Object Identification by Signal Gain and Correlation

In this study, “ring rotation invariant transform” techniques are used to add more salient feature to the original images. The “ring rotation invariant transform” can solve image rotation problem, which transfers a ring signal to several signal vectors in the complex domain, whereby to generate invariant magnitude. Matrix correlation is employed to combine these magnitudes to generate the various discriminators, by which to identify objects. For managing image-shifting problem, one pixel in sample image is compared with surrounding pixels of unknown image. The comparison approaching in this study is by the basis of pixel-to-pixel-comparisons.

PENGENALAN BUAH KOPI BERDASARKAN PARAMETER WARNA MENGGUNAKAN ALGORITMA BACKPROPAGATION DAN ALGORITMA SUPPORT VECTOR MACHINE (SVM)

Salah satu kopi arabika unggulan Indonesia adalah Kopi Lintong yang berasal dari Sumatera Utara. Peneliti akan melakukan 2 percobaan yaitu percobaan I untuk memperoleh model terbaik dalam melakukan klasifikasi buah kopi arabika varietas Sigarar Utang. Sedangkan percobaan II dilakukan untuk mengetahui objek mana yang lebih baik digunakan dalam klasifikasi kopi berkualitas berdasarkan parameter warna, apakah buah kopi atau biji kopi. Dataset yang digunakan pada percobaan I adalah berupa 250 gambar buah kopi kualitas baik dan 250 gambar buah kopi kualitas kurang yang diambil langsung dari KSU POM Humbang Cooperative. Kemudian dilakukan image preprocessing yang menghasilkan 2500 gambar baru. Sedangkan dataset yang digunakan pada percobaan II adalah data buah kopi dan biji kopi. Buah kopi terdiri dari 240 gambar buah kopi baik dan 240 gambar buah kopi cacat hasil image rotation. Biji kopi terdiri dari 240 gambar biji kopi baik dan 240 gambar biji kopi cacat. Data tersebut kemudian akan dilakukan ekstraksi fitur dengan menggunakan metode HSV (Hue, Saturation, Value). Selanjutnya akan dilakukan proses learning menggunakan algoritma Backpropagation dan algoritma Support Vector Machine dengan tiga jenis kernel yaitu RBF, polynomial, dan sigmoid. Berdasarkan pengujian yang telah dilakukan, maka diperoleh hasil pada percobaan I menghasilkan model klasifikasi terbaik dengan menggunakan algoritma SVM dengan kernel RBF menghasilkan nilai akurasi sebesar 86% dan nilai f-score sebesar 86%. Untuk percobaan II memperoleh hasil bahwa buah kopi dan biji kopi baik digunakan sebagai objek dalam pengenalan buah kopi berdasarkan fitur warna dengan menggunakan machine learning.

Analysis Methods Used to Extract Fingerprints Features

The fingerprint is used in many vital applications important to humans, which requires searching for an effective way to extract the characteristics of the fingerprint. In this paper we will study some of the most popular methods used to extract fingerprints features. For each method the efficiency, accuracy, flexibility and sensitivity for image rotation will be experimentally tested, measured, analyzed in order to give good recommendations of how and when to use a certain method of features extraction. A detailed comparison analysis between MLBP, K_means, WPT, Minutiae methods will be done using several color images in various rotation modes to insure the stability of image features.

Development of a method for improving stability method of applying digital watermarks to digital images

A technique for increasing the stability of methods for applying digital watermark into digital images is presented. A technique for increasing the stability of methods for applying digital watermarks into digital images, based on pseudo-holographic coding and additional filtering of a digital watermark, has been developed. The technique described in this work using pseudo-holographic coding of digital watermarks is effective for all types of attacks that were considered, except for image rotation. The paper presents a statistical indicator for assessing the stability of methods for applying digital watermarks. The indicator makes it possible to comprehensively assess the resistance of the method to a certain number of attacks. An experimental study was carried out according to the proposed method. This technique is most effective when part of the image is lost. When pre-filtering a digital watermark, the most effective is the third filtering method, which is averaging over a cell with subsequent binarization. The least efficient is the first method, which is binarization and finding the statistical mode over the cell. For an affine type attack, which is an image rotation, this technique is effective only when the rotation is compensated. To estimate the rotation angle, an affine transformation matrix is found, which is obtained from a consistent set of corresponding ORB-descriptors. Using this method allows to accurately extract a digital watermark for the entire range of angles. A comprehensive assessment of the methodology for increasing the stability of the method of applying a digital watermark based on Wavelet transforms has shown that this method is 20 % better at counteracting various types of attacks

Preserving Information Security Using Fractal-Based Cryptosystem

The chapter intends to propose a hybrid cryptosystem based on a chaotic map and a fractal function. The sequential order of process execution provides a computationally less expensive and simple approach that still designed a secure cryptosystem. A one-dimensional Ricker map and its modified form are employed to initially shuffle the image pixels twice, and also a pseudo-random sequence is generated using both maps. The algorithm implemented a sequence of pixel confusion-diffusion steps using the image rotation and a transcendental anti-Mandelbrot fractal function (TAMFF) and its Mann-iterated fractal function (Sup-TAMFF). Finally, the pixel value of an image obtained in the last step and the recent two pixels of the encrypted image is XORed with the corresponding pseudo-random matrix value to get the cipher image. Subsequently, various performance tests are conducted to verify the suitability of the given method to be used in real-world information transmission.