scholarly journals Convolutional Neural Network-Based Digital Image Watermarking Adaptive to the Resolution of Image and Watermark

2020 ◽  
Vol 10 (19) ◽  
pp. 6854 ◽  
Author(s):  
Jae-Eun Lee ◽  
Young-Ho Seo ◽  
Dong-Wook Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Binary Data ◽  
Digital Images ◽  
Image Watermarking ◽  
Value Added ◽  
Absolute Error ◽  
Geometric Attacks ◽  
Host Image ◽  
Processing Network

Digital watermarking has been widely studied as a method of protecting the intellectual property rights of digital images, which are high value-added contents. Recently, studies implementing these techniques with neural networks have been conducted. This paper also proposes a neural network to perform a robust, invisible blind watermarking for digital images. It is a convolutional neural network (CNN)-based scheme that consists of pre-processing networks for both host image and watermark, a watermark embedding network, an attack simulation for training, and a watermark extraction network to extract watermark whenever necessary. It has three peculiarities for the application aspect: The first is the host image resolution’s adaptability. This is to apply the proposed method to any resolution of the host image and is performed by composing the network without using any resolution-dependent layer or component. The second peculiarity is the adaptability of the watermark information. This is to provide usability of any user-defined watermark data. It is conducted by using random binary data as the watermark and is changed each iteration during training. The last peculiarity is the controllability of the trade-off relationship between watermark invisibility and robustness against attacks, which provides applicability for different applications requiring different invisibility and robustness. For this, a strength scaling factor for watermark information is applied. Besides, it has the following structural or in-training peculiarities. First, the proposed network is as simple as the most profound path consists of only 13 CNN layers, which is through the pre-processing network, embedding network, and extraction network. The second is that it maintains the host’s resolution by increasing the resolution of a watermark in the watermark pre-processing network, which is to increases the invisibility of the watermark. Also, the average pooling is used in the watermark pre-processing network to properly combine the binary value of the watermark data with the host image, and it also increases the invisibility of the watermark. Finally, as the loss function, the extractor uses mean absolute error (MAE), while the embedding network uses mean square error (MSE). Because the extracted watermark information consists of binary values, the MAE between the extracted watermark and the original one is more suitable for balanced training between the embedder and the extractor. The proposed network’s performance is confirmed through training and evaluation that the proposed method has high invisibility for the watermark (WM) and high robustness against various pixel-value change attacks and geometric attacks. Each of the three peculiarities of this scheme is shown to work well with the experimental results. Besides, it is exhibited that the proposed scheme shows good performance compared to the previous methods.

A SVD and Modified Firefly Optimization Based Robust Digital Image Watermarking Technique

2017 ◽  
Vol 7 (7) ◽  
pp. 268
Author(s):  
Chauhan Usha ◽  
Singh Rajeev Kumar
Keyword(s):  
Digital Media ◽  
Firefly Algorithm ◽  
Image Watermarking ◽  
Singular Values ◽  
Robust Watermarking ◽  
Scaling Factors ◽  
Geometric Attacks ◽  
Host Image ◽  
Firefly Optimization ◽  
Value Decomposition

Digital Watermarking is a technology, to facilitate the authentication, copyright protection and Security of digital media. The objective of developing a robust watermarking technique is to incorporate the maximum possible robustness without compromising with the transparency. Singular Value Decomposition (SVD) using Firefly Algorithm provides this objective of an optimal robust watermarking technique. Multiple scaling factors are used to embed the watermark image into the host by multiplying these scaling factors with the Singular Values (SV) of the host image. Firefly Algorithm is used to optimize the modified host image to achieve the highest possible robustness and transparency. This approach can significantly increase the quality of watermarked image and provide more robustness to the embedded watermark against various attacks such as noise, geometric attacks, filtering attacks etc.

scholarly journals Short-Term Traffic Flow Forecasting Model Based on GA-TCN

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Rongji Zhang ◽  
Feng Sun ◽  
Ziwen Song ◽  
Xiaolin Wang ◽  
Yingcui Du ◽  
...  
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Convolutional Neural Network ◽  
Traffic Flow ◽  
Absolute Error ◽  
Forecasting Model ◽  
Average Absolute Error ◽  
Short Term ◽  
Traffic Flow Forecasting ◽  
Fitness Value

Traffic flow forecasting is the key to an intelligent transportation system (ITS). Currently, the short-term traffic flow forecasting methods based on deep learning need to be further improved in terms of accuracy and computational efficiency. Therefore, a short-term traffic flow forecasting model GA-TCN based on genetic algorithm (GA) optimized time convolutional neural network (TCN) is proposed in this paper. The prediction error was considered as the fitness value and the genetic algorithm was used to optimize the filters, kernel size, batch size, and dilations hyperparameters of the temporal convolutional neural network to determine the optimal fitness prediction model. Finally, the model was tested using the public dataset PEMS. The results showed that the average absolute error of the proposed GA-TCN decreased by 34.09%, 22.42%, and 26.33% compared with LSTM, GRU, and TCN in working days, while the average absolute error of the GA-TCN decreased by 24.42%, 2.33%, and 3.92% in weekend days, respectively. The results indicate that the model proposed in this paper has a better adaptability and higher prediction accuracy in short-term traffic flow forecasting compared with the existing models. The proposed model can provide important support for the formulation of a dynamic traffic control scheme.

scholarly journals Robust and Blind Multiple Image Watermarking Using CNN and DWT in Video

2020 ◽  
Vol 6 (3) ◽  
pp. 8-13
Author(s):  
Farha Khan ◽  
M. Sarwar Raeen
Keyword(s):  
Neural Network ◽  
Wavelet Coefficient ◽  
Image Watermarking ◽  
High Capacity ◽  
Multimedia Systems ◽  
Convolution Neural Network ◽  
Discrete Wavelet ◽  
Host Image ◽  
Different Types ◽  
Result Analysis

Digital watermarking was introduced as a result of rapid advancement of networked multimedia systems. It had been developed to enforce copyright technologies for cover of copyright possession. Due to increase in growth of internet users of networks are increasing rapidly. It has been concluded that to minimize distortions and to increase capacity, techniques in frequency domain must be combined with another technique which has high capacity and strong robustness against different types of attacks. In this paper, a robust multiple watermarking which combine Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT)and Convolution Neural Network techniques on selected middle band of the video frames is used. This methodology is considered to be robust blind watermarking because it successfully fulfills the requirement of imperceptibility and provides high robustness against a number of image-processing attacks such as Mean filtering, Median filtering, Gaussian noise, salt and pepper noise, poison noise and rotation attack. The proposed method embeds watermark by decomposing the host image. Convolution neural network calculates the weight factor for each wavelet coefficient. The watermark bits are added to the selected coefficients without any perceptual degradation for host image. The simulation is performed on MATLAB platform. The result analysis is evaluated on PSNR and MSE which is used to define robustness of the watermark that means that the watermark will not be destroyed after intentional or involuntary attacks and can still be used for certification. The analysis of the results was made with different types of attacks concluded that the proposed technique is approximately 14% efficient as compared to existing work.

scholarly journals Multiple-Input Deep Convolutional Neural Network Model for COVID-19 Forecasting in China

2020 ◽  
Author(s):  
Chiou-Jye Huang ◽  
Yung-Hsiang Chen ◽  
Yuxuan Ma ◽  
Ping-Huan Kuo
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Forecasting Model ◽  
Cumulative Number ◽  
Mean Square ◽  
Multiple Input ◽  
Network Method

AbstractCOVID-19 is spreading all across the globe. Up until March 23, 2020, the confirmed cases in 173 countries and regions of the globe had surpassed 346,000, and more than 14,700 deaths had resulted. The confirmed cases outside of China had also reached over 81,000, with over 3,200 deaths. In this study, a Convolutional Neural Network (CNN) was proposed to analyze and predict the number of confirmed cases. Several cities with the most confirmed cases in China were the focus of this study, and a COVID-19 forecasting model, based on the CNN deep neural network method, was proposed. To compare the overall efficacies of different algorithms, the indicators of mean absolute error and root mean square error were applied in the experiment of this study. The experiment results indicated that compared with other deep learning methods, the CNN model proposed in this study has the greatest prediction efficacy. The feasibility and practicality of the model in predicting the cumulative number of COVID-19 confirmed cases were also verified in this study.

Estimation of structural response using convolutional neural network: application to the Suramadu bridge

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Arya Panji Pamuncak ◽  
Mohammad Reza Salami ◽  
Augusta Adha ◽  
Bambang Budiono ◽  
Irwanda Laory
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Structural Response ◽  
Force Sensor ◽  
Absolute Error ◽  
Percentage Error ◽  
Learning Approaches ◽  
Content Type ◽  
Cable Force

PurposeStructural health monitoring (SHM) has gained significant attention due to its capability in providing support for efficient and optimal bridge maintenance activities. However, despite the promising potential, the effectiveness of SHM system might be hindered by unprecedented factors that impact the continuity of data collection. This research presents a framework utilising convolutional neural network (CNN) for estimating structural response using environmental variations.Design/methodology/approachThe CNN framework is validated using monitoring data from the Suramadu bridge monitoring system. Pre-processing is performed to transform the data into data frames, each containing a sequence of data. The data frames are divided into training, validation and testing sets. Both the training and validation sets are employed to train the CNN models while the testing set is utilised for evaluation by calculating error metrics such as mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE). Comparison with other machine learning approaches is performed to investigate the effectiveness of the CNN framework.FindingsThe CNN models are able to learn the trend of cable force sensor measurements with the ranges of MAE between 10.23 kN and 19.82 kN, MAPE between 0.434% and 0.536% and RMSE between 13.38 kN and 25.32 kN. In addition, the investigation discovers that the CNN-based model manages to outperform other machine learning models.Originality/valueThis work investigates, for the first time, how cable stress can be estimated using temperature variations. The study presents the first application of 1-D CNN regressor on data collected from a full-scale bridge. This work also evaluates the comparison between CNN regressor and other techniques, such as artificial neutral network (ANN) and linear regression, in estimating bridge cable stress, which has not been performed previously.

scholarly journals Hyperspectral imaging for prediction of surface roughness in laser powder bed fusion

2021 ◽  
Author(s):  
Niklas Gerdes ◽  
Christian Hoff ◽  
Jörg Hermsdorf ◽  
Stefan Kaierle ◽  
Ludger Overmeyer
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Quality Assurance ◽  
Convolutional Neural Network ◽  
Absolute Error ◽  
Hyperspectral Data ◽  
Future Research ◽  
Powder Bed Fusion ◽  
Laser Powder Bed Fusion ◽  
Powder Bed

AbstractThis article discusses the relevance of in situ quality assurance in metal additive manufacturing for cost-efficient product qualification. It presents an approach for monitoring the laser powder bed fusion (LPBF) process using an area-scan hyperspectral camera to predict the surface roughness Rz with the help of a convolutional neural network. These investigations were carried out during LPBF processing of the magnesium alloy WE43 that, due to its bioresorbability and compatibility, holds significant potential for biomedical implants. A data acquisition and processing methodology has been set up to enable efficient management of the hyperspectral data. The hyperspectral images obtained from the process were labeled with the surface roughness Rz as determined by a confocal microscope. The data was used to train a convolutional neural network whose hyperparameters were optimized in a hyperparameter tuning process. The resulting network was able to predict the surface roughness within a mean absolute error (MAE) of 4.1 μm over samples from three different parameter sets. Since this is significantly smaller than the spread of the actual roughness measured (MAE = 14.3 μm), it indicates that the network identified features in the hyperspectral data linking to the roughness. These results provide the basis for future research aiming to link hyperspectral process images to further part properties relevant for quality assurance.

scholarly journals Deep learning in geodesy

2021 ◽  
Author(s):  
Omid Memarian Sorkhabi
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Absolute Error ◽  
Three Solutions ◽  
Resolution Problem

Abstract Deep learning (DL) can be a way to automate the analysis of predictions. DL algorithms are in the hierarchy of increasing complexity and abstraction while traditional machine learning is linear. In this study, the downscaling of the GRACE-FO satellite was investigated using a convolutional neural network (CNN). Three solutions were used for downscaling with CNN. Down-scaling accuracy is estimated to be 0.1 degree and its absolute error is 1 mm. The results show that this method can improve the GRACE-FO spatial resolution problem with higher efficiency and make it easier to analyze the results. Also, DL can solve many geodesy problems.

scholarly journals Coffee Flower Identification Using Binarization Algorithm Based on Convolutional Neural Network for Digital Images

2020 ◽  
Vol 2020 ◽  
pp. 1-15
Author(s):  
Pengliang Wei ◽  
Ting Jiang ◽  
Huaiyue Peng ◽  
Hongwei Jin ◽  
Han Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Digital Images ◽  
Time Lapse ◽  
Identification Accuracy ◽  
Support Vector ◽  
Small Scale ◽  
Binarization Algorithm

Crop-type identification is one of the most significant applications of agricultural remote sensing, and it is important for yield estimation prediction and field management. At present, crop identification using datasets from unmanned aerial vehicle (UAV) and satellite platforms have achieved state-of-the-art performances. However, accurate monitoring of small plants, such as the coffee flower, cannot be achieved using datasets from these platforms. With the development of time-lapse image acquisition technology based on ground-based remote sensing, a large number of small-scale plantation datasets with high spatial-temporal resolution are being generated, which can provide great opportunities for small target monitoring of a specific region. The main contribution of this paper is to combine the binarization algorithm based on OTSU and the convolutional neural network (CNN) model to improve coffee flower identification accuracy using the time-lapse images (i.e., digital images). A certain number of positive and negative samples are selected from the original digital images for the network model training. Then, the pretrained network model is initialized using the VGGNet and trained using the constructed training datasets. Based on the well-trained CNN model, the coffee flower is initially extracted, and its boundary information can be further optimized by using the extracted coffee flower result of the binarization algorithm. Based on the digital images with different depression angles and illumination conditions, the performance of the proposed method is investigated by comparison of the performances of support vector machine (SVM) and CNN model. Hence, the experimental results show that the proposed method has the ability to improve coffee flower classification accuracy. The results of the image with a 52.5° angle of depression under soft lighting conditions are the highest, and the corresponding Dice (F1) and intersection over union (IoU) have reached 0.80 and 0.67, respectively.

scholarly journals Deteksi Penyakit Pada Tanaman Mangga Dengan Citra Digital : Tinjauan Literatur Sistematis (SLR)

2020 ◽  
Vol 7 (1) ◽  
pp. 63
Author(s):  
Solikin Solikin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Literature Review ◽  
Decision Tree ◽  
Convolutional Neural Network ◽  
Systematic Literature Review ◽  
Digital Image ◽  
Digital Images ◽  
Disease Identification ◽  
Mango Leaves

Abstrak: Penelitian dengan melakukan tinjauan literatur sistematis (Sistematic Literatur Review-SLR) dilakukan untuk mempelajari berbagai teknik identifikasi penyakit pada daun dengan citra digital  sebagai tahapan untuk mendapatkan pemahaman mengenai teknik identifikasi penyakit pada daun mangga dengan citra digital. Produksi Mangga di Indonesia dari tahun 2014 – 2018 secara fluktuatif selalu mengalami peningkatan dan di tahun 2018 produksi mangga di Indonesia mencapai 2.624.783 ton, proses budidaya tanaman mangga tidak selamanya dapat terlepas dari serangan penyakit. Penyakit pada tanaman mangga disebabkan oleh jamur atau bakteri yang biasanya menyerang pada bagian akar, batang, kulit batang, ranting atau buah mangga. Jenis penyakit pada tanaman mangga adalah : Penyakit mangga (Jamur Gloesoporium), Penyakit Diplodia, Cendawan jelaga, Bercak karat merah, Kudis buah, Penyakit Blendok. Penyakit pada mangga memiliki berbagai gejala dan kadang sulit didiagnosis oleh petani dan untuk itu diperlukan keahlian untuk mendiagnosis penyakit pada tanaman mangga dan bagaimana cara penanggulangannya yang biasanya keahlian tersebut terdapat pada ahli patologi tanaman professional. Sehingga dibutuhkan suatu Teknologi IT dengan Sistem Cerdas yang dirancang untuk dapat mengidentifikasi secara otomatis penyakit tanaman mangga dan cara penanggulangannya berdasarkan gejala visual dengan menggunakan metode citra digital. Metode literatur review yang digunakan yaitu Compare, Contrast, Criticize, Synthesize dan Summarize. Metode Citra Digital yang dapat digunakan dalam identifikasi penyakit pada daun mangga adalah tahapan Image Acquisition, Preprocessing , Segmentation, Ekstraksi Fitur, Seleksi Fitur. Metode Klasifikasi yang dapat digunakan adalah SVM, Artificial Neural Network, Decision Tree, Convolutional Neural Network.   Kata kunci: citra digital, daun, penyakit mangga, tinjauan literatur sistematis     Abstract: Research by conducting a systematic literature review (Systematic Literature Review-SLR) was conducted to study various techniques of disease identification in leaves with digital images as a stage to gain an understanding of the techniques for disease identification on mango leaves with digital images. Mango production in Indonesia from 2014 - 2018 fluctuations has always increased and in 2018 mango production in Indonesia reached 2,624,783 tons, the process of mango cultivation is not always free from disease. Diseases of mango plants are caused by fungi or bacteria that usually attack the roots, stems, bark, twigs or mangoes. Types of diseases in mango plants are: Mango disease (Gloesoporium Fungus), Diplodia disease, sooty fungus, red rust spots, fruit scabies, Blendok disease. Diseases of mangoes have a variety of symptoms and are sometimes difficult to diagnose by farmers and expertise is needed to diagnose diseases on mango plants and how to overcome them which are usually found in professional plant pathologists. So that we need an IT Technology with an Intelligent System that is designed to be able to automatically identify mango plant diseases and how to overcome them based on visual symptoms using digital image methods. The literature review method used is Compare, Contrast, Criticize, Synthesize and Summarize. Digital image methods that can be used in the identification of diseases on mango leaves are the stages of Image Acquisition, Preprocessing, Segmentation, Feature Extraction, Feature Selection. Classification methods that can be used are SVM, Artificial Neural Network, Decision Tree, Convolutional Neural Network.

scholarly journals Automatic Rain Detection System Based on Digital Images of CCTV Cameras Using Convolutional Neural Network Method

2021 ◽  
Vol 893 (1) ◽  
pp. 012048
Author(s):  
Arif Luqman Hakim ◽  
Ristiana Dewi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Digital Images ◽  
Detection System ◽  
Observation Data ◽  
Detection Process ◽  
Weather Information ◽  
Network Method ◽  
Testing Accuracy ◽  
Evaluation Accuracy

Abstract The Meteorology, Climatology and Geophysics Agency (BMKG) has a duty to provide weather information including rainfall. BMKG has several types of rainfall gauges, but these are not evenly distributed across regions. The solution to increase the density of rainfall observations is to use existing sources to obtain weather information. This research uses Closed Circuit Television (CCTV) that is spread across the Jakarta area to produce information on rainy conditions. The method used is the Convolutional Neural Network (CNN). The image from CCTV will be used for the training and testing process, so as to get the best accuracy model. The results of this model will be used for rain detection on CCTV digital images. The rain detection process is carried out automatically and in real time. The results of the rain detection process will be displayed on the map according to the location where the CCTV was installed. This research has succeeded in making a CNN model for rain detection with a training accuracy of 98.8% and a testing accuracy of 96.4%, as well as evaluating the BMKG observation data, so it has an evaluation accuracy of 96.7%.

Sign in / Sign up

Export Citation Format

Share Document