PENGGUNAAN CITRA HIMPUNAN JULIA SEBAGAI CITRA SAMPUL UNTUK MENYEMBUNYIKAN CITRA RAHASIA

Steganografi dengan metode fraktal (fractal steganography) adalah teknik menyembunyikan informasi atau pesan, yang dapat berupa citra rahasia, dalam suatu citra sampul (cover image) yang berupa citra fraktal (fractal image). Dalam penelitian ini digunakan citra fraktal matematis yaitu citra himpunan Julia dari fungsi komplek z2 – c, dengan memanfaatkan sifat-sifat fraktalnya yaitu antara lain sensitif terhadap nilai awal, kesamaan diri dan iteratif. Pertama, dibahas bagaimana menyembunyikan citra rahasia dalam suatu citra sampul yaitu citra himpunan Julia dari fungsi komplek z2 – c dengan nilai c dijadikan salah satu komponen dari kunci(key) dan juga nggunakan manipulasi warna (RGB) dari citra sampul, suatu pesan berupa citra rahasia yang sudah dikonversi dalam betuk matrik biner 0,1 dapat disembunyikan sehingga menghasilkan citra stego (stego image) yang secara visual sama dengan citra sampulnya dan diharapkan tahan terhadap serangan. Kemudian, dibuat program komputer yang mampu menyembunyikan dan mengambil kembali citra rahasia pada citra sampul himpunan. Dari analisis hasil program komputer yang dibuat, perbandingan antara citra sampul dan citra stego berukuran 512x512 pixel, didapat bahwa rata-rata RMSE 0,2305 dan rata-rata PSNR 60,88 db dari 12 set data uji, hal ini menunjukkan bahwa kedua citra sangat mirip sehingga sulit dibedakan mana citra yang memuat citra rahasia dengan ukuran citra rahasia paling besar 128x85 pixel atau 261.120 bits. Waktu proses penyembunyian citra rahasia rata-rata 1,626 detik (tidak termasuk waktu pembuatan citra sampul) sedangkan waktu proses pengambilan kembali citra rahasia rata-rata 4,526 detik

Fast Fractal Technique using Modified Moment Features on Domain Blocks

In this research, a new technique is suggested to reduce the long time required by the encoding process by using modified moment features on domain blocks. The modified moment features were used in accelerating the matching step of the Iterated Function System (IFS). The main disadvantage facing the fractal image compression (FIC) method is the over-long encoding time needed for checking all domain blocks and choosing the least error to get the best matched domain for each block of ranges. In this paper, we develop a method that can reduce the encoding time of FIC by reducing the size of the domain pool based on the moment features of domain blocks, followed by a comparison with threshold (the selected threshold based on experience is 0.0001). The experiment was conducted on three images with size of 512x512 pixel, resolution of 8 bits/pixel, and different block size (4x4, 8x8 and, 16x16 pixels). The resulted encoding time (ET) values achieved by the proposed method were 41.53, 39.06, and 38.16 sec, respectively, for boat , butterfly, and house images of block size 4x4 pixel. These values were compared with those obtained by the traditional algorithm for the same images with the same block size, which were 1073.85, 1102.66, and 1084.92 sec, respectively. The results imply that the proposed algorithm could remarkably reduce the ET of the images in comparison with the traditional algorithm.

Investigation and Evaluation of Impact Bruising in Guava Using Image Processing and Response Surface Methodology

Simulated impact damage testing was investigated by fractal image analysis using response surface methodology (RSM) with a central composite design (CCF) on quality of ‘Glom Sali’ guava for drop heights (0.2, 0.4, and 0.6 m), number of drops (1, 3, and 5) and storage temperature conditions (10, 20, and 30 °C). After 48 h, impacted fruit were determined and analyzed for bruise area (BA), bruise volume (BV), browning index (BI), total color difference (∆E), image analysis for bruise area (BAI), and fractal dimension (FD) at the bruising region on peeled guava. Results showed that the correlation coefficient (r = −0.6055) between ∆E and FD value was higher than ∆E and either BA (r = 0.3132) or BV (r = 0.2095). The FD variable was determined as a better indicator than conventional measurement (BA or BV) for pulp browning and impact bruising susceptibility. The FD variable also exhibited highest R2adj value (81.69%) among the other five variables, as the highest precision model with high determination coefficient value (R2adj) (>0.8) for impact bruising prediction. Recommended condition of the FD variable to minimize impact bruising was drop height of 0.53 m for five drops under storage at 30 °C. FD variable assessed by image analysis was shown to be a highly capable measurement to determine impact bruising susceptibility in guava fruit.

Partitioned iterated function systems by regression models for head pose estimation

Head pose estimation represents an important computer vision technique in different contexts where image acquisition cannot be controlled by an operator, making face recognition of unknown subjects more accurate and efficient. In this work, starting from partitioned iterated function systems to identify the pose, different regression models are adopted to predict the angular value errors (yaw, pitch and roll axes, respectively). This method combines the fractal image compression characteristics, such as self-similar structures in order to identify similar head rotation, with regression analysis prediction. The experimental evaluation is performed on widely used benchmark datasets, i.e., Biwi and AFLW2000, and the results are compared with many existing state-of-the-art methods, demonstrating the robustness of the proposed fusion approach and excellent performance.

Image Compression Technique Based on Fractal Image Compression Using Neural Network – A Review

Image compression research has increased dramatically as a result of the growing demands for image transmission in computer and mobile environments. It is needed especially for reduced storage and efficient image transmission and used to reduce the bits necessary to represent a picture digitally while preserving its original quality. Fractal encoding is an advanced technique of image compression. It is based on the image's forms as well as the generation of repetitive blocks via mathematical conversions. Because of resources needed to compress large data volumes, enormous programming time is needed, therefore Fractal Image Compression's main disadvantage is a very high encoding time where decoding times are extremely fast. An artificial intelligence technique similar to a neural network is used to reduce the search space and encoding time for images by employing a neural network algorithm known as the “back propagation” neural network algorithm. Initially, the image is divided into fixed-size and domains. For each range block its most matched domain is selected, its range index is produced and best matched domains index is the expert system's input, which reduces matching domain blocks in sets of results. This leads in the training of the neural network. This trained network is now used to compress other images which give encoding a lot less time. During the decoding phase, any random original image, converging after some changes to the Fractal image, reciprocates the transformation parameters. The quality of this FIC is indeed demonstrated by the simulation findings. This paper explores a unique neural network FIC that is capable of increasing neural network speed and image quality simultaneously.

Implementation and Analysis of Fractals Shapes using GPU-CUDA Model

The rapid evolution of floating-point computing capacity and memory in recent years has resulted graphics processing units (GPUs) an increasingly attractive platform to speed scientific applications and are popular rapidly due to the large amount of data that processes the data on time. Fractals have many implementations that involve faster computation and massive amounts of floating-point computation. In this paper, constructing the fractal image algorithm has been implemented both sequential and parallel versions using fractal Mandelbrot and Julia sets. CPU was used for the execution in sequential mode while GPUarray and CUDA kernel was used for the parallel mode. The evaluation of the performance of the constructed algorithms for sequential structure using CPUs (2.20 GHz and 2.60 GHz) and parallelism structure for various models of GPU (GeForce GTX 1060 and GeForce GTX 1660 Ti ) devices, calculated in terms of execution time and speedup to compare between CPU and GPU maximum ability. The results showed that the execution on GPU using GPUArray or GUDA kernel is faster than its sequential implementation using CPU. And the execution using the GUDA kernel is faster than the execution using GPUArray, and the execution time between GPU devices was different, GPU with (Ti) series execute faster than the other models.