• Journal of Multimedia Information System
• /
• v.2 no.2
• /
• pp.193-206
• /
• 2015

In this paper a new approach for image encryption based on quadruple encryption with dual chaotic maps is proposed. The encryption process is performed with quadruple encryption by invoking the encrypt and decrypt routines with different keys in the sequence EDEE. The decryption process is performed in the reverse direction DDED. The key generation for the quadruple encryption is achieved with a 1D Circle map. The chaotic values for the encrypt and decrypt routines are generated by using a 2D Henon map. The Encrypt routine E is composed of three stages i.e. permutation, pixel value rotation and diffusion. The permutation is achieved by: row and column scrambling with chaotic values, exchanging the lower and the upper principal and secondary diagonal elements based on the chaotic values. The second stage circularly rotates all the pixel values based on the chaotic values. The last stage performs the diffusion in two directions (forward and backward) with two previously diffused pixels and two chaotic values. The security and performance of the proposed scheme are assessed thoroughly by using the key space, statistical, differential, entropy and performance analysis. The proposed scheme is computationally fast with security intact.

• ETRI Journal
• /
• v.46 no.3
• /
• pp.526-537
• /
• 2024

Monitoring fetal growth in utero is crucial to anomaly diagnosis. However, current computer-vision models struggle to accurately assess the key metrics (i.e., head circumference and occipitofrontal and biparietal diameters) from ultrasound images, largely owing to a lack of training data. Mitigation usually entails image augmentation (e.g., flipping, rotating, scaling, and translating). Nevertheless, the accuracy of our task remains insufficient. Hence, we offer a U-Net fetal head measurement tool that leverages a hybrid Dice and binary cross-entropy loss to compute the similarity between actual and predicted segmented regions. Ellipse-fitted two-dimensional ultrasound images acquired from the HC18 dataset are input, and their lower feature layers are reused for efficiency. During regression, a novel region of interest pooling layer extracts elliptical feature maps, and during segmentation, feature pyramids fuse field-layer data with a new scale attention method to reduce noise. Performance is measured by Dice similarity, mean pixel accuracy, and mean intersection-over-union, giving 97.90%, 99.18%, and 97.81% scores, respectively, which match or outperform the best U-Net models.

• Journal of the Society of Disaster Information
• /
• v.17 no.2
• /
• pp.206-217
• /
• 2021

Purpose: Recently, a series of large social disasters have led to a lot of research to prevent social disasters as well as natural disasters and reduce damage. However, this paper aims to select the types of social disasters that local governments should focus on and create basic data for effective countermeasures and mitigation efforts. Method: Among 43 types of disasters announced by the Ministry of Public Administration and Security, 11 types of disasters were selected and collected to select the main types of disasters, and risk types were derived by region with risk maps. In order to derive the risk map, each detailed index was rescheduled to be 0-1 and weights were determined through entropy technique. Result: As a result, about 41% of the major disasters announced by the Ministry of Public Administration and Security were consistent, and the rest of the major types were disasters that could not be obtained or have not occurred in the past 20 years. Conclusion: Therefore, in order to establish an effective prevention and recovery plan for social disasters through this study, it was intended to present social disaster-focused disasters for each local government.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.6
• /
• pp.72-79
• /
• 2017

In this paper, we present a new saliency detection algorithm using the mutual information of wavelet subbands. Our method constructs an intermediate saliency map using the power operation and Gaussian blurring for high-frequency wavelet coefficients. After combining three intermediate saliency maps according to the direction of wavelet subband, we find the main directional components using entropy measure. The amount of mutual information of each subband is obtained centering on the subband having the minimum entropy The final saliency map is detected using Minkowski sum based on weights calculated by the mutual information. As a result of the experiment on CAT2000 and ECSSD databases, our method showed good detection results in terms of ROC and AUC with few computation times compared with the conventional methods.

• Journal of Computing Science and Engineering
• /
• v.8 no.4
• /
• pp.187-198
• /
• 2014

In this paper an efficient image encryption scheme based on cyclic rotations and multiple blockwise diffusions with two chaotic maps is proposed. A Sin map is used to generate round keys for the encryption/decryption process. A Pomeau-Manneville map is used to generate chaotic values for permutation, pixel value rotation and diffusion operations. The encryption scheme is composed of three stages: permutation, pixel value rotation and diffusion. The permutation stage performs four operations on the image: row shuffling, column shuffling, cyclic rotation of all the rows and cyclic rotation of all the columns. This stage reduces the correlation significantly among neighboring pixels. The second stage performs circular rotation of pixel values twice by scanning the image horizontally and vertically. The amount of rotation is based on $M{\times}N$ chaotic values. The last stage performs the diffusion four times by scanning the image in four different ways: block of $8{\times}8$ pixels, block of $16{\times}16$ pixels, principal diagonally, and secondary diagonally. Each of the above four diffusions performs the diffusion in two directions (forwards and backwards) with two previously diffused pixels and two chaotic values. This stage makes the scheme resistant to differential attacks. The security and performance of the proposed method is analyzed systematically by using the key space, entropy, statistical, differential and performance analysis. The experimental results confirm that the proposed method is computationally efficient with high security.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.469-473
• /
• 2006

In general, a classification process between ground data and non-ground data, which include building objects, is required prior to producing a DEM for a certain surface reconstruction from LiDAR data in which the DEM can be produced from the ground data, and certain objects like buildings can be reconstructed using non-ground data. Thus, an exact classification between ground and non-ground data from LiDAR data is the most important factor in the ground reconstruction process using LiDAR data. In particular, building objects can be largely used as digital maps, orthophotos, and urban planning regarding the object in the ground and become an essential to providing three dimensional information for certain urban areas. In this study, an entropy theory, which has been used as a standard of disorder or uncertainty for data used in the information theory, is used to apply a more objective and generalized method in the recognition and segmentation of buildings from raw LiDAR data. In particular, a method that directly uses the raw LiDAR data, which is a type of point shape vector data, without any changes, to a type of normal lattices was proposed, and the existing algorithm that segments LiDAR data into ground and non-ground data as a binarization manner was improved. In addition, this study proposes a generalized building extraction method that excludes precedent information for buildings and topographies and subsidiary materials, which have different data sources.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.9
• /
• pp.1613-1631
• /
• 2011

Several metrics have been reported in the literature to assess stereo image quality, mostly based on visual attention or human visual sensitivity based distortion prediction with the help of disparity information, which do not consider the combined aspects of human visual processing. In this paper, visual attention and depth assisted stereo image quality assessment model (VAD-SIQAM) is devised that consists of three main components, i.e., stereo attention predictor (SAP), depth variation (DV), and stereo distortion predictor (SDP). Visual attention is modeled based on entropy and inverse contrast to detect regions or objects of interest/attention. Depth variation is fused into the attention probability to account for the amount of changed depth in distorted stereo images. Finally, the stereo distortion predictor is designed by integrating distortion probability, which is based on low-level human visual system (HVS), responses into actual attention probabilities. The results show that regions of attention are detected among the visually significant distortions in the stereo image pair. Drawbacks of human visual sensitivity based picture quality metrics are alleviated by integrating visual attention and depth information. We also show that positive correlation with ground-truth attention and depth maps are increased by up to 0.949 and 0.936 in terms of the Pearson and the Spearman correlation coefficients, respectively.

• 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.

• Journal of Intelligence and Information Systems
• /
• v.15 no.2
• /
• pp.33-48
• /
• 2009

Capsule endoscopy is one of the most remarkable inventions in last ten years. Causing less pain for patients, diagnosis for entire digestive system has been considered as a most convenience method over a normal endoscope. However, it is known that the diagnosis process typically requires very long inspection time for clinical experts because of considerably many duplicate images of same areas in human digestive system due to uncontrollable movement of a capsule endoscope. In this paper, we propose a method for clinical diagnosticians to get highly valuable information from capsule-endoscopy video. Our software system consists of three global maps, such as movement map, characteristic map, and brightness map, in temporal domain for entire sequence of the input video. The movement map can be used for effectively removing duplicated adjacent images. The characteristic and brightness maps provide frame content analyses that can be quickly used for segmenting regions or locating some features(such as blood) in the stream. Our experiments show the results of four patients having different health conditions. The result maps clearly capture the movements and characteristics from the image frames. Our method may help the diagnosticians quickly search the locations of lesion, bleeding, or some other interesting areas.