Nanik Suciati
Unknown Affiliation

Published : 8 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 8 Documents
Search

CHARACTER IMAGE SEGMENTATION OF JAVANESE SCRIPT USING CONNECTED COMPONENT METHOD Yuna Sugianela; Nanik Suciati
Jurnal Ilmu Komputer dan Informasi Vol 12, No 2 (2019): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (607.599 KB) | DOI: 10.21609/jiki.v12i2.677

Abstract

Automation of Javanese script translation is needed to make it easier for people to understand the meaning of ancient Javanese script. By using Javanese script image as input, the translation system generally consists of character segmentation, character recognition, and combining the recognized characters as a meaningful word. The segmentation which obtains region of interest of each character, is an important process in the translation system. In the previous research, segmentation using projection profile method can separate each character well. The method can overcome characters overlapping, but it still produces truncated characters. In this study, we proposed a new segmentation to reduce the truncated character. The first step of the proposed method is pre-processing that consists of converting input into binary image and cleaning noises. The next step is to determine the connected component labels, which further perform as candidate of characters. Some of the candidates are still represented by more than one labels, so that we need a process to merge the connected component labels that have centroid distance less than threshold. We evaluate the proposed method using Intersection over Union (IoU). The evaluation shows the best accuracy 93,26%.
KUANTISASI SEL DARAH PUTIH BERTUMPUK MENGGUNAKAN ANALISIS DISTANCE MARKER Benny Afandi; Chastine Fatichah; Nanik Suciati
Jurnal Simantec Vol 5, No 3 (2016)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/simantec.v5i3.2384

Abstract

ABSTRAKKuantisasi sel darah putih melalui citra mikroskopis sel darah yang low-cost dan reliable masih menjadi tantangan pada banyak penelitian. Keragaman citra sel darah putihdapat mengurangi akurasi kuantisasi sel darah putih, khususnya keberadaan sel darah putih bertumpuk. Penelitian ini mengusulkan metode baru dalam mengkuantisasi sel darah putih bertumpuk menggunakan analisis distance marker. Setiap objek mempunyai marker yang merupakan local maxima dalam distance transform map. Ketika dua objek bertumpuk, marker kedua objek tetap terbentuk dan terpisah. Informasi nilai jarak marker dapat digunakan sebagai pengkuantisasi objek sel darah putih bertumpuk. Metode analisis distance marker lebih robust terhadap bentuk dan ukuran objek sel darah putih dengan tingkat akurasi mencapai 94,1%.Kata kunci :Analisis distance marker, Citra mikroskopis sel darah, Kuantisasi sel darah putihbertumpuk.ABSTRACTThe low-cost and reliable white blood cells quantization through a microscopic image of blood cells still a challenge in many studies. the diversity of white blood cell microscopic images can decrease the accuracy of white blood cell quantization, particularly the presence of the overlapping white blood cells. This paper proposes a novel method to quantize the overlapping white blood cells using analysis distance marker.Each object has a marker which is a local maximum in the distance transform map. When two objects overlap, the marker of both objects is still formed and separate. The information of distance marker values can be used as the overlapping white blood cells quantization. In addition, the proposed method is robust to the shape and size of the white blood cell objects with the accuracy of 94.1%.Keywords: Analysis distance marker, blood cell microscopic image, overlapping white blood cells quantization
LOCAL LINE BINARY PATTERN FOR FEATURE EXTRACTION ON PALM VEIN RECOGNITION Jayanti Yusmah Sari; Chastine Fatichah; Nanik Suciati
Jurnal Ilmu Komputer dan Informasi Vol 8, No 2 (2015): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information)
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (748.614 KB) | DOI: 10.21609/jiki.v8i2.309

Abstract

In recent years, palm vein recognition has been studied to overcome problems in conventional systems in biometrics technology (finger print, face, and iris). Those problems in biometrics includes convenience and performance. However, due to the clarity of the palm vein image, the veins could not be segmented properly. To overcome this problem, we propose a palm vein recognition system using Local Line Binary Pattern (LLBP) method that can extract robust features from the palm vein images that has unclear veins. LLBP is an advanced method of Local Binary Pattern (LBP), a texture descriptor based on the gray level comparison of a neighborhood of pixels. There are four major steps in this paper, Region of Interest (ROI) detection, image preprocessing, features extraction using LLBP method, and matching using Fuzzy k-NN classifier. The proposed method was applied on the CASIA Multi-Spectral Image Database. Experimental results showed that the proposed method using LLBP has a good performance with recognition accuracy of 97.3%. In the future, experiments will be conducted to observe which parameter that could affect processing time and recognition accuracy of LLBP is needed
Perbaikan Citra Ber-Noise Menggunakan Switching Median Filter dan Boundary Discriminative Noise Detection Ahmad Saikhu; Nanik Suciati; Widhiantantri S.
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2009
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Citra yang mengalami proses editing ataupun kompresi biasanya akan terkontaminasi noiseyang akan mengurangi kualitas citra. Beberapa teknik filtering telah diperkenalkan untuk penghilangan noisecitra. Penelitian ini mengangkat suatu metode dalam penghilangan noise citra yaitu switching median filteryang digabung dengan sebuah metode deteksi noise yang disebut Boundary Discriminative Noise Detection(BDND).Dalam algoritma BDND untuk menentukan apakah suatu piksel termasuk noise atau bukan, makapiksel tersebut diklasifikasikan ke dalam 3 kelompok yaitu noise berintensitas rendah, piksel yang bukannoise, dan noise berintensitas tinggi. Suatu piksel dianggap bukan noise jika piksel termasuk kelompokkedua. Untuk membentuk 3 kelompok dibutuhkan 2 pembatas. Algoritma ini cukup bagus karena dengannoise density mencapai 90% bisa menghasilkan kesalahan deteksi 0.Empat model noise digunakan dalam ujicoba untuk mengevaluasi ketangguhan algoritma BDND. Hasil uji coba pada citra grayscale dan warnadengan range noise density antara 10%-90% menunjukkan bahwa switching median filter yang digabungdengan algoritma BDND mempunyai kinerja yang sangat bagus dalam mengembalikan detil citra dalamrange noise density antara 10% -70%.Kata kunci : switching median filter, penghilangan noise, deteksi noise
Segmentasi Variasi Pencahayaan Citra Tomat Menggunakan Marker Controlled Watershed dan Arimoto Entropy untuk Perbaikan Citra Suastika Yulia Riska; R. V. Hari Ginardi; Nanik Suciati
Jurnal Buana Informatika Vol. 6 No. 3 (2015): Jurnal Buana Informatika Volume 6 Nomor 3 Juli 2015
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v6i3.434

Abstract

Abstract. Tomatoes image acquisition in outdoors condition results in an image that cannot be processed because of lighting variation on the glossy surface. Lighting variation is one of the problems in image processing because the resulting color values on tomatoes is lost from the affected area due to lighting variation. This research is meant to improve the image of tomatoes with lighting variations in the preprocessing stage. Segmentation methods proposed to detect and eliminate lighting variation is marker-controlled watershed with Arimoto entropy. After eliminating the detected area with lighting, tomatoes image are improved in three ways, namely by applying RGB average, searching the value of pixels with pixels index, and using a moving window with various kernel sizes. The error segmentation of the proposed method is by 36.67%, which better than the previous method. The best results tomato image enhancement is by using a moving window with a kernel size 15x15.Keywords: arimoto entropy, image enhancement, marker controlled watershed, preprocessing, segmentation.  Abstrak. Pengambilan citra tomat di luar ruangan mengakibatkan citra tidak dapat langsung diproses karena memiliki variasi pencahayaan pada permukaannya yang glossy. Variasi pencahayaan merupakan salah satu masalah dalam pemrosesan citra tomat karena mengakibatkan hilangnya nilai warna yang dimiliki area yang terkena variasi pencahayaan. Tujuan penelitian ini adalah untuk memperbaiki citra tomat yang terdeteksi memiliki variasi pencahayaan pada tahap preprocessing. Metode segmetasi yang diusulkan pada penelitian ini untuk mendeteksi dan menghilangkan area variasi pencahayaan adalah marker controlled watershed dengan arimoto entropy. Setelah menghilangkan area yang terdeteksi memiliki pencahayaan, citra tomat diperbaiki dengan tiga cara, yaitu dengan rata-rata RGB tomat, pencarian nilai piksel dengan indeks piksel, dan menggunakan moving window dengan berbagai ukuran kernel. Eror segmentasi dari metode yang diusulkan sebesar 36,67%, yaitu lebih baik dari pada metode sebelumnya. Hasil perbaikan citra secara visual menunjukkan hasil yang paling baik dengan menerapkan perbaikan citra menggunakan moving window dengan ukuran kernel 15x15.Kata Kunci: arimoto entropy, marker controlled watershed, perbaikan citra, preprosesing, segmentasi.
Modifikasi Ant Colony Optimization Berdasarkan Gradient Untuk Deteksi Tepi Citra Febri Liantoni; Nanik Suciati; Chastine Fatichah
Jurnal Buana Informatika Vol. 6 No. 3 (2015): Jurnal Buana Informatika Volume 6 Nomor 3 Juli 2015
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v6i3.435

Abstract

Abstract. Ant Colony Optimization (ACO) is an optimization algorithm which can be used for image edge detection. In traditional ACO, the initial ant are randomly distributed. This condition can cause an imbalance ants distribution. Based on this problem, a modified ant distribution in ACO is proposed to optimize the deployment of ant based gradient. Gradient value is used to determine the placement of the ants. Ants are not distributed randomly, but are placed in the highest gradient. This method is expected to be used to optimize the path discovery. Based on the test results, the use of the proposed ACO modification can obtain an average value of the Peak Signal to Noise Ratio (PSNR) of 12.724. Meanwhile, the use of the traditional ACO can obtain an average value of PSNR of 12.268. These results indicate that the ACO modification is capable of generating output image better than traditional ACO in which ants are initially distributed randomly.Keywords: Ant Colony Optimization, gradient, Edge Detection, Peak Signal to Noise Ratio Abstrak. Ant Colony Optimization (ACO) merupakan algoritma optimasi, yang dapat digunakan untuk deteksi tepi pada citra Pada ACO tradisional, semut awal disebarkan secara acak. Kondisi ini dapat menyebabkan ketidakseimbangan distribusi semut. Berdasarkan permasalahan tersebut, modifikasi distribusi semut pada ACO diusulkan untuk mengoptimalkan penempatan semut berdasarkan gradient. Nilai gradient digunakan untuk menentukan penempatan semut. Semut tidak disebar secara acak akan tetapi ditempatkan di gradient tertinggi. Cara ini diharapkan dapat digunakan untuk optimasi penemuan jalur. Berdasarkan hasil uji coba, dengan menggunakan ACO modifikasi yang diusulkan dapat diperoleh nilai rata-rata Peak Signal to Noise Ratio (PSNR) 12,724. Sedangkan, menggunakan ACO tradisional diperoleh nilai rata-rata PSNR 12,268. Hasil ini menunjukkan bahwa ACO modifikasi mampu menghasilkan citra keluaran yang lebih baik dibandingkan ACO tradisional yang sebaran semut awalnya dilakukan secara acak.Kata Kunci: Ant Colony Optimization, gradient, deteksi tepi, Peak Signal to Noise Ratio
Kombinasi Fitur Bentuk, Warna dan Tekstur untuk Identifikasi Kesuburan Telur Ayam Kampung Sebelum Inkubasi Rohman Dijaya; Nanik Suciati; Darlis Herumurti
Jurnal Buana Informatika Vol. 7 No. 3 (2016): Jurnal Buana Informatika Volume 7 Nomor 3 Juli 2016
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v7i3.659

Abstract

Abstract. In the chicken nursery industry (doc) hatching efficiency is obtained by observing the eggs through candling before the incubation process. To sort out infertile eggs the use of fertility image identification thought egg candling is needed before incubation. The focus of this study is to combine the features of shape, texture and color to the area and egg yolk to determine the most dominant features in the image representing firtile egg candling. Features used in this study are the feature of forms: roundness, elongation, Index, Ellips Varriance and Circularity Ratio, moment invariant texture features of the area and the egg yolk, and features HSI color in egg yolks area. The test results show that the highest accuracy is on the features of the new forms of egg yolk with an accuracy of 76.67%. The second highest is shown by the combination of form features (Circularity Ratio, Ellips Varriance) and texture features in the area moment yolk color features HSI with 81.67% accuracy using SVM classification method.Keywords: Egg candling imagery, fertile, infertile, incubation Abstrak. Pada industri pembibitan ayam (doc) efisiensi penetasan telur ayam didapatkan dengan melakukan candling (peneropongan telur) sebelum proses inkubasi menggunakan mesin tetas. Untuk mengklasifikasikan telur fertile dan infertile dibutuhkan identifikasi kesuburan telur menggunakan citra candling sebelum inkubasi. Fokus dari penelitian ini adalah mengkombinasikan fitur bentuk, tekstur dan warna pada area kuning telur dan telur untuk mengetahui fitur yang paling dominan dalam merepresentasikan citra candling telur ayam kampung. Fitur yang digunakan dalam penelitian ini adalah fitur bentuk (Roundness, Elongation, Index, Ellips Varriance dan Circularity Ratio), fitur tektur moment invarian dari area telur dan kuning telur dan fitur warna HSI pada area kuning telur. Hasil pengujian menunjukkan akurasi tertinggi pada fitur bentuk kuning telur baru dengan akurasi 76,67% dan kombinasi fitur bentuk (Circularity Ratio, Ellips Varriance), fitur tekstur moment pada area kuning telur dengan fitur warna HSI dengan akurasi 81,67 % menggunakan metode klasifikasi SVM. Kata Kunci: Citra candling telur, fertile, infertile, inkubasi.
Optic Nerve Head Segmentation Using Hough Transform and Active Contours Handayani Tjandrasa; Ari Wijayanti; Nanik Suciati
Indonesian Journal of Electrical Engineering and Computer Science Vol 10, No 3: July 2012
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Optic nerve head is part of the retina where ganglion cell axons exit the eye to form the optic nerve. Glaucomatous changes related to loss of the nerve fibers decrease the neuroretinal rim and expand the area and volume of the cup. This study implements  the detection of the optic nerve head in retinal fundus images based on the Hough Transform and Active Contour Models. The process starts with the image enhancement using homomorphic filtering for illumination correction, then proceeds with the removal of blood vessels on the image  to facilitate the subsequent segmentation process. The result of the Hough Transform fitting circle becomes the initial level set for the active contour model. The experimental results show that the implemented segmentation algorithms are capable of segmenting optic nerve head with the average accuracy of 75.56%. DOI: http://dx.doi.org/10.11591/telkomnika.v10i3.614