Proceeding ICOIACT : An Improve Image Watermarking using Random Spread Technique and Discrete Cosine Transform

Abstract: Watermarking is a powerful technique to protect copyright from cyber-crime. This study proposes a random spread technique based on the Discrete Cosine Transform (DCT) to improve image watermarking performance. The use of the random spread technique is proven to be able to improve the output quality of the watermarked image, where the watermark image is increasingly invisible to the eye after being pinned on the cover image. Better PSNR and MSE values prove this, besides watermark security also increases indirectly because embedding techniques spread randomly.

Download paper di sini.
#semuanyaajib

Read More...

Proceeding : Performance Analysis of Face Recognition using Eigenface Approach

Abstract— Eigenface is an algorithm in the principal component analysis (PCA) that is used to recognize faces. Eigenface used to reduce dimensionality and find the best vector for distributing the facial image in the facial space. This method has been widely used and implemented in various previous researches to recognize human face images. Not only to detect human faces under normal conditions, but PCA has also been proven to be able to properly recognize images in various expressions. It can even recognize facial images with various challenges such as detecting faces after plastic surgery and combining them with facial image reconstruction techniques. This research aims to examine the performance of the PCA Eigenface method to recognize human face images from several databases that have their own challenges, such as the lack of illumination of facial images, significant variations in expression and the use of accessories such as glasses. The recognizable accuracy is quite varied, from 100% to 67% in each database with and with an average recognition of more than 85%.

Keywords—Eigenface, Euclidian, Face recognition, JAFFE,PCA, Yale

Download paper di sini

Read More...

Proceeding ICITACEE : A Comparative Study of Image Cryptographic Method

Abstract:

Cryptography is a technique that is widely used to secure data transactions, this technique has also been widely used to secure digital images. There are several cryptographic techniques that are widely used in digital imagery, such as Arnold Transform, Rivest Code 4 (RC4) and One-time pad (OTP). This research aims to compare the performance of these three techniques on digital images. Performance of each encryption method is measured using entropy, SSIM, NPCR, UACI, computation time and histogram analysis. While the decrypted image is measured by the correlation coefficient and computation time using tic toc function. Based on the test results can be concluded that Arnold transforms algorithm only do a scramble on the image based on a certain iteration, so that the entropy and histogram values remain the same as the original image, only visually the image looks random and meaningless. RC4 has an advantage on entropy value and should not require a very long key, so it does not have to be a special memory to store the key. While OTP has advantages in the fastest computing time, and also superior values in NPCR, UACI, and SSIM. A random key of the same size as the original image makes encryption hard to decrypt. Although the size of the key to making the algorithm must provide a larger space for key storage.

Download di sini.

Read More...

Proceeding ICITACEE : A Comparative Study of Image Cryptographic Method

Abstract:

Cryptography is a technique that is widely used to secure data transactions, this technique has also been widely used to secure digital images. There are several cryptographic techniques that are widely used in digital imagery, such as Arnold Transform, Rivest Code 4 (RC4) and One-time pad (OTP). This research aims to compare the performance of these three techniques on digital images. Performance of each encryption method is measured using entropy, SSIM, NPCR, UACI, computation time and histogram analysis. While the decrypted image is measured by the correlation coefficient and computation time using tic toc function. Based on the test results can be concluded that Arnold transforms algorithm only do a scramble on the image based on a certain iteration, so that the entropy and histogram values remain the same as the original image, only visually the image looks random and meaningless. RC4 has an advantage on entropy value and should not require a very long key, so it does not have to be a special memory to store the key. While OTP has advantages in the fastest computing time, and also superior values in NPCR, UACI, and SSIM. A random key of the same size as the original image makes encryption hard to decrypt. Although the size of the key to making the algorithm must provide a larger space for key storage.

Download : IEEEXplore

#semuanyaajib

Read More...

Conference iSemantic 2018 : A Robust Non-Blind Image Watermarking Method Using 2-Level HWT-DCT

Abstract:

The current technology allows to distribute digital images quickly and easily over the internet. Some digital images have copyright that needs to be protected. Watermarking is a technique for protecting copyright. In order for copyright is not easily lost with image manipulation, then watermarking technique must be robust. This study proposes a combination of Discrete Cosine Transform (DCT) based on two levels of the Haar Wavelet Transform (HWT) on image watermarking method with the aim of improving aspects of robustness and imperceptibility. The first step, host image is transformed with DWT as much as two levels to get LL2 subband. LL2 subband is a subband containing the image core information of two levels of wavelet transformation. Furthermore, LL2 subband split into small sub-blocks with the size of 4 * 4. The sub-blocks are transformed again using DCT. Insertion of watermarks using alpha variables with a certain value on the DC coefficient matrix. This value is used for managing the quality and strength of the watermark. To test the imperceptibility and watermark resistance used measuring instruments MSE, PSNR, and correlation coefficient. Based on the simulation results obtained a watermarked image is quite satisfactory with a relatively good imperceptibility value and resistant to various attacks.

Download : IEEE, researchgate

#semuanyaajib

Read More...

Jurnal IEEE : Indonesian news classification based on NaBaNA

Abstract:

This paper focused on the classification of Indonesian news categories. News articles have the format of text, so it will be more complex and needs to be a process to prepare the data. Also, the article is accepted Indonesia language articles should be simplified into a basic word on every word, this can be done by the method of stemmer Nazief and Andriani. For the classification method used is Naïve Bayes method is commonly used for text mining. Both of these methods Naïve Bayes and Nazief-Adriani stemming (NaBaNA) will collaborate to get results with high accuracy. The results showed by Naïve Bayes classification with the support of Nazief and Andriani get higher accuracy.

I. Introduction

Today the development of science and information technology is very rapid; many innovations created information technology to help alleviate human work. Not a few companies or agencies that get big profits after optimizing the utilization of information technology owned. The Internet is one of the media information today that always experience a very rapid development. With the internet one can easily do activities such as reading news, watching movies, finding information, even doing transactions though. Therefore, the internet is considered become source information as background knowledge that required to be classified [1].

Download paper PDF

Read More...

Jurnal IEEE : Hybrid Method using HWT-DCT for Image Watermarking

Astract- This paper proposed a hybrid method that had been solved both of these issues. We proposed a combination of Discrete Cosine Transform (DCT) and Haar Wavelet Transform (HWT) due to achieved imperceptibility and robustness comes from PSNR and NC value. Firstly, HWT applied in host image and then selected subband LL. LL subband will be divided into an 8x8 matrix in which each matrix was applied using DCT. Copyright embedded at the DC coefficient. In this paper we choose PSNR to measure the imperceptibility. Meanwhile, to measure the extracted copyright we used correlation coefficient. The results of this simulation method getting high PSNR value with an average of 43.2392 dB. Experiment results of extraction has tested using image watermarking attacks are JPEG compression, low pass filtering, mid filtering, unsharp filter, gaussian noise, cropingp, blurring, salt and pepper with the average value of the correlation coefficient of 0.8676. Our results proved that HWT-DCT has fulfilled the purpose of image watermarking, namely copyright protection. Keywords─ Haar Wavelet Transform, Discrete Cosine Transform, PSNR, Correlation Coefficient, Image Watermarking

Download di sini

#semuanyaajib

Read More...