estimation is an essential module in video encoders based on international standards such as H.263 and MPEG. Many fast motion estimation algorithms have been proposed in order to reduce the computational complexity of a well-known full search algorithms(FS). However, these fast algorithms can not work efficiently in DSP processors recently developed for video processing. To solve for this. we propose an efficient motion estimation scheme optimized in the DSP processor like Philips TM1300. A motion vector predictor is pre-estimated and a small search range is chosen in the proposed scheme using strong motion vector correlation between a current macro block (MB) and its neighboring MB's to reduce computation time. An MPEG-4 SP@L3(Simple Profile at Level 3) encoding system is implemented in Philips TM1300 to verify the effectiveness of the proposed method. In that processor, we can achieve better performance using our method than other conventional ones while keeping visual quality as good as that of the FS.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.843-845
• /
• 2003

Shortest Path Problems are among the most studied network flow optimization problems, with interesting applications in various fields. One such field is the route determination service, where various kinds of shortest path problems need to be solved in location-based service. Our research aim is to propose a route technique in real-time locationbased service (LBS) environments according to user’s route preferences such as shortest, fastest, easiest and so on. Turn costs modeling and computation are important procedures in route planning. There are major two kinds of cost parameters in route planning. One is static cost parameter which can be pre-computed such as distance and number of traffic-lane. The other is dynamic cost parameter which can be computed in run-time such as number of turns and risk of congestion. In this paper, we propose a new cost modeling method for turn costs which are traditionally attached to edges in a graph. Our proposed route determination technique also has an advantage that can provide service interoperability by implementing XML web service for the OpenLS route determination service specification. In addition to, describing the details of our shortest path algorithms, we present a location-based service system by using proposed routing algorithms.

• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.489-495
• /
• 2010

Hyperspectral imaging obtains information with a wider wavelength range a large number of bands. However, a high correlation between each band, computation cost, and noise causes inaccurate results in cases of no pre-processing. The noises of band extraction and elimination positively necessary in hyperspectral imaging. Since the previous studies have used a characteristic the whole image, a local characteristic of the image is considered for the noise band extraction. In this study, the Quadtree, which is a data structure algorithm. and the fractal dimension are adopted for noise band extraction in Hyperion images. The fractal dimensions of the segments divided by the Quadtree structure are calculated, and variation is used. We focused on the extraction of random noise bands in Hyperion images and compared them with the reference data made by visual decisions. The proposed algorithm extracts the most bands, including random noises. It is possible to eliminate more than 30 noise bands, regardless of images.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.3
• /
• pp.323-330
• /
• 2021

Recently, the advantages of high-speed arithmetic in quantum computers have been known, and interest in quantum circuits utilizing qubits has increased. The Grover algorithm is a quantum algorithm that can reduce n-bit security level symmetric key cryptography and hash functions to n/2-bit security level. Since the Grover algorithm work on quantum computers, the symmetric cryptographic technique and hash function to be applied must be implemented in a quantum circuit. This is the motivation for these studies, and recently, research on implementing symmetric cryptographic technique and hash functions in quantum circuits has been actively conducted. However, at present, in a situation where the number of qubits is limited, we are interested in implementing with the minimum number of qubits and aim for efficient implementation. In this paper, the domestic hash function LSH is efficiently implemented using qubits recycling and pre-computation. Also, major operations such as Mix and Final were efficiently implemented as quantum circuits using ProjectQ, a quantum programming tool provided by IBM, and the quantum resources required for this were evaluated.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.