• Journal of Digital Policy
• /
• v.3 no.3
• /
• pp.9-14
• /
• 2024

In this paper, proposes a method using a multi block structure composed of residual blocks with adaptive weights to improve the quality of results in single image super resolution. In the process of generating super resolution images using deep learning, the most critical factor for enhancing quality is feature extraction and application. While extracting various features is essential for restoring fine details that have been lost due to low resolution, issues such as increased network depth and complexity pose challenges in practical implementation. Therefore, the feature extraction process was structured efficiently, and the application process was improved to enhance quality. To achieve this, a multi block structure was designed after the initial feature extraction, with nested residual blocks inside each block, where adaptive weights were applied. Additionally, for final high resolution reconstruction, a multi kernel image reconstruction process was employed, further improving the quality of the results. The performance of the proposed method was evaluated by calculating PSNR and SSIM values compared to the original image, and its superiority was demonstrated through comparisons with existing algorithms.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.3 s.345
• /
• pp.1-9
• /
• 2006

In this paper, we propose a MIMO-OFDMA (Multi Input Multi Output-Orthogonal Frequency Division Multiple Access) system based on beamforming for performance improvement of downlink real-time traffic transmission in harsh channel conditions with low CIR (Carrier-to-Interference Ratio). In the proposed system, we first consider the M-GTA-SBA (Modified-Grouped Transmit Antenna-Simple Bit Allocation) using effective CSI (Channel State Information) calculation procedure based on spatial resource grouping, which is adequate for the combination of MRT (Maximum Ratio Transmission) in the transmitter and MRC (Maximum Ratio Combining) in the receiver. In addition, to reduce feedback information for the beamforming, we also apply QEGT (Quantized Equal Gain Transmission) based on quantization of amplitudes and phases of beam weights. Furthermore, considering multi-user environments, we propose the P-SRA (Proposed-Simple Resource Allocation) algorithm for fair and efficient resource allocation. Simulation results reveal that the proposed MIMO-OFDMA system achieves significant improvement of spectral efficiency in low CRI region as compared to a typical open-loop MIMO-OFDMA system using pseudo-orthogonal space time block code and H-ARQ IR (Hybrid-Automatic Repeat Request Incremental Redundancy).

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.451-454
• /
• 2001

본 논문에서는 그룹화 블록스네이크와 영상분할을 이용하여 다차선을 검출하고 컬러 정보를 기반으로 차량 후면에 위치하는 미등과 브레이크등을 인식, 저속 주행환경에서의 다차선 및 전방차량을 인식하는 알고리즘을 제안하였다. 제안한 알고리즘에서는 기울기 값과 명암도 값으로 기초 블록을 얻은 뒤, 차선의 가능성이 큰 블록을 탐색하여 영상분할을 시행한다. 영상 분할에서 잡음 블록들을 제거하여 차선일 가능성이 가장 높은 블록들만을 검출하고, 그룹화 블록스네이크를 이용하여 차선을 검출하도록 하였다. 또한 전방 차량인식을 위해 미등과 브레이크등의 컬러 특징을 이용하여 후보 영역을 분할한 후, 미등과 브레이크등의 패턴의 기하학적 특징과 위치적 특징을 이용하여 한 쌍의 미등 혹은 브레이크등을 탐지하도록 하였다. 탐지된 양쪽 등의 위치정보를 이용하여 전방차량의 위치를 측정 할 수 있다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.11
• /
• pp.2264-2275
• /
• 1994

In this paper, image compression based on neural networks is presented with block classification and coding. Multilayer neural networks with error back-propagation learning algorithm are used to transform the normalized image date into the compressed hidden values by reducing spatial redundancies. Image compression can basically be achieved with smaller number of hidden neurons than the numbers of input and output neurons. Additionally, the image blocks can be grouped for adaptive compression rates depending on the characteristics of the complexity of the blocks in accordance with the sensitivity of the human visual system(HVS). The quantized output of the hidden neuron can also be entropy coded for an efficient transmission. In computer simulation, this approach lie in the good performances even with images outside the training set and about 25:1 compression rate was achieved using the entropy coding without much degradation of the reconstructed images.