• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.6
• /
• pp.239-245
• /
• 2004

A hue-based noise-tolerant corner detector is proposed for the exact detection of the real corners in spite of the shadows and random noise. Based on the fact that the hue gradient at the border of the opaque objects' shadow is smaller than the intensity gradient in HSI (hue-saturation-intensity) color space, the effects of shadow are eliminated by introducing the hue-weighted combination of vector gradient to the proposed corner detector. Furthermore, the proposed corner detector is robust to random noise by offsetting the contribution to the corner candidate when the polarities of the color gradients of the pixel pairs are out of phase each other. Results of the experiment show that the proposed corner detector can effectively detect the real corners.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.390-395
• /
• 2009

The robustness of audio fingerprinting system in a noisy environment is a principal challenge in the area of content-based audio retrieval. The selected feature for the audio fingerprints must be robust in a noisy environment and the computational complexity of the searching algorithm must be low enough to be executed in real-time. The audio fingerprint proposed by Philips uses expanded hash table lookup to compensate errors introduced by noise. The expanded hash table lookup increases the searching complexity by a factor of 33 times the degree of expansion defined by the hamming distance. We propose a new method to improve noise robustness of audio fingerprinting in noise environment using predominant pitch which reduces the bit error of created hash values. The sub-fingerprint of our approach method is computed in each time frames of audio. The time frame is transformed into the frequency domain using FFT. The obtained audio spectrum is divided into 33 critical bands. Finally, the 32-bit hash value is computed by difference of each bands of energy. And only store bits near predominant pitch. Predominant pitches are extracted in each time frames of audio. The extraction process consists of harmonic enhancement, harmonic summation and selecting a band among critical bands.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.4
• /
• pp.407-414
• /
• 2002

The inherent reliability of a product is primarily determined in the design stage, and therefore, design engineers should be able to design reliability into the product in an efficient manner. Especially, the product should be designed such that its reliability is robust to various noise factors encountered in production and field environments. The Taguchi method can be effectively used for this purpose. However, there exist only a few attempts to integrate the Taguchi method with reliability design, and in addition, the existing works do not sufficiently consider the robustness and/or the distinction between noise and acceleration factors. This paper develops a unified approach to robust reliability design assuming that accelerated life tests are conducted at each combination of design and noise conditions. First, an experimental structure for assigning not only acceleration but also noise factors is presented. Second, the reliability at the use condition is estimated using the assumed accelerated life test model. Third, reliabilities are transformed into 'efforts' using an effort function which reflects the degree of difficulty involved in improving the reliability. Finally, an optimal setting of design parameters is determined based on the mean and standard deviation of the effort values. The above approach is illustrated with an example of a paper feeder design.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.10a
• /
• pp.295-298
• /
• 2018

The proposed paper proposes an algorithm that automatically extracts the region of interest using image processing techniques for medical images. In general, the robust boundary segmentation technique provides robust and accurate segmentation results in object boundaries with various noise and direction generated during image acquisition through optimal segmentation of the edges considering noise characteristics and directionality in noise images. In this paper, it is possible to apply adaptive filter type and size to the structural information of the image object and apply it to the boundary division of various object objects. In addition, it is possible to divide the boundary between various noise images such as an ultrasound image and an optical image.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.11a
• /
• pp.431-436
• /
• 2000

Adaptive feed forward control algorithms based largely upon LMS approach have developed in recent two decades, and they have been widely applied to practical sound and vibration control problems in the case of the reference signal is available. Feedforward control can be applied only when reference signals can be measured or regenerated, while feedback controllers are used to reduce; sound and vibration when reference signals are not available. In recent years, hybrid control schemes in which adaptive feed forward controllers are combined with feedback ones have been studied based on simulations and experiments. The results have shown that the hybrid control may have better control performances in convergence speed and steady state error than the single control schemes. Hybrid control has the advantages of improving stability and performance as well as the disturbance rejection property. However, little effort has been made to the analysis or interpretation of hybrid control systems. In this study, we discussed the feedback controller effects on the stability of feed forward control algorithm in the presence of uncertain error path and a simple example showed that a stable feedback controller could make the feedforward controller unstable. A design criterion of feedback controllers is proposed in order to guarantee the stability of feedforward algorithms in the presence of error paths with uncertainties.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.868-877
• /
• 2015

The barcode area extraction from images has been extensively studied, and existing methods exploit frequency characteristics or depend on the Hough transform (HT). However, the slantedness of the images and noise affects the performance of these approaches. Moreover, it is difficult to deal with the case where an image contains multiple barcodes. We therefore propose a barcode detection algorithm that is robust under such unfavorable conditions. The pre-processing step implements a probabilistic Hough transform to determine the areas that contain barcodes with a high probability, regardless of the slantedness, noise, and the number of instances. Then, a frequency component analysis extracts the barcodes. We successfully implemented the proposed system and performed a series of barcode extraction tests.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.175-182
• /
• 2010

In this paper, we propose a robust speech reinforcement technique to enhance the intelligibility of the degraded speech signal under the ambient noise environments based on soft decision scheme incorporating a speech absence probability (SAP) with speech reinforcement gains. Since the ambient noise significantly decreases the intelligibility of the speech signal, the speech reinforcement approach to amplify the estimated clean speech signal from the background noise environments for improving the intelligibility and clarity of the corrupted speech signal was proposed. In order to estimate the robust reinforcement gain rather than the conventional speech reinforcement method between speech active periods and nonspeech periods or transient intervals, we propose the speech reinforcement algorithm based on soft decision applying the SAP to the estimation of speech reinforcement gains. The performances of the proposed algorithm are evaluated by the Comparison Category Rating (CCR) of the measurement for subjective determination of transmission quality in ITU-T P.800 under various ambient noise environments and show better performances compared with the conventional method.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.670-677
• /
• 2019

As the presence of background noise in acoustic signal degrades the performance of speech or acoustic event recognition, it is still challenging to extract noise-robust acoustic features from noisy signal. In this paper, we propose a combined structure of Wasserstein Generative Adversarial Network (WGAN) and MultiTask AutoEncoder (MTAE) as deep learning architecture that integrates the strength of MTAE and WGAN respectively such that it estimates not only noise but also speech features from noisy acoustic source. The proposed MTAE-WGAN structure is used to estimate speech signal and the residual noise by employing a gradient penalty and a weight initialization method for Leaky Rectified Linear Unit (LReLU) and Parametric ReLU (PReLU). The proposed MTAE-WGAN structure with the adopted gradient penalty loss function enhances the speech features and subsequently achieve substantial Phoneme Error Rate (PER) improvements over the stand-alone Deep Denoising Autoencoder (DDAE), MTAE, Redundant Convolutional Encoder-Decoder (R-CED) and Recurrent MTAE (RMTAE) models for robust speech recognition.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3290-3299
• /
• 2000

Digital watermarking has similar concepts with channel coding thechnique for transferring data with minimizing error in noise environment, since it should be robust to various kinds of data manipulation for protecting copyrights of multimedia data. This paper proposes a digital watermarking technique which is robust to various kinds of data manipulation. Intellectual property rights information is encoded using a convolutional code, and block-interleaving technique is applied to prevent successive loss of encoded data. Encoded intelloctual property rithts informationis embedded using spread spectrum technique which is robust to cata manipulation. In order to reconstruct intellectual property rights information, watermark signalis detected by covariance between watermarked image and pseudo rando noise sequence which is used to einbed watermark. Embedded intellectual property rights information is obtaned by de-interleaving and cecoding previously detected wtermark signal. Experimental results show that block interleaving watermarking technique can detect embedded intellectial property right informationmore correctly against to attacks like Gaussian noise additon, filtering, and JPEG compression than general spread spectrum technique in the same PSNR.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.39-46
• /
• 2019

In this paper, combining features is proposed as a way to enhance the classification accuracy of sounds under noisy environments using the CNN (Convolutional Neural Network) structure. A robust log Mel-filter bank using Wiener filter and PNCCs (Power Normalized Cepstral Coefficients) are extracted to form a 2-dimensional feature that is used as input to the CNN structure. An ebird database is used to classify 43 types of bird species in their natural environment. To evaluate the performance of the combined features under noisy environments, the database is augmented with 3 types of noise under 4 different SNRs (Signal to Noise Ratios) (20 dB, 10 dB, 5 dB, 0 dB). The combined feature is compared to the log Mel-filter bank with and without incorporating the Wiener filter and the PNCCs. The combined feature is shown to outperform the other mentioned features under clean environments with a 1.34 % increase in overall average accuracy. Additionally, the accuracy under noisy environments at the 4 SNR levels is increased by 1.06 % and 0.65 % for shop and schoolyard noise backgrounds, respectively.