• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• Journal of Advanced Marine Engineering and Technology
• /
• v.28 no.4
• /
• pp.611-617
• /
• 2004

Pixel classification is one of basic image processing issues. The general characteristics of the pixels belonging to various classes are discussed and the radical principles of pixel classification are given. At the same time. a pixel classification scheme based on image direction measure is proposed. As a typical application instance of pixel classification, an adaptive multi-level median filter is presented. An image can be classified into two types of areas by using the direction information measure, that is. smooth area and edge area. Single direction multi-level median filter is used in smooth area. and multi-direction multi-level median filter is taken in the other type of area. What's more. an adaptive mechanism is proposed to adjust the type of the filters and the size of filter window. As a result. we get a better trade-off between preserving details and noise filtering.

• Journal of the Korea Society for Simulation
• /
• v.10 no.3
• /
• pp.59-70
• /
• 2001

Typical low-level image processing tasks require thousands of operations per pixel for each input image. Traditional general-purpose computers are not capable of performing such tasks in real time. Yet important features of traditional computers are not exploited by low-level image processing tasks. Since storage requirements are limited to a small number of low-precision integer values per pixel, large hierarchical memory systems are not necessary. The mismatch between the demands of low-level image processing tasks and the characteristics of conventional computers motivates investigation of alternative architectures. The structure of the tasks suggests employing an array of processing elements, one per pixel, sharing instructions issued by a single controller. In this paper we implemented various image processing filtering using the format converter. Also, we realized from conventional gray image process to color image process. This design method is based on realized the large processor-per-pixel array by integrated circuit technology This format converter design has control path implementation efficiently, and can be utilize the high technology without complicated controller hardware.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.9
• /
• pp.1672-1677
• /
• 2015

The multi-level holographic storage system can store more than one bit per pixel. In this paper, we introduce a 6-pixel 4-level modulation code and compare with 4-level 6/9 modulation code and 2/3 modulation code. The proposed 6-pixel modulation code has the minimum Euclidean distance 3. The 6-pixel modulation code is approximately 1dB better than the other modulation codes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.1
• /
• pp.175-182
• /
• 2013

The digitalization of sea level measurement recording which is recorded as analog type is useful for many related oceanology. In this paper, we propose a method which separates the graph area from a sea level measurement recording image. At first, a pixel that is regarded as the pixel which is included in the graph area is selected. Then, many background pixels are separated using the color of the selected pixel. In each vertical line, a pixel is determined as the pixel within the graph area and the graph area is separated from the image using that pixels. Experimental results show that the proposed method in this paper overcome drawbacks of the previous research and can separate the graph area which similar to the graph area of the original image.

• Journal of the Korean Society of Visualization
• /
• v.20 no.2
• /
• pp.78-85
• /
• 2022

In these days, the rapid development in prediction technology using artificial intelligent is being applied in a variety of engineering fields. Especially, dimensionality reduction technologies such as autoencoder and convolutional neural network have enabled the classification and regression of high-dimensional data. In particular, pixel level prediction technology enables semantic segmentation (fine-grained classification), or physical value prediction for each pixel such as depth or surface normal estimation. In this study, the pressure distribution of the ship's surface was estimated at the pixel level based on the artificial neural network. First, a potential flow analysis was performed on the hull form data generated by transforming the baseline hull form data to construct 429 datasets for learning. Thereafter, a neural network with a U-shape structure was configured to learn the pressure value at the node position of the pretreated hull form. As a result, for the hull form included in training set, it was confirmed that the neural network can make a good prediction for pressure distribution. But in case of container ship, which is not included and have different characteristics, the network couldn't give a reasonable result.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.11
• /
• pp.2555-2562
• /
• 2010

In this paper, we propose the method that extracts sea level measurements graph from the sea level measurements recording paper image with a little interaction. At first, a pixel that is included in the graph area is selected. Then, background pixels are automatically determined using the distance between a selected pixel and other pixels on LAB color space. In each vertical line, a pixel that is the nearest to the selected pixel on LAB color space is extracted and the graph area is determined using that pixels. Experimental results show that the sea level measurements graph can be extracted with a few interaction from the various sea level measurements recording paper images.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.10
• /
• pp.610-612
• /
• 2014

Mutilevel holographic data storage systems have a big advantage for capacity since it can store more than one bit per pixel. For instance, 2/3 modulation code stores 2/3(symbol/pixel) and 4/3(bit/pixel). Then it is about 1.3 bits per one pixel. In this paper, we propose two 4-level modulation codes, which have the minimum Euclidean distances of 3 and 4, respectively. The proposed codes perform better than random data. The performance of larger minimum distance code shows better than that of shorter one.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1998.11a
• /
• pp.137-140
• /
• 1998

An active-matrix LCD using thin film transistors (TFT) has been widely recognized as having potential for high-quality color flat-panel displays. Pixel-Design Array Simulation Tool (PDAST) was used to profoundly understand the gate si후미 distortion and pixel charging capability. which are the most critical limiting factors for high-quality TFT-LCDs. Since PDAST can simulate the gate, data and pixel voltages of a certain pixel on TFT array at any time and at any location on an array, the effect of the resistivity of gate line material on the pixel operations can be effectively analyzed. The gate signal delay, pixel charging ratio and level-shift of the pixel voltage were simulated with varying the parameters. The information obtained from this study could be utilized to design the larger area and finer image quality panel.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1998.06a
• /
• pp.321-324
• /
• 1998

Pixel-Design Array Simulation Tool(PDAST) was used to profoundly the gate signal distortion and pixel changing capability, which are the most critical limiting factors for high-quality TFT-LCDs. Since PDAST can simulate the gate, data and pixel voltages of a certain pixel on TFT array at any time and at any location on an array, the effect of the resistivity of gate line material on the pixel operations can be effectively analyzed. The gate signal delay, pixel charging ratio, level-shift of the pixel voltage were simulated with varying the resis5tivity of the gate line material. The information obtained from this study could be utilized to design the larger area and finer image quality panel.