• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.5
• /
• pp.1135-1140
• /
• 2007

This paper proposes an edge-based text region detection algorithm using the adaptive character-edge maps which are independent of the size of characters and the orientation of character string in natural images. First, labeled images are obtained from edge images and in order to search for characters, adaptive character-edge maps by way grammar are applied to labeled images. Next, selected label images are clustered as for distance of its neighbors. And then, text region candidates are obtained. Finally, text region candidates are verified by using the empirical rules and horizontal/vertical projection profiles based on the orientation of text region. As the results of experiments, a text region detection algorithm turned out to be robust in the matter of various character size, orientation, and the complexity of the background.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.11
• /
• pp.95-101
• /
• 1999

In this paper, we propose an adaptive method of tracking multiple moving objects using contour and features in surrounding conditions. We use an adaptive background model for robust processing in surrounding conditions. Object segmentation model detects pixels thresholded from local difference image between background and current image and extracts connected regions. Data association problem is solved by using feature extraction and object recognition model in searching window. We use Kalman filters for real-time tracking. The results of simulation show that the proposed method is good for tracking multiple moving objects in highway image sequences.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.2
• /
• pp.95-102
• /
• 2008

This paper proposes an adaptive speech enhancement system based on an auditory system to enhance speech that is degraded by various background noises. As such, the proposed system detects voiced and unvoiced sections, adaptively adjusts the coefficients for both the lateral inhibition and the amplitude component according to the detected sections for each input fame, then reduces the noise signal using a time-delay neural network. Based on measuring the signal-to-noise ratio, experiments confirm that the proposed system is effective for speech degraded by various noises.

• Journal of Information Technology Services
• /
• v.6 no.3
• /
• pp.241-249
• /
• 2007

This paper describes a real-time face tracking system using effective detector and Kalman filter. In the proposed system, an image is separated into a background and an object using a real-time updated face color for effective face detection. The face features are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted using Principal Component Analysis (PCA), and interpreted principal components are used for Support Vector Machine (SVM) that classifies the faces and non-faces. The moving face is traced with Kalman filter, which uses the static information of the detected faces and the dynamic information of changes between previous and current frames. The proposed system sets up an initial skin color and updates a region of a skin color through a moving skin color in a real time. It is possible to remove a background which has a similar color with a skin through updating a skin color in a real time. Also, as reducing a potential-face region using a skin color, the performance is increased up to 50% when comparing to the case of extracting features from a whole region.

• MALSORI
• /
• no.63
• /
• pp.125-137
• /
• 2007

Recently, many techniques have been proposed to improve the noise robustness for speaker verification. In this paper, we consider the feature recombination technique in multi-band approach. In the conventional feature recombination for speaker verification, to compute the likelihoods of speaker models or universal background model, whole feature components are used. This computation method is not effective in a view point of multi-band approach. To deal with non-effectiveness of the conventional feature recombination technique, we introduce a subband likelihood computation, and propose a modified feature recombination using subband likelihoods. In decision step of speaker verification system in noise environments, a few very low likelihood scores of a speaker model or universal background model cause speaker verification system to make wrong decision. To overcome this problem, a reliable feature selection method is proposed. The low likelihood scores of unreliable feature are substituted by likelihood scores of the adaptive noise model. In here, this adaptive noise model is estimated by maximum a posteriori adaptation technique using noise features directly obtained from noisy test speech. The proposed method using subband-based reliable feature selection obtains better performance than conventional feature recombination system. The error reduction rate is more than 31 % compared with the feature recombination-based speaker verification system.

• The KIPS Transactions:PartB
• /
• v.18B no.4
• /
• pp.173-180
• /
• 2011

This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version.

• Journal of IKEEE
• /
• v.20 no.1
• /
• pp.31-44
• /
• 2016

This paper presents a hole-filling algorithm based on extrapolating spatial-temporal background information used in view synthesis for free-viewpoint television. A new background codebook is constructed and updated in order to extract reliable temporal background information. In addition, an estimation of spatial local background values is conducted to discriminate an adaptive boundary between the background region and the foreground region as well as to update the information about the hole region. The holes then are filled by combining the spatial background information and the temporal background information. In addition, an exemplar-based inpainting technique is used to fill the rest of holes, in which a priority function using background-depth information is defined to determine the order in which the holes are filled. The experimental results demonstrated that the proposed algorithm outperformed the other comparative methods about average 0.3-0.6 dB, and that it synthesized satisfactory views regardless of video characteristics and type of hole region.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.6 no.1
• /
• pp.23-28
• /
• 2013

In this paper, background noise reduction method using dual microphone is proposed in mobile environment. Each Signal, reference and primary, would be replaced by microphone input signals, which were measured by reference and primary microphones, and then, noise reduction was performed using FDAF. After then, residual and background noise would be estimated and reduced by MMSE-LSA. For consistent noise reduction performance, result of VAD that could be caculated by PLD between two microphones was used.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.07a
• /
• pp.49-50
• /
• 2013

본 논문에서는 물체탐지를 위한 적응적 배경 생성 기법을 제안한다. 연속적으로 입력되는 영상들의 통계적 평균을 이용하여 배경을 생성하고 배경과 입력영상간의 차영상을 구하여 물체를 탐지한다. 탐지된 물체를 추척하여 일정시간이상 계속 정지해 있는 경우에는 그 물체영역을 배경으로 갱신하고, 이동 물체인 경우에는 배경 갱신에서 배제함으로써 지속적으로 물체를 탐지할 수 있도록 한다. 실험결과는 제안된 방법의 강건함을 보인다.

• Journal of Information Display
• /
• v.3 no.2
• /
• pp.19-25
• /
• 2002

In this paper, a new target extraction algorithm is proposed, in which the coordinates of target are obtained adaptively by using the difference image information and the optical BPEJTC(binary phase extraction joint transform correlator) with which the target object can be segmented from the input image and background noises are removed in the stereo vision system. First, the proposed algorithm extracts the target object by removing the background noises through the difference image information of the sequential left images and then controlls the pan/tilt and convergence angle of the stereo camera by using the coordinates of the target position obtained from the optical BPEJTC between the extracted target image and the input image. From some experimental results, it is found that the proposed algorithm can extract the target object from the input image with background noises and then, effectively track the target object in real time. Finally, a possibility of implementation of the adaptive stereo object tracking system by using the proposed algorithm is also suggested.