• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.31-39
• /
• 2018

Recently, there has been active studies to provide a user-friendly interface in a virtual reality environment by recognizing user hand gestures based on deep learning. However, most studies use separate sensors to obtain hand information or go through pre-process for efficient learning. It also fails to take into account changes in the external environment, such as changes in lighting or some of its hands being obscured. This paper proposes a hand gesture recognition method based on deep learning that is strong in external environments without the need for pre-process of RGB images obtained from general webcam. In this paper we improve the VGGNet and the GoogLeNet structures and compared the performance of each structure. The VGGNet and the GoogLeNet structures presented in this paper showed a recognition rate of 93.88% and 93.75%, respectively, based on data containing dim, partially obscured, or partially out-of-sight hand images. In terms of memory and speed, the GoogLeNet used about 3 times less memory than the VGGNet, and its processing speed was 10 times better. The results of this paper can be processed in real-time and used as a hand gesture interface in various areas such as games, education, and medical services in a virtual reality environment.

• Journal of the Institute of Convergence Signal Processing
• /
• v.9 no.1
• /
• pp.18-23
• /
• 2008

In this paper, we propose the input image selection-method to improve the reconstructed high-resolution (HR) image quality. To obtain ideal super-resolution (SR) reconstruction image, all input images are well-registered. However, the registration is not ideal in practice. Due to this reason, the selection of input images with low registration error (RE) is more important than the number of input images in order to obtain good quality of a HR image. The suitability of a candidate input image can be determined by using statistical and restricted registration properties. Therefore, we propose the proper candidate input Low Resolution(LR) image selection-method as a pre-processing for the SR reconstruction in automatic manner. In video sequences, all input images in specified region are allowed to use SR reconstruction as low-resolution input image and/or the reference image. The candidacy of an input LR image is decided by the threshold value and this threshold is calculated by using the maximum motion compensation error (MMCE) of the reference image. If the motion compensation error (MCE) of LR input image is in the range of 0 < MCE < MMCE then this LR input image is selected for SR reconstruction, else then LR input image are neglected. The optimal reference LR (ORLR) image is decided by comparing the number of the selected LR input (SLRI) images with each reference LR input (RLRI) image. Finally, we generate a HR image by using optimal reference LR image and selected LR images and by using the Hardie's interpolation method. This proposed algorithm is expected to improve the quality of SR without any user intervention.

• Journal of Broadcast Engineering
• /
• v.9 no.3
• /
• pp.185-195
• /
• 2004

This paper presents a multi-depth map fusion method for the 3D scene reconstruction. It fuses depth maps obtained from the stereo matching technique and the depth camera. Traditional stereo matching techniques that estimate disparities between two images often produce inaccurate depth map because of occlusion and homogeneous area. Depth map obtained from the depth camera is globally accurate but noisy and provide a limited depth range. In order to get better depth estimates than these two conventional techniques, we propose a depth map fusion method that fuses the multi-depth maps from stereo matching and the depth camera. We first obtain two depth maps generated from the stereo matching of 3-view images. Moreover, a depth map is obtained from the depth camera for the center-view image. After preprocessing each depth map, we select a depth value for each pixel among them. Simulation results showed a few improvements in some background legions by proposed fusion technique.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.306-310
• /
• 2002

In this paper, we realized a system that converts the Korean alphabet (Hangul) images, which are in any domain that is formed by the finger movement on the Hangul document, to the editable characters and then outputs them to the word editor. The domain of hand is separated from the sphere of document in the pre-process step of image. The centroid point of hand is drawn by the maximum circular movement method. After the system recognizes the hand with the circular pattern vector algorithm, finds out the position of finger by the distance spectrum and then draws out the sphere of selected character image by the finger movement to divide the characters into character units by applying the histogram between the Hangul characters. We standardized the characters of various sizes. We used the circular pattern vector algorithm that grafts on the fuzzy inference to divert the character images of the domain, which user wants, to the editable characters by comparing the characteristic vectors between the standard pattern character and the inputted character and by recognizing the character.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.270-279
• /
• 1997

The conversion of printed maps into computerized databases is an enormous task. Thus the automation of the conversion process is essential. Efficient computer representation of printed maps and line drawings depends on codes assigned to characters, symbols, and vector representation of the graphics. In many cases, maps are constructed in a number of layers, where each layer is printed in a distinct color, and it represents a subset of the map information. In order to properly represent the character layer from color map images, an interactive clustering and character extraction technique is proposed. Character is usually separated from graphics by extracting and classifying connected components in the image. But this procedure fails, when characters touch or overlap lines-something that occurs often in land register maps. By vectorizing line segments, the touched characters and numbers are extracted. The algorithm proposed in this paper is intended to contribute towards the solution of the color image clustering and touched character problem.

• The Journal of the Korea Contents Association
• /
• v.8 no.7
• /
• pp.1-8
• /
• 2008

In this paper, an algorithm to compensate the inter-view mismatch in the multi-view video according to the different characteristics of cameras is presented. Interview mismatches make it difficult to merge the multi-view images and decrease the coding performance. So, a preprocessing operation to compensate the mismatches is requisite in the multi-view video coding. It is shown that the mismatch in the outputs of multi-view cameras with different electro-optical transfer functions can be approximated with a linear model of a gain and an offset. In addition, a new algorithm for estimating and compensating the inter-view mismatch based on the detection of the overlapped region is presented. Experimental results using various rectified stereo images show that the proposed method compensates inter-view mismatches more accurately compared to the conventional approach.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.9
• /
• pp.1987-1992
• /
• 2010

This paper deals with the method of using the three dimensional characteristic information to classify the front environment in travelling by using the images captured by a CCD camera equipped on a mobile robot. The images detected by the three dimensional characteristic information is divided into the part of obstacles, the part of corners, and th part of doorways in a corridor. In designing the travelling path of a mobile robot, these three situations are used as an important information in the obstacle avoidance and optimal path computing. So, this paper proposes the method of deciding the travelling direction of a mobile robot with using input images based upon the suggested algorithm by preprocessing, and verified the validity of the image information which are detected as obstacles by the analysis through neural network.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.5 s.311
• /
• pp.37-44
• /
• 2006

In this paper, a new version of the ICM method(MICM, modified ICM) in which the contextual information is modelled by Markov random fields (MRF) is introduced. To extract the feature, a new local MRF model with a fitting block neighbourhood is proposed. This model selects contextual information not only from the relative intensity levels but also from the geometrically directional position of neighbouring cliques. Feature extraction depends on each block's contribution to the local variance. They discriminates it into several regions, for example context and background. Boundaries between these regions are also distinctive. The proposed algerian performs segmentation using directional block fitting procedure which confines merging to spatially adjacent elements and generates a partition such that pixels in unified cluster have a homogeneous intensity level. From experiment with ink rubbed copy images(Takbon, 拓本), this method is determined to be quite effective for feature identification. In particular, the new algorithm preserves the details of the images well without over- and under-smoothing problem occurring in general iterated conditional modes (ICM). And also, it may be noted that this method is applicable to the handwriting recognition.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.2
• /
• pp.102-113
• /
• 2014

This paper suggests a novel hardware architecture of a real-time rectification which is to remove vertical parallax of an image occurred in the pre-processing stage of stereo matching. As an off-line step, Matlab Toolbox which was designed by J.Y Bouguet, was used to calculate calibration parameter of the image. Then, based on the Heikkila and Silven's algorithm, rectification hardware was designed. At this point, to enhance the precision of the rectified image, floating-point unit was generated by using Xilinx Core Generator. And, we confirmed that proposed hardware design had higher precision compared to other designs while having the ability to do rectification in real-time.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.6
• /
• pp.43-50
• /
• 2007

In this paper we propose a method that identifies users at H.264 streaming using watermarking with fingerprints. The watermark can efficiently reduce the potential danger of forgery or alteration. Especially a biometric watermark has various advantages. Among entire biometric characteristics, the fingerprint is the most convenient and economical. In this paper we propose a novel fingerprint-based watermarking technique that can survive under very low bit-rate compression. The proposed algorithm consists of enhancement of a fingerprint image, the watermark generation using the extracted feature coordinates, watermark insertion using discrete wavelet transform, and authentication. The proposed algorithm can achieve robust watermark extraction against 0.264 compressed videos.