scispace - formally typeset
Search or ask a question
Author

Ledya Novamizanti

Bio: Ledya Novamizanti is an academic researcher from Telkom University. The author has contributed to research in topics: Digital watermarking & Discrete wavelet transform. The author has an hindex of 6, co-authored 70 publications receiving 183 citations.

Papers published on a yearly basis

Papers
More filters
Journal ArticleDOI
08 Dec 2020
TL;DR: Pengenalan sidik jari merupakan bagian dari teknologi biometrik. as discussed by the authors menggunakan Convolutional Neural Network (CNN) dengan model arsitektur Residual Network-50 (ResNet-50) untuk mengembangkan sistem klasifikasi sidik Jari sebesar 11,79%.
Abstract: Pengenalan sidik jari merupakan bagian dari teknologi biometrik. Klasifikasi sidik jari yang paling popular adalah Henry classification system. Henry membagi sidik jari berdasarkan garis polanya menjadi lima kelas yaitu arch (A), tented arch (T), left loop (L), right loop (R), dan whorl (W). Penelitian ini menggunakan Convolutional Neural Network (CNN) dengan model arsitektur Residual Network-50 (ResNet-50) untuk mengembangkan sistem klasifikasi sidik jari. Dataset yang digunakan diperoleh dari website National Institute of Standards and Technology (NIST) berupa citra sidik jari grayscale 8-bit. Hasil pengujian menunjukkan bahwa pemrosesan awal Contrast Limited Adaptive Histogram Equalization (CLAHE) dalam model CNN dapat meningkatkan performa akurasi dari sistem klasifikasi sidik jari sebesar 11,79%. Pada citra tanpa CLAHE diperoleh akurasi validasi 83,26%, sedangkan citra dengan CLAHE diperoleh akurasi validasi 95,05%.

19 citations

Journal ArticleDOI
TL;DR: The simulation result performs that GA is useful to search the value of parameter that produces controllable the combination between robustness, invisibility and capacity, and improves the method by determining the exactvalue of parameter achieving BER, PSNR and payload.
Abstract: data in an image file is needed by its owner to set his ownership in a logo as a watermark embedded in the image file. Hiding the logo in the image was done in several methods. One of the method is domain transform using 2D-DCT in which data is embedded in frequency domain of the image. First, the host RGB image is converted to certain color space. The available and chosen color spaces are RGB, YCbCr or NTSC. The layer in which the watermark is embedded also can be selected. The available choices are 1 st layer, 2 nd layer, 3 rd layer, 1 st & 2 nd layer, 2 nd & 3 rd layer, 1 st & 3 rd layer and all layers. After the selected layer of image in certain color space is transformed in block based to frequency domain by DCT, one bit watermark is embedded on the AC coefficient of each block such a way that the bit is represented by specific value called delta in a zigzag and vary length of pixel. The vary parameters optimized by Genetics Algorithm are selected color space, selected layer, block size, length of pixel to be embedded by one bit watermark, and delta. Bit “1” is represented by +delta, and bit “0” is represented by –delta in vary length of pixel after zigzag. The simulation result performs that GA is useful to search the value of parameter that produces controllable the combination between robustness, invisibility and capacity. Thus, GA improves the method by determining the exact value of parameter achieving BER, PSNR and payload.

16 citations

Journal ArticleDOI
TL;DR: In this paper, the authors proposed a multiple basis reweighted analysis (M-BRA) method to improve the signal sparsity in M-BP reconstruction methods and achieved a signal-to-noise ratio (SNR) of 30dB for MRI data on a sampling ratio of M / N = 0.3.

15 citations

Proceedings ArticleDOI
16 Jul 2019
TL;DR: A system for measuring cholesterol levels through eye images has been designed so that it can facilitate a person in detecting cholesterol levels early and the results of the measurement model will be used to determine cholesterol levels.
Abstract: Cholesterol is a complex fat compound, which is produced from the body and food substances. Cholesterol is needed by the body for the formation of cell walls and as a raw material for several hormones. But if the cholesterol content in the blood is excessive, it will cause the disease. To find out cholesterol levels in the blood, a laboratory check is usually done by taking blood samples. However, in the world of iridology, a technique for analyzing disease and weakness in the body is based on the shape and structure of the iris. One of the diseases that can be analyzed through the iris is cholesterol. Cholesterol, through the iris is marked by a change in iris pattern called Arcus Senilis. To see the cholesterol ring in the eye is not easy, because everyone has a different iris structure so that it becomes a characteristic of identification with someone. In this research, a system for measuring cholesterol levels through eye images has been designed so that it can facilitate a person in detecting cholesterol levels early. The process to be carried out starts from taking 60 training eye images and 30 test eye images using a mobile camera. Then the results of the photograph will be carried out using the feature extraction using FLBP and obtain the best FLBP operator there is sampling point 8 and radius 4 with $\mathrm{F}=7$ . After knowing the characteristic value, it was analyzed using linear regression to obtain measurement modeling. The results of the measurement model will be used to determine cholesterol levels. The results in this study are still quite large at 38.28 with a computational time of 11 seconds for each test image.

15 citations

Journal ArticleDOI
01 Jan 2017
TL;DR: Robustness in the proposed method has reached perfect watermark quality with BER=0.01, and the watermark image quality by PSNR parameter is also increased about 5 dB than the watermarked image quality from previous method.
Abstract: Data hiding in an image content is mandatory for setting the ownership of the image. Two dimensions discrete wavelet transform (DWT) and discrete cosine transform (DCT) are proposed as transform method in this paper. First, the host image in RGB color space is converted to selected color space. We also can select the layer where the watermark is embedded. Next, 2D-DWT transforms the selected layer obtaining 4 subband. We select only one subband. And then block-based 2D-DCT transforms the selected subband. Binary-based watermark is embedded on the AC coefficients of each block after zigzag movement and range based pixel selection. Delta parameter replacing pixels in each range represents embedded bit. +Delta represents bit "1" and –delta represents bit "0". Several parameters to be optimized by Genetics Algorithm (GA) are selected color space, layer, selected subband of DWT decomposition, block size, embedding range, and delta. The result of simulation performs that GA is able to determine the exact parameters obtaining optimum imperceptibility and robustness, in any watermarked image condition, either it is not attacked or attacked. DWT process in DCT based image watermarking optimized by GA has improved the performance of image watermarking. By five attacks: JPEG 50%, resize 50%, histogram equalization, salt-pepper and additive noise with variance 0.01, robustness in the proposed method has reached perfect watermark quality with BER=0. And the watermarked image quality by PSNR parameter is also increased about 5 dB than the watermarked image quality from previous method.

14 citations


Cited by
More filters
Journal ArticleDOI

[...]

08 Dec 2001-BMJ
TL;DR: There is, I think, something ethereal about i —the square root of minus one, which seems an odd beast at that time—an intruder hovering on the edge of reality.
Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

33,785 citations

01 Nov 2012
TL;DR: Improved Histogram Equalization of quadratic forms brightness equalization process outside of the existing limited imaging Histograms Equalization to fit in the hardware design and implementation of the first order by the implementation.
Abstract: Histogram Equalization, the most typical algorithm for improving the image quality of algorithms that can effectively implement measures presented in this paper. Improved Histogram Equalization of quadratic forms brightness equalization process outside of the existing limited imaging Histogram Equalization to fit in the hardware design and implementation of the first order by the implementation. And our hardware was proved through the experimental performance

55 citations

Journal ArticleDOI
TL;DR: In this paper, a hybrid data compression algorithm was proposed to increase the security level of the compressed data by using RSA (Rivest-Shamir-Adleman) cryptography.
Abstract: Data compression is an important part of information security because compressed data is more secure and easy to handle. Effective data compression technology creates efficient, secure, and easy-to-connect data. There are two types of compression algorithm techniques, lossy and lossless. These technologies can be used in any data format such as text, audio, video, or image file. The main objective of this study was to reduce the physical space on the various storage media and reduce the time of sending data over the Internet with a complete guarantee of encrypting this data and hiding it from intruders. Two techniques are implemented, with data loss (Lossy) and without data loss (Lossless). In the proposed paper a hybrid data compression algorithm increases the input data to be encrypted by RSA (Rivest–Shamir–Adleman) cryptography method to enhance the security level and it can be used in executing lossy and lossless compacting Steganography methods. This technique can be used to decrease the amount of every transmitted data aiding fast transmission while using slow internet or take a small space on different storage media. The plain text is compressed by the Huffman coding algorithm, and also the cover image is compressed by Discrete wavelet transform DWT based that compacts the cover image through lossy compression in order to reduce the cover image’s dimensions. The least significant bit LSB will then be used to implant the encrypted data in the compacted cover image. We evaluated that system on criteria such as percentage Savings percentage, Compression Time, Compression Ratio, Bits per pixel, Mean Squared Error, Peak Signal to Noise Ratio, Structural Similarity Index, and Compression Speed. This system shows a high-level performance and system methodology compared to other systems that use the same methodology.

50 citations

Journal ArticleDOI
TL;DR: Experimental results proved that auto landmark localization with the proposed feature extraction technique is an efficient approach towards developing a robust HGR system.
Abstract: Due to the constantly increasing demand for the automatic localization of landmarks in hand gesture recognition, there is a need for a more sustainable, intelligent, and reliable system for hand gesture recognition. The main purpose of this study was to develop an accurate hand gesture recognition system that is capable of error-free auto-landmark localization of any gesture dateable in an RGB image. In this paper, we propose a system based on landmark extraction from RGB images regardless of the environment. The extraction of gestures is performed via two methods, namely, fused and directional image methods. The fused method produced greater extracted gesture recognition accuracy. In the proposed system, hand gesture recognition (HGR) is done via several different methods, namely, (1) HGR via point-based features, which consist of (i) distance features, (ii) angular features, and (iii) geometric features; (2) HGR via full hand features, which are composed of (i) SONG mesh geometry and (ii) active model. To optimize these features, we applied gray wolf optimization. After optimization, a reweighted genetic algorithm was used for classification and gesture recognition. Experimentation was performed on five challenging datasets: Sign Word, Dexter1, Dexter + Object, STB, and NYU. Experimental results proved that auto landmark localization with the proposed feature extraction technique is an efficient approach towards developing a robust HGR system. The classification results of the reweighted genetic algorithm were compared with Artificial Neural Network (ANN) and decision tree. The developed system plays a significant role in healthcare muscle exercise.

33 citations