• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.148-154
• /
• 2021

Text-Independent speaker verification needs to extract text-independent speaker embedding to improve generalization performance. However, deep neural networks that depend on training data have the potential to overfit text information instead of learning the speaker information when repeatedly learning from the identical time series. In this paper, to prevent the overfitting, we propose a segment unit shuffling layer that divides and rearranges the input layer or a hidden layer along the time axis, thus mixes the time series information. Since the segment unit shuffling layer can be applied not only to the input layer but also to the hidden layers, it can be used as generalization technique in the hidden layer, which is known to be effective compared to the generalization technique in the input layer, and can be applied simultaneously with data augmentation. In addition, the degree of distortion can be adjusted by adjusting the unit size of the segment. We observe that the performance of text-independent speaker verification is improved compared to the baseline when the proposed segment unit shuffling layer is applied.

• Annual Conference of KIPS
• /
• 2011.04a
• /
• pp.346-349
• /
• 2011

In this paper, we design a perceptually invisible dot pattern layout and its recognition scheme, and we apply the recognition scheme into a smart self learning aid for interactive learning aid. To increase maximum information capacity and also increase robustness to the noises, we design a ECC (error correcting code) based dot pattern with directional vector indicator. To make a smart self-learning aid, we embed the micro dot pattern (20 information bit + 15 ECC bits + 9 layout information bit) using K ink (CMYK) and extract the dot pattern using IR (infrared) LED and IR filter based camera, which is embedded in the smart pen. The reason we use K ink is that K ink is a carbon based ink in nature, and carbon is easily recognized with IR even without light. After acquiring IR camera images for the dot patterns, we perform layout adjustment using the 9 layout information bit, and extract 20 information bits from 35 data bits which is composed of 20 information bits and 15 ECC bits. To embed and extract information bits, we use topology based dot pattern recognition scheme which is robust to geometric distortion which is very usual in camera based recognition scheme. Topology based pattern recognition traces next information bit symbols using topological distance measurement from the pivot information bit. We implemented and experimented with sample patterns, and it shows that we can achieve almost 99% recognition for our embedding patterns.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.11
• /
• pp.2893-2912
• /
• 2013

The design of geometrically invariant watermarking is one of the most challenging work in digital image watermarking research area. To achieve the robustness to geometrical attacks, the inherent characteristic of an image is usually used. In this paper, a geometrically invariant image watermarking scheme using connected objects and gravity center is proposed. First, the gray-scale image is converted into the binary one, and the connected objects according to the connectedness of binary image are obtained, then the coordinates of these connected objects are mapped to the gray-scale image, and the gravity centers of those bigger objects are chosen as the feature points for watermark embedding. After that, the line between each gravity center and the center of the whole image is rotated an angle to form a sector, and finally the same version of watermark is embedded into these sectors. Because the image connectedness is topologically invariant to geometrical attacks such as scaling and rotation, and the gravity center of the connected object as feature points is very stable, the watermark synchronization is realized successfully under the geometrical distortion. The proposed scheme can extract the watermark information without using the original image or template. The simulation results show the proposed scheme has a good invisibility for watermarking application, and stronger robustness than previous feature-based watermarking schemes against geometrical attacks such as rotation, scaling and cropping, and can also resist common image processing operations including JPEG compression, adding noise, median filtering, and histogram equalization, etc.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.7A
• /
• pp.711-723
• /
• 2002

A finer granular scalable (FGS) version of ISO/IEC MPEG-4 video streaming is investigated in this work with the prioritized stream delivery over loss-rate differentiated networks. Our proposed system is focused on the seamless integration of rate adaptation, prioritized packetization, and simplified differentiation for the MPEG-4 FGS video streaming. The proposed system consists of three key components: 1) rate adaptation with scalable source encoding, 2) content-aware prioritized packetization, and 3) loss-based differential forwarding. More specifically, a constant-quality rate adaptation is first achieved by optimally truncating the over-coded FGS stream based on the embedding rate-distortion (R-D) information (obtained from a piecewise linear R-D model). The rate-controlled video stream is then packetized and prioritized according to the loss impact of each packet. Prioritized packets are transmitted over the underlying network, where packets are subject to differentiated dropping and forwarding. By focusing on the end-to-end quality, we establish an effective working conditions for the proposed video streaming and the superior performance is verified by simulated MPEG-4 FGS video streaming.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.404-421
• /
• 2020

A reversible data hiding scheme in JPEG compressed bitstreams is proposed, which could avoid decoding failure and file expansion by means of removing of bitstreams corresponding to high frequency coefficients and embedding of secret data in file header as comment part. We decode original JPEG images to quantified 8×8 DCT blocks, and search for a high frequency as an optimal termination point, beyond which the coefficients are set to zero. These blocks are separated into two parts so that termination point in the latter part is slightly smaller to make the whole blocks available in substitution. Then spare space is reserved to insert secret data after comment marker so that data extraction is independent of recovery in receiver. Marked images can be displayed normally such that it is difficult to distinguish deviation by human eyes. Termination point is adaptive for variation in secret size. A secret size below 500 bits produces a negligible distortion and a PSNR of approximately 50 dB, while PSNR is also mostly larger than 30 dB for a secret size up to 25000 bits. The experimental results show that the proposed technique exhibits significant advantages in computational complexity and preservation of file size for small hiding capacity, compared to previous methods.

• Journal of Broadcast Engineering
• /
• v.6 no.2
• /
• pp.195-202
• /
• 2001

As a solution for copyright protection of digital multimedia contents, digital watermark technology is now drawing the attention. In this paper, we presented two novel audio watermarking algorithms as a solution for protecting unauthorized copy of digital audio. Proposed watermarking schemes include the psychoacoustic model of MPEG audio coding to achieve the perceptual transparency after watermark embedding and preprocessing procedure before correlation in watermark detection to extract copyright information without access to the original audio signal. Experimental results show that our watermarking scheme is robust to common signal Processing attacks and it Introduces no audible distortion after watermark insertion.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.3
• /
• pp.307-314
• /
• 2015

In this paper, the embedding type novel liquid metal strain gauge was developed for measuring the deformation of wind turbine blades. In general, the conventional methods for the SHM have many disadvantages such as frequency distortion in FBG sensors, the low gauge factor and mechanical failures in strain gauges and extremely sophisticated filtering in AE sensors. However, the liquid metal filled in a pre-confined micro channel shows dramatic characteristics such as high sensitivity, flexibility and robustnes! s to environment. To adopt such a high feasibility of the liquid metal in flexible sensor applications, the EGaIn was introduced to make flexible liquid metal strain gauges for the SHM. A micro channeled flexible film fabricated by the several MEMS processes and the PDMS replication was filled with EGaIn and wire-connected. Lots of experiments were conducted to investigate the performance of the developed strain gauges and verify the feasibility to the actual wind turbine blades health monitoring.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2572-2589
• /
• 2014

Reversible data hiding is a technique for recovering original images without any distortion after secret data are extracted from the image. The technique continues to attract attention from many researchers. In this paper, we introduce a new reversible data hiding scheme based on the adjacent index differences of vector quantization (VQ) indices. The proposed scheme exploits the differences between two adjacent indices to embed secret data. Experimental results show that our scheme can achieve a lower compression rate than an earlier scheme by Yang and Lin. Our scheme's average compression rate, 0.44 bpp, outperforms that of Yang and Lin's scheme, which averages 0.53 bpp. Moreover, the embedding capacity of our scheme can rise to 1.45 bpi, which also is superior to that of Chang et al.'s scheme [35] (1.00 bpi)Yang and Lin's scheme [27] (0.91 bpi) as well as Chang et al.'s scheme [26] (0.74 bpi).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6190-6213
• /
• 2019

For small-scale vector data, restrictions on watermark scheme capacity and robustness limit the use of copyright protection. A watermarking scheme based on robust geometric features and capacity maximization strategy that simultaneously improves capacity and robustness is presented in this paper. The distance ratio and angle of adjacent vertices are chosen as the watermark domain due to their resistance to vertex and geometric attacks. Regarding watermark embedding and extraction, a capacity-improved strategy based on quantization index modulation, which divides more intervals to carry sufficient watermark bits, is proposed. By considering the error tolerance of the vector map and the numerical accuracy, the optimization of the capacity-improved strategy is studied to maximize the embedded watermark bits for each vertex. The experimental results demonstrated that the map distortion caused by watermarks is small and much lower than the map tolerance. Additionally, the proposed scheme can embed a copyright image of 1024 bits into vector data of 150 vertices, which reaches capacity at approximately 14 bits/vertex, and shows prominent robustness against vertex and geometric attacks for small-scale vector data.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.11C
• /
• pp.1169-1176
• /
• 2003

In this paper, we propose a blind watermarking that embeds watermarks into wavelet middle frequency subbands using human visual system. Wavelet middle frequency pairs(MFP) show similar distortion against general image processing attacks such as compression and filtering. So the quantization between MFPs is more robust than conventional methods that directly quantize DWT coefficients. We use a noise visibility function(NVF) to obtain a good visual quality This is able to preserve embedding positions after many attacks. Our experimental results show that the proposed scheme is robust to various image processing such as JPEG, while preserving good visual quality above 44㏈.