• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2013

In this paper, we propose an algorithm to detect scale invariant object from IR image obtained in the sea environment. We create horizontal edge (HL), vertical edge (LH), diagonal edge (HH) of images through 2-D discrete Haar wavelet transform (DHWT) technique after noise reduction using morphology operations. Considering the sea environment, Gaussian blurring to the horizontal and vertical edge images at each level of wavelet is performed and then saliency map is generated by multiplying the blurred horizontal and vertical edges and combining into one image. Then we extract object candidate region by performing a binarization to saliency map. A small area in the object candidate region are removed to produce final result. Experiment results show the feasibility of the proposed algorithm.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.700-703
• /
• 2016

OpenCV(Open Computer Vision)에서 제공하는 얼굴 검출 알고리즘은 Haar-like feature와 Cascade 방식을 이용하여 얼굴의 패턴을 찾아내 얼굴을 검출한다. 그러나 우연히 얼굴이 아닌 곳이 얼굴과 유사한 패턴일 경우, 얼굴로 인식하는 오류를 범하게 된다. 따라서 본 논문은 MCT(Modified Census Transform)와 신경망을 이용하여 잘못된 얼굴 검출 영역을 감소시키는 알고리즘을 제안한다. MCT는 다양한 조명 조건에서도 강인한 얼굴 영상의 지역적 구조 특징을 추출하기 위하여 사용되고, 신경망 알고리즘은 Haar-Cascade 알고리즘의 얼굴 검출 방법으로 검출된 영역이 실제로 얼굴인지 아닌지를 판단하기 위하여 사용된다. 실험에서 사용된 6개의 데이터들은 인터넷에서 수집한 것으로서, Haar-Cascade 알고리즘의 얼굴 검출 방법으로 얼굴을 검출하였을 때 오검출된 영역이 1개 이상 존재한다. 본 논문에서 제안한 알고리즘으로 실험한 결과, Haar-Cascade 알고리즘의 얼굴 검출 방법에 비하여 오검출된 영역이 감소된 것을 확인할 수 있었다.

• Journal of Digital Convergence
• /
• v.11 no.2
• /
• pp.243-248
• /
• 2013

This paper proposes an effective method using Adaptive Boosting to track a person's head in complex background. By only one way to feature extraction methods are not sufficient for modeling a person's head. Therefore, the method proposed in this paper, several feature extraction methods for the accuracy of the detection head running at the same time. Feature Extraction for the imaging of the head was extracted using sub-region and Haar wavelet transform. Sub-region represents the local characteristics of the head, Haar wavelet transform can indicate the frequency characteristics of face. Therefore, if we use them to extract the features of face, effective modeling is possible. In the proposed method to track down the man's head from the input video in real time, we ues the results after learning Harr-wavelet characteristics of the three types using AdaBoosting algorithm. Originally the AdaBoosting algorithm, there is a very long learning time, if learning data was changes, and then it is need to be performed learning again. In order to overcome this shortcoming, in this research propose efficient method using cascade AdaBoosting. This method reduces the learning time for the imaging of the head, and can respond effectively to changes in the learning data. The proposed method generated classifier with excellent performance using less learning time and learning data. In addition, this method accurately detect and track head of person from a variety of head data in real-time video images.

• Journal of Korean Clinical Health Science
• /
• v.4 no.4
• /
• pp.756-761
• /
• 2016

Purpose. Noise occurs at measuring Electoretinogram(ERG) signals as the other bio-signal measurement. It is compared the denoising performance according to the mother function of wavelet transforms. Methods. The ERG signal that generated power supply noise and white noise was used as a sampling signal. The noise of ERG signal was filtered by using haar, db7, bior mother function. The filtering performance of each mother functions was compared using Fourier transform spectrum and SNR(signal to noise ratio). Results. In the haar functioin, the result of the Fourier transform spectrum was that the power supply noise is removed and the white noise performance is not good. The SNR was 27.0404. In the db7 function, the results of Fourier transform spectrum was that the power supply noise is removed and the white noise performance is good. The SNR was 35.1729. In the db7 function, the results of Fourier transform spectrum was that the power supply noise is removed and the white noise performance is the bset. The SNR was 35.4445. Conclusions. The db7, bior function was good results in power supply noise and white noise filtered. The bior function is suitable for filtering noise of the ERG signal.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.1
• /
• pp.83-95
• /
• 1999

Wavelet transform has localization for time or frequency. It is useful to analyze a nonstationary signal. Basic function on wavelet transform is generated dilating and translating the original wavelet(mother wavelet). In this paper, time-frequency analysis method using linear combination wavelet transform is proposed. And it is applied to diagnostic monitoring system using the proposed linear combination wavelet transform. The stationary and nonstationary signal is used linear chirp signal, fan noise signal, a sinusoid signal from revolution body, electronic signal. Transform applied to signal analysis use fast Fourier transform (FFT), Daubechies, Haar and proposed linear combination method. The result of time-frequency analysis using linear combination wavelet transform is suited for portraying nonstationary time signal as well as stationary signal. Also the diagnostic monitoring system carry out the effective the signal analysis.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.8
• /
• pp.839-844
• /
• 2009

In this paper, a real-time eye tracking method using fast face detection is proposed. Most of the current eye tracking systems have operational limitations due to sensors, complicated backgrounds, and uneven lighting condition. It also suffers from slow response time which is not proper for a real-time application. The tracking performance is low under complicated background and uneven lighting condition. The proposed algorithm detects face region from acquired image using elliptic Hough transform followed by eye detection within the detected face region using Haar-like features. In order to reduce the computation time in tracking eyes, the algorithm predicts next frame search region from the information obtained in the current frame. Experiments through simulation show good performance of the proposed method under various environments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2641-2646
• /
• 2011

In this paper, we studied that the EZW algorithm based in HWT was proposed effective compression technique of wavelet transformed image. The proposed Haar-EZW algorithm is that image was coding by zerotree coding technique using self-similarity of HWT coefficients. If the HWT coefficient is larger than the threshold, that is coding to POS. If the HWT coefficient is smaller than the threshold, that is coding to NEG. If the HWT coefficient is larger than the root of zerotree, that is coding to ZTR. If the HWT coefficient is smaller then the threshold, and if that is not the root of zerotree, that is coding to IZ. This process is repeated until all the HWT coefficients have been encoded completely. This paper is compared Haar-EZW algorithm with Daubechies and Antonini. As the results of compare, it is shown that the PSNR of the Haar-EZW algorithm is better than Daubechies's and Antonini's.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.1
• /
• pp.658-665
• /
• 2015

In the production of medical images, noise reduction and contrast enhancement are important methods to increase qualities of processing results. By using the edge-based denoising and adaptive nonlinear histogram stretching, a novel medical image enhancement algorithm is proposed. First, a medical image is decomposed by wavelet transform, and then all high frequency sub-images are decomposed by Haar transform. At the same time, edge detection with Sobel operator is performed. Second, noises in all high frequency sub-images are reduced by edge-based soft-threshold method. Third, high frequency coefficients are further enhanced by adaptive weight values in different sub-images. Finally, an adaptive nonlinear histogram stretching method is applied to increase the contrast of resultant image. Experimental results show that the proposed algorithm can enhance a low contrast medical image while preserving edges effectively without blurring the details.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.2
• /
• pp.1-10
• /
• 2003

This paper presents an efficient method for image segmentation based on a multiresolution application of a wavelet transform and watershed segmentation algorithm. The procedure toward complete segmentation consists of four steps: pyramid representation, image segmentation, region merging and region projection. First, pyramid representation creates multiresolution images using a wavelet transform. Second, image segmentation segments the lowest-resolution image of the pyramid using a watershed segmentation algorithm. Third, region merging merges the segmented regions using the third-order moment values of the wavelet coefficients. Finally, the segmented low-resolution image with label is projected into a full-resolution image (original image) by inverse wavelet transform. Experimental results of the presented method can be applied to the segmentation of noise or degraded images as well as reduce over-segmentation.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.113-118
• /
• 2024

In this paper, we propose an optimal wavelet in a system for canceling background noise of acoustic signals. This system performed Discrete Wavelet Transform(DWT) instead of the existing Short Time Fourier Transform(STFT) and then improved noise cancellation performance through a deep learning process. DWT functions as a multi-resolution band-pass filter and obtains transformation parameters by time-shifting the parent wavelet at each level and using several wavelets whose sizes are scaled. Here, the noise cancellation performance of several wavelets was tested to select the most suitable mother wavelet for analyzing the speech. In this study, to verify the performance of the noise cancellation system for various wavelets, a simulation program using Tensorflow and Keras libraries was created and simulation experiments were performed for the four most commonly used wavelets. As a result of the experiment, the case of using Haar or Daubechies wavelets showed the best noise cancellation performance, and the mean square error(MSE) was significantly improved compared to the case of using other wavelets.