Garuda - Garba Rujukan Digital

Penggunaan Gray Level Co-Occurance Matrix Dari Koefisien Aproksimasi Wavelet untuk Deteksi Cacat Tekstil Islamadina, Raihan; Arnia, Fitri; Munadi, Khairul
Jurnal Buana Informatika Vol 6, No 2 (2015): Jurnal Buana Informatika Volume 6 Nomor 2 April 2015
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (501.216 KB)

Pendeteksian cacat tekstil saat ini masih dilakukan secara manualmengakibatkan seseorang sulit mendeteksi lebih dari 60% dari cacat yang ada.Untuk itu, penelitian ini menerapkan metode deteksi cacat tekstil secara otomatismenggunakan Gray Level Co-Occurance Matrix (GLCM) dari koefisienaproksimasi wavelet yang bertujuan untuk mengevaluasi analisis kinerja metode.Tahapannya, sampel citra tekstil dibagi menjadi delapan bagian untukmendapatkan tekstur cacat yang lebih jelas. Bagian tersebut didekomposisikedalam dua level. GLCM dihitung dari koefisien aproksimasi wavelet level satudan dua untuk dijadikan fitur. Penelitian ini dilakukan empat set simulasi citradengan orientasi latar berbeda. Setiap set terdiri dari satu citra noncacat dan duajenis citra cacat. Setiap bagian citra noncacat dihitung jaraknya dengan semuabagian pada citra cacat pertama dan kedua menggunakan jarak euclidean. Hasilsimulasi menunjukkan bahwa GLCM dari koefisien aproksimasi wavelet levelkedua mampu mendeteksi lebih dari 70% dari cacat yang ada.

HISTOGRAM E QUALIZATION SMOOTHING FOR DETERMINING THRESHOLD ACCURACY ON ANCIENT DOCUMENT IMAGE BINARIZATION Dwipayana, Mahendar; Arnia, Fitri; Musliyana, Zuhar
JOURNAL OF INFORMATICS AND COMPUTER SCIENCE Vol 2, No 2 (2016): Oktober 2016
Publisher : Universitas Ubudiyah Indonesia

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

Ancient documents are inheritance that must be preserved. The documents contain historical, scientific, social, religious information, etc. Converting ancient documents into digital image formats is one of ways to preserve the inheritance and can be stored into a computer. However, images of ancientdocuments have many blemishes caused by age, moisture, flood, etc. Therefore, special techniques are needed for those images to be restored and can improve the legibility of the ancient documentsâ images. In this study, the image restoration process uses separation of background and foreground/text on histogram equalization such as research conducted by Fitri Arnia in 2008. Through histogram equalizationimages can be seen the distribution of pixels from the intensity of black color "0" to white "1". The distribution of pixels on histogram equalization describes the curves of foreground/text and curves of background. Among the histogram curves, the determination of thresholdvalues can be done so as to clarify the foreground/text and background areas on images of ancient documents. The lowest point between the two curves is the lowest pixel (local minima) which is used as the threshold value. However, the selection of such threshold values in some cases is very difficult to determine because there are still many fluctuations in the curve at the lowest curve. Therefore, this study proposesa histogram smoothing method in the ancient documentsâ images to minimize curvature fluctuations and to determine more accurate threshold values. In this research, average filtering method is used for smoothing the histogram image. This filter successfully refines the histogram and makes the image of the restoration or binary image display the value of the ancient document image readability increases.Keywords: HistogramEqualization, Smoothing Histogram, Average Filtering, Thresholding

HISTOGRAM E QUALIZATION SMOOTHING FOR DETERMINING THRESHOLD ACCURACY ON ANCIENT DOCUMENT IMAGE BINARIZATION Dwipayana, Mahendar; Arnia, Fitri; Musliyana, Zuhar
JOURNAL OF INFORMATICS AND COMPUTER SCIENCE Vol 2, No 2 (2016): Oktober 2016
Publisher : Ubudiyah Indonesia University

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

Ancient documents are inheritance that must be preserved. The documents contain historical, scientific, social, religious information, etc. Converting ancient documents into digital image formats is one of ways to preserve the inheritance and can be stored into a computer. However, images of ancientdocuments have many blemishes caused by age, moisture, flood, etc. Therefore, special techniques are needed for those images to be restored and can improve the legibility of the ancient documents? images. In this study, the image restoration process uses separation of background and foreground/text on histogram equalization such as research conducted by Fitri Arnia in 2008. Through histogram equalizationimages can be seen the distribution of pixels from the intensity of black color "0" to white "1". The distribution of pixels on histogram equalization describes the curves of foreground/text and curves of background. Among the histogram curves, the determination of thresholdvalues can be done so as to clarify the foreground/text and background areas on images of ancient documents. The lowest point between the two curves is the lowest pixel (local minima) which is used as the threshold value. However, the selection of such threshold values in some cases is very difficult to determine because there are still many fluctuations in the curve at the lowest curve. Therefore, this study proposesa histogram smoothing method in the ancient documents? images to minimize curvature fluctuations and to determine more accurate threshold values. In this research, average filtering method is used for smoothing the histogram image. This filter successfully refines the histogram and makes the image of the restoration or binary image display the value of the ancient document image readability increases.Keywords: HistogramEqualization, Smoothing Histogram, Average Filtering, Thresholding

Penggunaan Gray Level Co-Occurance Matrix Dari Koefisien Aproksimasi Wavelet untuk Deteksi Cacat Tekstil Islamadina, Raihan; Arnia, Fitri; Munadi, Khairul
Jurnal Buana Informatika Vol 6, No 2 (2015): Jurnal Buana Informatika Volume 6 Nomor 2 April 2015
Publisher : Universitas Atma Jaya Yogyakarta

Pendeteksian cacat tekstil saat ini masih dilakukan secara manualmengakibatkan seseorang sulit mendeteksi lebih dari 60% dari cacat yang ada.Untuk itu, penelitian ini menerapkan metode deteksi cacat tekstil secara otomatismenggunakan Gray Level Co-Occurance Matrix (GLCM) dari koefisienaproksimasi wavelet yang bertujuan untuk mengevaluasi analisis kinerja metode.Tahapannya, sampel citra tekstil dibagi menjadi delapan bagian untukmendapatkan tekstur cacat yang lebih jelas. Bagian tersebut didekomposisikedalam dua level. GLCM dihitung dari koefisien aproksimasi wavelet level satudan dua untuk dijadikan fitur. Penelitian ini dilakukan empat set simulasi citradengan orientasi latar berbeda. Setiap set terdiri dari satu citra noncacat dan duajenis citra cacat. Setiap bagian citra noncacat dihitung jaraknya dengan semuabagian pada citra cacat pertama dan kedua menggunakan jarak euclidean. Hasilsimulasi menunjukkan bahwa GLCM dari koefisien aproksimasi wavelet levelkedua mampu mendeteksi lebih dari 70% dari cacat yang ada.

HISTOGRAM E QUALIZATION SMOOTHING FOR DETERMINING THRESHOLD ACCURACY ON ANCIENT DOCUMENT IMAGE BINARIZATION Dwipayana, Mahendar; Arnia, Fitri; Musliyana, Zuhar
JOURNAL OF INFORMATICS AND COMPUTER SCIENCE Vol 2, No 2 (2016): Oktober 2016
Publisher : Ubudiyah Indonesia University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33143/jics.Vol2.Iss2.733

Ancient documents are inheritance that must be preserved. Thedocuments contain historical, scientific, social, religious information, etc.Converting ancient documents into digital image formats is one of ways topreserve the inheritance and can be stored into a computer. However,images of ancientdocuments have many blemishes caused by age,moisture, flood, etc. Therefore, special techniques are needed for thoseimages to be restored and can improve the legibility of the ancientdocumentsâ€™ images. In this study, the image restoration process usesseparation of background and foreground/text on histogram equalizationsuch as research conducted by Fitri Arnia in 2008. Through histogramequalizationimages can be seen the distribution of pixels from the intensityof black color "0" to white "1". The distribution of pixels on histogramequalization describes the curves of foreground/text and curves ofbackground. Among the histogram curves, the determination ofthresholdvalues can be done so as to clarify the foreground/text andbackground areas on images of ancient documents. The lowest pointbetween the two curves is the lowest pixel (local minima) which is used asthe threshold value. However, the selection of such threshold values insome cases is very difficult to determine because there are still manyfluctuations in the curve at the lowest curve. Therefore, this studyproposesa histogram smoothing method in the ancient documentsâ€™ imagesto minimize curvature fluctuations and to determine more accuratethreshold values. In this research, average filtering method is used forsmoothing the histogram image. This filter successfully refines thehistogram and makes the image of the restoration or binary image displaythe value of the ancient document image readability increases.Keywords: HistogramEqualization, Smoothing Histogram, AverageFiltering, Thresholding

Improvement of binarization performance using local otsu thresholding Khairun Saddami; Khairul Munadi; Yuwaldi Away; Fitri Arnia
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 1: February 2019
Publisher : Institute of Advanced Engineering and Science

Ancient document usually contains multiple noises such as uneven-background, show-through, water-spilling, spots, and blur text. The noise will affect the binarization process. Binarization is an extremely important process in image processing, especially for character recognition. This paper presents an improvement to Nina binarization technique. Improvements were achieved by reducing processing steps and replacing median filtering by Wiener filtering. First, the document background was approximated by using Wiener filter, and then image subtraction was applied. Furthermore, the manuscript contrast was adjusted by mapping intensity of image value using intensity transformation method. Next, the local Otsu thresholding was applied. For removing spotting noise, we applied labeled connected component. The proposed method had been testing on H-DIBCO 2014 and degraded Jawi handwritten ancient documents. It performed better regarding recall and precision values, as compared to Otsu, Niblack, Sauvola, Lu, Su, and Nina, especially in the documents with show-through, water-spilling and combination noises.

Moment invariant-based features for Jawi character recognition Fitri Arnia; Khairun Saddami; Khairul Munadi
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 3: June 2019
Publisher : Institute of Advanced Engineering and Science

Ancient manuscripts written in Malay-Arabic characters, which are known as "Jawi" characters, are mostly found in Malay world. Nowadays, many of the manuscripts have been digitalized. Unlike Roman letters, there is no optical character recognition (OCR) software for Jawi characters. This article proposes a new algorithm for Jawi character recognition based on Hu’s moment as an invariant feature that we call the tree root (TR) algorithm. The TR algorithm allows every Jawi character to have a unique combination of moment. Seven values of the Hu’s moment are calculated from all Jawi characters, which consist of 36 isolated, 27 initial, 27 middle, and 35 end characters; this makes a total of 125 characters. The TR algorithm was then applied to recognize these characters. To assess the TR algorithm, five characters that had been rotated to 90o and 180o and scaled with factors of 0.5 and 2 were used. Overall, the recognition rate of the TR algorithm was 90.4%; 113 out of 125 characters have a unique combination of moment values, while testing on rotated and scaled characters achieved 82.14% recognition rate. The proposed method showed a superior performance compared with the Support Vector Machine and Euclidian Distance as classifier.

Binarization of Ancient Document Images based on Multipeak Histogram Assumption Fitri Arnia; Khairul Munadi
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 15, No 3: September 2017
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v15i3.5105

In document binarization, text is segmented from the background. This is an important step, since the binarization outcome determines the success rate of the optical character recognition (OCR). In ancient documents, that are commonly noisy, binarization becomes more difficult. The noise can reduce binarization performance, and thus the OCR rate. This paper proposes a new binarization approach based on an assumption that the histograms of noisy documents consist of multipeaks. The proposed method comprises three steps: histogram calculation, histogram smoothing, and the use of the histogram to track the first valley and determine the binarization threshold. In our simulations we used a set of Jawi ancient document images with natural noises. This set is composed of 24 document tiles containing two noise types: show-through and uneven background. To measure performance, we designed and implemented a point compilation scheme. On average, the proposed method performed better than the Otsu method, with the total point score obtained by the former being 7.5 and that of the latter 4.5. Our results show that as long as the histogram fulfills the multipeak assumption, the proposed method can perform satisfactorily.

Enhancement of Iris Recognition System Based on Phase Only Correlation Fitri Arnia; Nuriza Pramita
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 9, No 2: August 2011
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v9i2.711

Iris recognition system is one of biometric based recognition/identification systems. Numerous techniques have been implemented to achieve a good recognition rate, including the ones based on Phase Only Correlation (POC). Significant and higher correlation peaks suggest that the system recognizes iris images of the same subject (person), while lower and unsignificant peaks correspond to recognition of those of difference subjects. Current POC methods have not investigated minimum iris point that can be used to achieve higher correlation peaks. This paper proposed a method that used only one-fourth of full normalized iris size to achieve higher (or at least the same) recognition rate. Simulation on CASIA version 1.0 iris image database showed that averaged recognition rate of the proposed method achieved 67%, higher than that of using one-half (56%) and full (53%) iris point. Furthermore, all (100%) POC peak values of the proposed method was higher than that of the method with full iris points.

Effectiveness of MPEG-7 Color Features in Clothing Retrieval Arsy Febrina Dewi; Fitri Arnia; Rusdha Muharar
Bulletin of Electrical Engineering and Informatics Vol 6, No 2: June 2017
Publisher : Institute of Advanced Engineering and Science

Clothing is a human used to cover the body. Clothing consist of dress, pants, skirts, and others. Clothing usually consists of various colors or a combination of several colors. Colors become one of the important reference used by humans in determining or looking for clothing according to their wishes. Color is one of the features that fit the human vision. Content Based Image Retrieval (CBIR) is a technique in Image Retrieval that give index to an image based on the characteristics contained in image such as color, shape, and texture. CBIR can make it easier to find something because it helps the grouping process on image based on its characteristic. In this case CBIR is used for the searching process of Muslim fashion based on the color features. The color used in this research is the color descriptor MPEG-7 which is Scalable Color Descriptor (SCD) and Dominant Color Descriptor (DCD). The SCD color feature displays the overall color proportion of the image, while the DCD displays the most dominant color in the image. For each image of Muslim women's clothing, the extraction process utilize SCD and DCD. This study used 150 images of Muslim women's clothing as a dataset consistingclass of red, blue, yellow, green and brown. Each class consists of 30 images. The similarity between the image features is measured using the eucludian distance. This study used human perception in viewing the color of clothing.The effectiveness is calculated for the color features of SCD and DCD adjusted to the human subjective similarity. Based on the simulation of effectiveness DCD result system gives higher value than SCD.

Title

Found 21 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 21 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 21 Documents
Search