Achmad Hidayatno
Departemen Teknik Elektro, Fakultas Teknik, Universitas Diponegoro, Jl. Prof. Sudharto, SH, Kampus UNDIP Tembalang, Semarang 50275, Indonesia

Published : 59 Documents
Articles

ANALISIS TRANSFORMASI BALIK CITRA IRIS MENGGUNAKAN WAVELET HAAR BERDASARKAN FAKTOR RETENSI KOEFISIEN WAVELET Wicaksono, Agung; Isnanto, R. Rizal; Hidayatno, Achmad
TRANSMISI Vol 14, No 4 (2012): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Abstract Wavelet is one method that can be used as a step to recognition an individual. Wavelet is used to perform an image feature extraction. In the process of image texture analysis, showed the value of the coefficients of a wavelet. The magnitude of the coefficients obtained using wavelet feature extraction is influenced by several factors. Besides affected by the type of wavelet used, is also influenced by the magnitude of the wavelet decomposition level of itself. In the wavelet is known as the wavelet energy retention, which means the number of retained energy after undergoing a process of decomposition and cutting coefficients. During the decomposition process, the calculation for texture analysis is often a constraint. In order for the current calculation lighter texture analysis, necessary to the process of cutting coefficients based on the retention factor of the wavelet coefficients. Based on these issues, created a program to analyze the influence of variations in the level of wavelet decomposition and coefficient of variation coefficient of cutting a cut on the image. The object of this final project is 30 iris image that has been converted into polar form presented. Having experienced the process of cutting coefficients, to prevent the image of the reverse transformation has a big difference to the original image, in this study was calculated Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Euclidean distance to determine the level of similarity of image input and output images. The Highest values of Retention​, MSE and the Euclidean distance is obtained at the level of decomposition of 1 and the lowest at the level of decomposition 6. While the truncated coefficient and PSNR values ​​obtained at the highest level of decomposition of 6 and the lowest level of decomposition of 6. The variation coefficient of pieces, value retention and highest PSNR obtained at koefsien piece 5 and the lowest coefficient of 50 pieces. While the coefficient value is truncated, MSE and the highest Euclidean distance is obtained at koefsien pieces 50 and the lowest coefficient of 5 pieces. Keywords: iris, texture analysis, Haar wavelet transform, MSE, PSNR, Euclidean distance
APLIKASI PENCIRIAN DENGAN LINEAR PREDICTIVE CODING UNTUK PEMBELAJARAN PENGUCAPAN NAMA HEWAN DALAM BAHASA INGGRIS MENGGUNAKAN JARINGAN SARAF TIRUAN PROPAGASI BALIK Rohman, Sigit Nur; Hidayatno, Achmad; Zahra, Ajub Ajulian
TRANSMISI Vol 14, No 4 (2012): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Abstract In this research designed a recognition system for learning the pronunciation of the word animal names in English. Original speech signal sample at 8000 Hz pick out a small portion For voice parameter extraction process used method Linear Predictive Coding (LPC​​) to obtain cepstral coefficients. LPC cepstral coefficients are transformed into the frequency domain with Fast Fourier Transform (FFT). For decision making process of the introduction and use Neural Networks (NN) back propagation. Testing is done using the data train, according to a database of test data and test data do not fit database. While the networks do a variation of 3, 4 and 5 hidden layers respectively for 1, 2 and 3 the number of syllables said. Based on the results of testing training data, the recognition rate for each variation of each network the number of syllables showed no difference in test results, the percentage was 99% for the 1 syllable, 98.5% for the 2 syllables and 100% for 3 syllables. Test data suitable for testing the database, the highest recognition rate for type 1 syllable is a network with 4 hidden layers using a variation of the percentage is 85%, whereas type 2 syllables highest recognition rate using a variation of 5 hidden layers with the correct percentage of 75% and 81.67 % for type 3 syllables using 5 hidden layers. While the test results do not fit the test database, the highest recognition rate for type 1 syllable is a network with 4 hidden layers using a variation of the percentage is 15.83% while the type 2 syllables highest recognition rate using a variation of 3 hidden layers with percentage correct, 20.83% and 33.33% for type 3 syllables using 3 and 4 hidden layers. Keywords : Linear Predictive Coding, Fast Fourier Transform, Neural Network, Backpropagation.
DETEKSI SUDUT MENGGUNAKAN KODE RANTAI UNTUK PENGENALAN BANGUN DATAR DUA DIMENSI Hastawan, Ahmad Fashiha; Hidayatno, Achmad; Isnanto, R. Rizal
TRANSMISI Vol 15, No 1 (2013): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1154.048 KB)

Abstract

Abstrak   Sistem computer vision yang handal diperlukan untuk melakukan sistem pengenalan yang konsisten terhadap beberapa kemungkinan gangguan, terutama untuk pengenalan objek  yang memiliki karakteristik khusus, seperti bangun datar dua dimensi. Dengan Salah satu metode yang diterapkan adalah dengan menggunakan deteksi sudut (corner detection). Terdapat beberapa macam algoritma deteksi sudut, salah satunya adalah dengan menggunakan kode rantai (chain code). Dalam PENELITIAN ini sistem pendeteksian sudut menggunakan kode rantai untuk pengenalan bangun datar dua dimensi ini dibuat dengan menggunakan software Matlab dengan memperhatikan beberapa faktor yang mempengaruhi kehandalan sistem. Perancangan dilakukan dengan membuat sistem pengenalan yang memiliki beberapa tahap diantaranya adalah tahap prapengolahan, tahap ekstraksi ciri, tahap identifikasi ciri,serta tahap pengenalan.  Dari hasil pengujian terhadap sistem, setiap tahap proses dalam sistem pengenalan menghasilkan keluaran sesuai yang diharapkan. Untuk pengujian sistem terhadap data yang diuji, didapatkan persentase pengujian bentuk bangun datar dua dimensi terhadap variasi warna adalah sebesar 100%, pengujian terhadap variasi ukuran adalah sebesar 95,24%, pengujian terhadap variasi posisi adalah sebesar 100%, pengujian terhadap variasi jarak hasil capture kamera webcam sebesar 88,09%, pengujian terhadap keakuratan deteksi sudut bangun tak beraturan sebesar  90%, dan pengujian terhadap variasi warna dan  latar objek sebesar 100%. Kata Kunci : Bangun Datar Dua Dimensi, Deteksi Sudut, Kode Rantai     Abstract   Solid vision computer system is needed to do a consistent recognizing system through some disturbance possibilities, especially for object recognitions which has special characteristic such as two dimensions shape. By this two dimensions shape recognition system, it is approximated can ease robot or shape recognition automatic hardware in doing its job. One of the used method is corner detection. There are some corner detection algorithms. One of them is chain code. This corner detection system using chain code for  two dimensions shape recognition system is built by Matlab software with giving special attention to some factors that influence the system solidity. Designing is done by building recognition system that has some stages, such as pre-processing stage, feature extraction stage, and recognition stage. From the system testing, every stage process gives expected results. Testing of two dimensions shape with color varying gives 100%, testing of size varying gives 95.24%, testing of position varying gives 100%, testing of object distance captured by webcam gives 88.09% ,testing the accurancy of the detection angle irregular shape gives 90%, and testing of object and background color variations gives 100%.   Key Words : Two dimensions shape, corner detection, chain code.
Aplikasi Pengenalan Ucapan Sebagai Pengatur Mobil Dengan Pengendali Jarak Jauh Ajulian Z., Ajub; Hidayatno, Achmad; Widyanto Tri Saksono, Muhammad
TRANSMISI Vol 10, No 1 (2008): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Growth in Digital signal processing technology gives positives influences in human life. One of the branch of science that gives significant influence is digital speech processing. It can be expand into some applications that make human life easier. Digital speech processing is appropriate to speech recognition.Speech recognition is used to arrange the movement of remote control car. The remote control car will move according to our speech.  This final project is closely related with speech recognition.  The LPC (Linear Predictive Coding) method will extract the speech signal features and HMM (Hidden Markov Model) to modelling the speech signal are used. It is done by comparing model from extracting  feature that is available in HMM modelling. Models will be used in the speech recognition process, if the models have highest level of conformity.The experiment has been done in two conditions, i.e ideal condition in room wih low noise level and unideal condition in room with noise. Result of the experiment from the whole sistem performace at ideal condition is 97,71% for people that have been inputed in the database, and 95,42% for people which have not been inputed in the database. Result of the experiment of database say it regulary is 97,14%. Result of the experiment of database at unideal condition is 54,28% for inputing word at noisy area, result of the experiment of database for inputing word at high frequency from siren voice is 98,57% and result of the experiment of inputing similar word with database is 97,6%Keywords: speech recognition, LPC, HMM
Identifikasi Keberadaan Tumor Pada Citra Mammografi Menggunakan Metode Run Length Santoso, Imam; Hidayatno, Achmad; Ghara Pratama, Andrio
TRANSMISI Vol 10, No 1 (2008): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Breast cancer is one of the most cancer disease among women until now. This cancer was formed by abnormal cells in breast tissue. For early breast cancer detection the mammography is used by the radiologyst. In mammography the breast tissue is scanned by Xrays then a resulting  image called mammogram produce. The radiologyst manually examine the mammogram identifying which area of scanned breast tissue that could have cancer suspect. In medical term the cancer appear as a mass or microcalcification. Because of the quality of mammograms and small of cancer area in early stadium the radiologist sometime have the problem to decide if there is a cancer perform as a mass or microcalcification. According to mammograms that can be viewed as texture image, the image processing especially   texture analysis computerizely helped the radiologist to classify the texturize cancer area. In this research one of  the texture analysis methods named run length method use to get the features. With this features, k-NN (k-Nearest Neighbour) classifier then decide whether the suspect area is cancer according to the mass or microcalcification appeareance or just normal tissue. As the result there is 72% correct identification among the mammograms data that have been analyzed texturizely with run length method.
Pewujudan Tapis Digital FIR Pemilih Frekuensi Menggunakan DSK TMS320C6713 Erwin, Gidion; Hidayatno, Achmad; Darjat, Darjat
TRANSMISI Vol 12, No 1 (2010): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Digital frequency selector filter is the simplest application of digital signal processing, in which process only passing signal with specific desired frequency or band frequency. Digital frequency selector filter can be implemented as software or hardware. In this final project, frequency selector filter is implemented as hardware using DSK (Digital Signal Processor Starter Kit)  TMS320C6713. In this final project, designed three type of  frequency selector filter : Low Pass Filter (LPF), High Pass Filter (HPF), and Band Pass Filter (BPF) with filter length (N) and cut-off frequency (Fc) variation. Filter coefficient is the final product of design stage. FDATool Matlab is used to help filter design and filter coefficient calculation. Then, this filter coefficient is implemented as digital filter in DSK TMS320C6713 using CCS (Code Composer Studio) v.3.1. In CCS, it is also arranged some source code to initialize internal peripheral device on DSK TMS320C6713 (Codec, McBSP, etc), initialize interrupt mode, and initialize memory mapping. Based on experiment’s result, it’s known that the implemented’s magnitude response  approriate with FDATool’s magnitude response (frequency selector filter algorithm was successfully implemented in DSK TMS320C6713). However, gain’s value at pass band region is not exactly 0 dB because resistance losses from cables and the low precision of measurement device. Based on experiment’s result, it’s also known that filter with higher filter length produces better magnitude response characteristics, especially narrower transition width characteristic. Keyword :   digital signal processing, digital filter, frequency selector filter, DSK TMS320C6713.
Rancang Bangun Perangkat Lunak Komunikasi Radio Adeunis Radio Frequency (ARF)7429B pada Sistem Radar Sekunder Utama, Zaini Agung; Darjat, Darjat; Hidayatno, Achmad
TRANSMISI Vol 12, No 3 (2010): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Adeunis Radio Frequency (ARF)7429B is a hardware module which will be used for the application of radio communication in secondary radar system. ARF module has AT Command and Register which can be accessed by using a software. This research is a designing and  making to integrate between ARF hardware and MATLAB software. The accessing process of ARF itself is in two ways through Universal Serial Bus (USB) computer. ARF module has frequency between 902-928 MHz which is divided into 50 channels. The exchanging  process of information between ARFs happens without cable (wireless) using Frequency Shift Keying (FSK) modulation. The AT command can be accessed only by using software in microcontroller or  computer. The command given in this communication is appropriated with the character of AT command itself, therefore the accessing process can be happened. The data input and output received in ARF communication is ASCII character. In transmitting process of information. The data is carried in channels randomly by using Frequency Hopping Spread Spectrum (FHSS) method. Keyword :   Adeunis Radio frequency (ARF)7429B, MATLAB, Secondary Radar, Receiving and Transmitting Data.
Pengenalan Citra Iris Mata Menggunakan Alihragam Wavelet Daubechies Orde 4 Hartanto, Antonius Dwi; Isnanto, R. Rizal; Hidayatno, Achmad
TRANSMISI Vol 12, No 4 (2010): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Iris is a part of the circle around the eye pupil. Iris has a very unique pattern, different in each individual. On this basis the iris can be used as the basis for the introduction of biometrics. To identify the texture of the iris in an eye image, method of texture analysis can be used. There are several methods of texture analysis, one of which is to use a wavelet based on image feature extraction energy. The analysis uses the energy characteristics contained in wavelet transform. Based on that reason, in this research an application program to identify the iris of the eye based on Daubechies order 4 wavelet transform.  Eye image used in this research was acquired and processed, beginning take on the characteristics and texture of the iris image which converted into polar form. Then the feature extraction is done using Daubechies wavelet transform order 4. The characteristics obtained is in the form of the energy value. The next stage is the recognition  using nearest normalized Euclidean distance. Tests carried out in the research consist of four types: influence of sample database, influence of the decomposition level of Daubechies wavelet transform order 4, influence of different input image formats, and testing on eye images which are not in database. From the test results, it can be concluded that the highest recognition rate with the parameters shown in testing Daubechies wavelet transform order 4 level 4 with two samples iris image stored is 86.66%. The lowest recognition rate is shown in tests with Daubechies wavelet transform order 4 level 6 with one sample iris image stored is 62.5%. Then from the results of testing the influence of different input image formats, it can be concluded that the samples taken from 40 individuals which one sample is take for each person, use the format BMP as  well as with use JPEG format. Whereas, from the test result for eye images which are not in database with threshold 0.3559, of the recognition level is 96%. Keyword :   texture analysis, Daubechies wavelet transform order 4, iris, Euclidean distance
Aplikasi Metode Template Matching untuk Klasifikasi Sidik Jari Leksono, Bowo; Hidayatno, Achmad; Isnanto, R. Rizal
TRANSMISI Vol 13, No 1 (2011): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

The development of image processing technologies now provide the possibility of human to create a system that can recognize a digital image. One method to recognize a digital image is the template matching. This method serves to find small parts of the image that matches the template image. Among the technologies to solve the problem of image processing is a system of classifying fingerprints into the form of software that is able to process the fingerprint image enhancement and match fingerprint images that have been recorded by the database system and classify fingerprints into a particular class. In this final project made ​​an application that aims to classify the fingerprint image into a particular class using template matching method.Classification process is started with fingerprint image acquisition, images size distorting 256x256, grayscale(gray level), histeq (histogram equalization), binary (image distorting becomes two scales black and white), thinning, image gets to aim, and resize 32x32. The process will then be calculated percentage of similarity with the template fingerprint image file by using the calculation of NC (Normalized Cross Correlation). The biggest percentage value indicates that the template matches the fingerprint image files. The experiment has been done classification process as much as 61 input fingerprint image with each 5 image formats are *.bmp, *.gif, *.jpg, *.png, and *.tif, so the total input fingerprint image as much as 305. For image format type *.bmp, *. gif, *. png, and *.tif on type template Plain Arch, Plain Whorl, and Double Loop point out that its success zoom as big as 100%. On Tented Arch increase supreme success on image format *.bmp, *. jpg, *. png, *. tif, on Ulnair Loop increase supreme success on image format *.png, *. tif and Radial Loop increase supreme success on image format *.bmp, *. png, *. tif. Image format that right usually experience fault which is on success zoom is contemned to image format *.jpg to type template Plain Arch, Radial Loop, Plain Whorl and Double Loop, then for image format *.gif on type template Tented Arch and Ulnair Loop. Keyword : image processing, fingerprint, template matching
Penyembunyian Data Rahasia pada Citra Digital Berbasis Chaos dan Discrete Cosine Transform Prabowo, Anton; Hidayatno, Achmad; Christyono, Yuli
TRANSMISI Vol 13, No 2 (2011): TRANSMISI
Publisher : TRANSMISI

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (71.575 KB)

Abstract

Steganography is one of technique that developed to keep the security of data by hidding or embedding it in other data media so that it’s content or even it’s existence is not notice. Many steganography methode have been developed in the last few years, but it still needed a steganography system with highest capacity and robustness. By combining and modifying few technic, in this Final Project has made a steganography system that used to embedding and extracting secret data in image data form (BMP 8 bit grayscale and 24 bit color), voice data form (WAV PCM 11.025 KHz 8 bit mono), and text data form (TXT) into cover data in image data form (BMP 8 bit grayscale). Data hidding was done at frequency domain by applying DCT (Discrete Cosine Transform) and chaos theory was applied using logistic map equation. Program was made using Borland Delphi 7 programming language. By using subjectif quality, RMS (Root Mean Square) metrics, and similarity ratio measurement parameter, program performance was observed by doing research consist of: research of initialitation parameter change influences; research of embedding and extracting secret digital data in image, voice, and text form into cover digital data in image form; research of program realibility from data manipulation operation including brigthness modification, contrast modification, resizing, cropping, and JPEG compression. Keyword : steganography, discrete cosine transform, chaos theory, logistic map, root mean square.