• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.203-211
• /
• 2021

Image tampering detection and localization have become an active area of research in the field of digital image forensics in recent times. This is due to the widespread of malicious image tampering. This study presents a new method for image tampering detection and localization that combines the advantages of dilated convolution, residual network, and UNET Architecture. Using the UNET architecture as a backbone, we built the proposed network from two kinds of residual units, one for the encoder path and the other for the decoder path. The residual units help to speed up the training process and facilitate information propagation between the lower layers and the higher layers which are often difficult to train. To capture global image tampering artifacts and reduce the computational burden of the proposed method, we enlarge the receptive field size of the convolutional kernels by adopting dilated convolutions in the residual units used in building the proposed network. In contrast to existing deep learning methods, having a large number of layers, many network parameters, and often difficult to train, the proposed method can achieve excellent performance with a fewer number of parameters and less computational cost. To test the performance of the proposed method, we evaluate its performance in the context of four benchmark image forensics datasets. Experimental results show that the proposed method outperforms existing methods and could be potentially used to enhance image tampering detection and localization.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2E
• /
• pp.91-97
• /
• 1995

This paper describes the implementation of a multi-channel audio codec for HETV. This codec has the features of the 3/2-stereo plus low frequency enhancement, downward compatibility with the smaller number of channels, backward compatibility with the existing 2/0-stereo system(MPEG-1 audio), and multilingual capability. The encoder of this codec consists of 6-channel analog audio input part with the sampling rate of 48 kHz, 4-channel digital audio input part and three TMS320C40 /DSPs. The encoder implements multi-channel audio compression using a human perceptual psychoacoustic model, and has the bit rate reduction to 384 kbit/s without impairment of subjective quality. The decoder consists of 6-channel analog audio output part, 4-channel digital audio output part, and two TMS320C40 DSPs for a decoding procedure. The decoder analyzes the bit stream received with bit rate of 384 kbit/s from the encoder and reproduces the multi-channel audio signals for analog and digital outputs. The multi-processing of this audio codec using multiple DSPs is ensured by high speed transfer of date between DSPs through coordinating communication port activities with DMA coprocessors. Finally, some technical considerations are suggested to realize the problem of real-time operation, which are found out through the implementation of this codec using the MPEG-2 layer II sudio coding algorithm and the use of the hardware architecture with commercial multiple DSPs.

• Journal of KIISE
• /
• v.45 no.1
• /
• pp.94-98
• /
• 2018

We propose Wide Inception ResNet (WIR Net) an optimized neural network architecture as a real-time semantic segmentation method for autonomous driving. The neural network architecture consists of an encoder that extracts features by applying a residual connection and inception module, and a decoder that increases the resolution by using transposed convolution and a low layer feature map. We also improved the performance by applying an ELU activation function and optimized the neural network by reducing the number of layers and increasing the number of filters. The performance evaluations used an NVIDIA Geforce GTX 1080 and TX1 boards to assess the class and category IoU for cityscapes data in the driving environment. The experimental results show that the accuracy of class IoU 53.4, category IoU 81.8 and the execution speed of $640{\times}360$, $720{\times}480$ resolution image processing 17.8fps and 13.0fps on TX1 board.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1269-1279
• /
• 2019

In medical image analysis, segmentation is considered as a vital process since it partitions an image into coherent parts and extracts interesting objects from the image. In this paper, we consider automatic segmentations of OCT retinal images to find six layer boundaries using convolutional neural networks. Segmenting retinal images by layer boundaries is very important in diagnosing and predicting progress of eye diseases including diabetic retinopathy, glaucoma, and AMD (age-related macular degeneration). We applied well-known CNN architecture for general image segmentation, called Segnet, U-net, and CNN-S into this problem. We also proposed a shortest path-based algorithm for finding the layer boundaries from the outputs of Segnet and U-net. We analysed their performance on public OCT image data set. The experimental results show that the Segnet combined with the proposed shortest path-based boundary finding algorithm outperforms other two networks.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.1
• /
• pp.1-9
• /
• 2019

In this paper, we propose a method of generating a 2D gray image from LiDAR 3D reflection intensity. The proposed method uses the Fully Convolutional Network (FCN) to generate the gray image from 2D reflection intensity which is projected from LiDAR 3D intensity. Both encoder and decoder of FCN are configured with several convolution blocks in the symmetric fashion. Each convolution block consists of a convolution layer with $3{\times}3$ filter, batch normalization layer and activation function. The performance of the proposed method architecture is empirically evaluated by varying depths of convolution blocks. The well-known KITTI data set for various scenarios is used for training and performance evaluation. The simulation results show that the proposed method produces the improvements of 8.56 dB in peak signal-to-noise ratio and 0.33 in structural similarity index measure compared with conventional interpolation methods such as inverse distance weighted and nearest neighbor. The proposed method can be possibly used as an assistance tool in the night-time driving system for autonomous vehicles.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.3
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• Current Optics and Photonics
• /
• v.8 no.5
• /
• pp.463-471
• /
• 2024

Multimode fibers (MMFs) possess high information throughput and small core diameter, making them highly promising for applications such as endoscopy and communication. However, modal dispersion hinders the direct use of MMFs for image transmission. By training neural networks on time-series waveforms collected from MMFs it is possible to reconstruct images, transforming blurred speckle patterns into recognizable images. This paper proposes a fully convolutional neural-network model, MSMDFNet, for image restoration in MMFs. The network employs an encoder-decoder architecture, integrating multiscale convolutional modules in the decoding layers to enhance the receptive field for feature extraction. Additionally, attention mechanisms are incorporated from both spatial and channel dimensions, to improve the network's feature-perception capabilities. The algorithm demonstrates excellent performance on MNIST and Fashion-MNIST datasets collected through MMFs, showing significant improvements in various metrics such as SSIM.

• The KIPS Transactions:PartB
• /
• v.12B no.6 s.102
• /
• pp.637-646
• /
• 2005

Most of the multimedia contents for DBM services art provided as MPEG-2 bit streams. However, they have to be transcoded to H.264 bit streams for practical services because the standard video codec for DMB is H.264. The existing transcoder architecture is Cascaded Pixel-Domain Transcoding Architecture, which consists of the MPEG-2 dacoding phase and the H.264 encoding phase. This architecture can be easily implemented using MPEG-2 decoder and H.264 encoder without source modifying. However. It has disadvantages in transcoding time and DCT-mismatch problem. In this paper, we propose two kinds of transcoder architecture, DCT-OPEN and DCT-CLOSED, to complement the CPDT architecture. Although DCT-OPEN has lower PSNR than CPDT due to drift problem, it is efficient for real-time transcoding. On the contrary, the DCT-CLOSED architecture has the advantage of PSNR over CPDT at the cost of transcoding time.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.47 no.1
• /
• pp.20-27
• /
• 2010

This paper describes a design of 5-stage pipelined de-blocking filter with power reduction scheme and proposes a efficient memory architecture and filter order for high performance H.264/AVC Decoder. Generally the de-blocking filter removes block boundary artifacts and enhances image quality. Nevertheless filter has a few disadvantage that it requires a number of memory access and iterated operations because of filter operation for 4 time to one edge. So this paper proposes a optimized filter ordering and efficient hardware architecture for the reduction of memory access and total filter cycles. In proposed filter parallel processing is available because of structured 5-stage pipeline consisted of memory read, threshold decider, pre-calculation, filter operation and write back. Also it can reduce power consumption because it uses a clock gating scheme which disable unnecessary clock switching. Besides total number of filtering cycle is decreased by new filter order. The proposed filter is designed with Verilog-HDL and functionally verified with the whole H.264/AVC decoder using the Modelsim 6.2g simulator. Input vectors are QCIF images generated by JM9.4 standard encoder software. As a result of experiment, it shows that the filter can make about 20% total filter cycles reduction and it requires small transposition buffer size.