• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.93-96
• /
• 2015

In this paper, we introduce a fire detection system using context-aware sensor. In existing weather and based on vision sensor of fire detection system case, acquired image through sensor of camera is extracting features about fire range as processing to convert HSI(Hue, Saturation, Intensity) model HSI which is color space can have durability in illumination changes. However, in this case, until a fire occurs wide range of sensing a fire in a single camera sensor, it is difficult to detect the occurrence of a fire. Additionally, the fire detection in complex situations as well as difficult to separate continuous boundary is set for the required area is difficult. In this paper, we propose an algorithm for real-time by using a temperature sensor, humidity, Co2, the flame presence information acquired and comparing the data based on multiple conditions, analyze and determine the weighting according to fire it. In addition, it is possible to differential management to intensive fire detection is required zone dividing the state of fire.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.5
• /
• pp.266-279
• /
• 2003

In this paper, we propose machine printed character recognition methods which utilize the character type information and divide the character clusters. The characters are subdivided into a total of seven types, of which six types are for Hangul according to the grapheme combination fashions and one type for English characters, numerals, and symbols. According to the character type, we separate input character image into several recognition units and recognize them by using the direction angle feature. The recognition for each character type is completed by combining recognition units which are recognized by neural networks respectively For combining a total of seven character recognizers, we implemented seven methods such as switching method, integrating method, and their several variants. As experimental results, we obtained 98.2% recognition rate of simple switching method, 90.54% of integrating one, and between 97.35% and 98.65% of five variants.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.86-97
• /
• 2011

This paper presents a novel algorithm to detect more accurate road lane with image sensor-based color classification and directional edge clustering. With treatment of road region and lane as a recognizable color object, the classification of color cues is processed by an iterative optimization of statistical parameters to each color object. These clustered color objects are taken into considerations as initial kernel information for color object detection and recognition. In order to improve the limitation of object classification using the color cues, the directional edge cures within the estimated region of interest in the lane boundary (ROI-LB) are clustered and combined. The results of color classification and directional edge clustering are optimally integrated to obtain the best detection of road lane. The characteristic of the proposed system is to obtain robust result to all real road environments because of using non-parametric approach based only on information of color and edge clustering without a particular mathematical road and lane model. The experimental results to the various real road environments and imaging conditions are presented to evaluate the effectiveness of the proposed method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.73-82
• /
• 2010

Door is an important object to understand given environment and it could be used to distinguish with corridors and rooms. Doors are widely used natural landmark in mobile robotics for localization and navigation. However, almost algorithm for door recognition with camera is difficult real-time application because feature extraction and matching have heavy computation complexity. This paper proposes a method to recognize a door in corridor. First, we extract distinguished lines which have high possibility to comprise of door using Hough transformation. Then, we detect candidate of door region by applying previously extracted lines to first-stage visual fuzzy system. Finally, door regions are determined by verifying knob region in candidate of door region suing second-stage visual fuzzy system.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.802-816
• /
• 2010

To create gesture from a new text input is an important problem in computer games and virtual reality. Recently, there is increasing interest in gesture stylization to imitate the gestures of celebrities, such as announcer. However, no attempt has been made so far to stylize a gestures using emotion such as happiness and sadness. Previous researches have not focused on real-time algorithm. In this paper, we present a system to automatically make gesture animation from SMS text and stylize the gesture from emotion. A key feature of this system is a real-time algorithm to combine gestures with emotion. Because the system's platform is a mobile phone, we distribute much works on the server and client. Therefore, the system guarantees real-time performance of 15 or more frames per second. At first, we extract words to express feelings and its corresponding gesture from Disney video and model the gesture statistically. And then, we introduce the theory of Laban Movement Analysis to combine gesture and emotion. In order to evaluate our system, we analyze user survey responses.

• Journal of Broadcast Engineering
• /
• v.15 no.5
• /
• pp.697-702
• /
• 2010

Contour artifact is known as the unintentional result of quantizing a flat area that has smooth gradients. In this letter, a decontouring algorithm is proposed to efficiently remove false contours that occur in typical block-based video coding applications. First, the algorithm goes through a refinement stage to determine candidate blocks probably having noticeable false contours with different kinds of features in a block. Then, pseudo-random noise masking is applied to those blocks to mitigate the contour artifacts. This block-based selective decontouring can efficiently remove the unnecessary processing of those blocks that have no false contour, which incidentally ensures a minor penalty in visual quality and computational complexity. The proposed algorithm was demonstrated, integrated into H.264/AVC, that visual quality can be significantly enhanced with an ignorable rate-distortion (RD) loss and an minor increase in computational complexity.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.4
• /
• pp.249-255
• /
• 2004

In fingerprint verification and identification, fingerprint and background region should be segmented. For this purpose, most systems obtain variance of brightness of X and Y direction using Sobel mask. To decide given local region is background or not, the variance is compared with a certain threshold. Although this method is simple, most fingerprint image does not separated with two region of fingerprint and background region. In this paper, we presented a new segmentation algorithm based on Run-Length Connectivity analysis. For a given binary image after thresholding, suggested algorithm calculates RL of X and Y direction. Until the given image is segmented to two regions, small run region is successively inverted. Experimental result show that this algorithm effectively separates fingerprint region and background region.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.5C
• /
• pp.505-513
• /
• 2009

This paper proposes a real-time foreground segmentation and background substitution method for protecting the privacy on visual communication. Previous works on this topic have some problems with the color and shape of foreground and the capture device such as stereo camera. we provide a solution which can segment the foreground in real-time using fixed mono camera. For improving the performance of a foreground extraction, we propose the Temporal Foreground Probability Model (TFPM) by modeling temporal information of a video. Also we provide an boundary processing method for natural and smooth synthesizing that using alpha matte and simple post-processing method.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.2
• /
• pp.115-122
• /
• 2017

This paper proposes a deep learning algorithm based sign detection and recognition system for the blind. The proposed system is composed of sign detection stage and sign recognition stage. In the sign detection stage, aggregated channel features are extracted and AdaBoost classifier is applied to detect regions of interest of the sign. In the sign recognition stage, convolutional neural network is applied to recognize the regions of interest of the sign. In this paper, the AdaBoost classifier is designed to decrease the number of undetected signs, and deep learning algorithm is used to increase recognition accuracy and which leads to removing false positives which occur in the sign detection stage. Based on our experiments, proposed method efficiently decreases the number of false positives compared with other methods.