• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.109-114
• /
• 2021

As various users increase in a network environment, it is difficult to protect sensitive and confidential information transmitted and received from attackers. Concealing bitwise secret data in an image using the LSB technique can be very vulnerable to attack. To solve this problem, a hybrid method that combines encryption and information hiding is used. Therefore, an effective method for users to securely protect secret messages and implement secret communication is required. A new approach is needed to improve security and imperceptibility to ensure image quality. In this paper, I propose an LSB steganography technique that hides Hangul messages in a cover image based on MSB and LSB. At this time, after separating Hangul into chosung, jungsung and jongsung, the secret message is applied with Exclusive-OR or Exclusive-NOR operation depending on the selected MSB. In addition, the calculated secret data is hidden in the LSB n bits of the cover image converted by Fibonacci technique. PSNR was used to confirm the effectiveness of the applied results. It was confirmed 41.517(dB) which is suitable as an acceptable result.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.1
• /
• pp.366-381
• /
• 2020

Steganography has been successfully employed in various applications, e.g., copyright control of materials, smart identity cards, video error correction during transmission, etc. Deep learning-based steganography models can hide information adaptively through network learning, and they draw much more attention. However, the capacity, security, and robustness of the existing deep learning-based steganography models are still not fully satisfactory. In this paper, three models for different cases, i.e., a basic model, a secure model, a secure and robust model, have been proposed for different cases. In the basic model, the functions of high-capacity secret information hiding and extraction have been realized through an encoding network and a decoding network respectively. The high-capacity steganography is implemented by hiding a secret image into a carrier image having the same resolution with the help of concat operations, InceptionBlock and convolutional layers. Moreover, the secret image is hidden into the channel B of carrier image only to resolve the problem of color distortion. In the secure model, to enhance the security of the basic model, a steganalysis network has been added into the basic model to form an adversarial network. In the secure and robust model, an attack network has been inserted into the secure model to improve its robustness further. The experimental results have demonstrated that the proposed secure model and the secure and robust model have an overall better performance than some existing high-capacity deep learning-based steganography models. The secure model performs best in invisibility and security. The secure and robust model is the most robust against some attacks.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.71-78
• /
• 2011

This paper propose image steganalysis scheme based on independence between parent and child subband on the multi-layer wavelet domain. The proposed method decompose cover and stego images into 12 subbands by applying 3-level Haar UWT(Undecimated Wavelet Transform), analyze statistical independency between parent and child subband. Because this independency is appeared more difference in stego image than in cover image, we can use it as feature to differenciate between cover and stego image. Therefore we extract 72D features by calculation first 3 order statistical moments from joint characteristic function between parent and child subband. Multi-layer perceptron(MLP) is applied as classifier to discriminate between cover and stego image. We test the performance of proposed scheme over various embedding rates by the LSB, SS, BSS embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.6
• /
• pp.281-288
• /
• 2014

QR code (abbreviated from Quick Response Code) is code system that is strong in against to apply image processing techniques (skew, warp, blur, and rotate) as QR codes can store several hundred times the amount of information carried by ordinary bar codes. For this reason, QR code is used in various fields, e.g., air ticket (boarding control system), food(vegetables, meat etc.) tracking system, contact lenses management, prescription management, patient wrist band (patient management) etc. In this paper, we proposed reversible data hiding for binary images. A reversible data hiding algorithm, which can recover the original image without any distortion from the marked (stego) image after the hidden data have been extracted, because it is possible to use various kinds of purposes. QR code can be used to generate by anyone so it can be easily used for crime. In order to prevent crimes related QR code, reversible data hiding can confirm if QR code is counterfeit or not as including authentication information. In this paper, we proved proposed method as experiments.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1398-1400
• /
• 1996

In this paper, a method of the decision of the road direction for ALV(Autonomous Land Vehicle) road following by region-based segmentation is presented. The decision of the road direction requires extracting road regions from images in real-time to guide the navigation of ALV on the roadway. Two thresholds to discriminate between road and non-road region in the image are easily decided, using knowledge of problem region and polygonal approximation that searches multiple peaks and valleys in histogram of a road image. The most likely road region of the binary image is selected from original image by these steps. The location of a vanishing point to indicate the direction of the road can be obtained applying it to X-Y profile of the binary road region again. It can successfully steer a ALV along a road reliably, even in the presence of fluctuation of illumination condition, bad road surface condition such as hidden boundaries, shadows, road patches, dirt and water stains, and unusual road condition. Pyramid structure also saves time in processing road images and a real-time image processing for achieving navigation of ALV is implemented. The efficacy of this approach is demonstrated using several real-world road images.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.507-513
• /
• 2018

Steganography is a technique that uses hidden messages to prevent anyone apart from knowing the existence of a secret message, except the sender and trusted recipients. This paper applies 24 bit color image as cover medium. And a 24-bit color image has three components corresponding to red, green and blue. This paper proposes an image steganography method that uses Triple-A algorithm to hide the secret (Hangul) message by arbitrarily selecting the number of LSB bits and the color channel to be used. This paper divides the secret character into the chosung, jungsung and jongsung, and applies crossover, encryption and arbitrary insertion positions to enhance robustness and confidentiality. Experimental results of the proposed method show that insertion capacity and correlation are excellent and acceptable image quality level. Also, considering the image quality, it was confirmed that the size of LSB should be less than 2.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.465-470
• /
• 2024

The advancement of AI-based image generation technology has resulted in the creation of various images, emphasizing the need for technology capable of accurately discerning them. The amount of generated image data is limited, and to achieve high performance with a limited dataset, this study proposes a model for discriminating generated images using transfer learning. Applying pre-trained models from the ImageNet dataset directly to the CIFAKE input dataset, we reduce training time cost followed by adding three hidden layers and one output layer to fine-tune the model. The modeling results revealed an improvement in the performance of the model when adjusting the final layer. Using transfer learning and then adjusting layers close to the output layer, small image data-related accuracy issues can be reduced and generated images can be classified.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.1
• /
• pp.10-17
• /
• 2016

GPS location information storage included in the HD black box is using a unique manner for each manufacturer does not have a specific standard. In this paper, in order to overcome the limitations of the storage space and thereby the image quality according to store GPS position information deteriorate to solve the problems that cause, we propose the location information concealment method included in the HDTV video content using a essential hidden region. HDTV video content is a Border Extender of 8 lines in the frame to the bottom of the compression will be required. This was inserted into the image of a gray scale used in block form in order to space the current position information is concealed to prevent image degradation. The proposed method was confirmed using real HD black box, there are more difficult to interpret the format of the ASCII code re-edit the location information when the compression effect disappears with the existing security zones added. Therefore, the proposed method is suitable for location-based services, such as Facebook or Youtube videos.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.471-476
• /
• 2016

In this paper, recognition system for continuous human action is explained by using motion history image and histogram of oriented gradient with spotter model based on depth information, and the spotter model which performs action spotting is proposed to improve recognition performance in the recognition system. The steps of this system are composed of pre-processing, human action and spotter modeling and continuous human action recognition. In pre-processing process, Depth-MHI-HOG is used to extract space-time template-based features after image segmentation, and human action and spotter modeling generates sequence by using the extracted feature. Human action models which are appropriate for each of defined action and a proposed spotter model are created by using these generated sequences and the hidden markov model. Continuous human action recognition performs action spotting to segment meaningful action and meaningless action by the spotter model in continuous action sequence, and continuously recognizes human action comparing probability values of model for meaningful action sequence. Experimental results demonstrate that the proposed model efficiently improves recognition performance in continuous action recognition system.