Claim Missing Document
Check
Articles

Pencarian Resep Makanan Berdasarkan Citra Makanan Menggunakan Ekstraksi Fitur Simple Morphological Shape Descriptors dan Color Moment Tri Rahayuni; Yuita Arum Sari; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1250.174 KB)

Abstract

The existing food recipe search application only uses text queries. Text queries often does not represent everything the user wants and cannot be done if user only knows food images. Solution offered to overcome this problem is make food recipe search using food image. Image search is done by measuring similarity between query image features and corpus image features. Features image are obtained by extracting Simple Morphological Shape Descriptors and Color Moment features. After feature extraction, similarity measurements are carried out using Euclidean Distance. Then system display search results which are as many as n images that have the greatest degree of similarity. The results of this study indicate the highest MAP value at k-rank 10 is 95.713% and the lowest MAP value is at k-rank 100 is 76.108%. Color Moment feature is better than Simple Morphological Shape Descriptors because MAP Color Moment value is higher at 93.32% than the Simple Morphological Shape Descriptors is 89.8%. Merging of the two features proved to be able to increase MAP value. It can be concluded that at k-rank 10 system returns good results according to user requirements and the use of the two merged features can overcome disadvantages of using each feature.
Temu Kembali Citra Makanan Menggunakan Ekstraksi Fitur Gray Level Co-occurrence Matrix dan CIE L*a*b* Color Moments Untuk Pencarian Resep Masakan Ahmad Fauzi Ahsani; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (726.903 KB)

Abstract

Recipes retrieval is an important thing in this technological era. Many people use search engine to find preferred food recipes. However, most people still use text query to search. Query text have many disadvantages, one of them is the lack of representation of food object because each person will be different in describing food. This problem can be solved if given query is an image of the food itself. This technique commonly referred as Content Based Image Retrieval. This study proposes image retrieval for cooking recipe searching using Gray Level Co-occurrence Matrix (GLCM) as a texture feature extraction method and CIE L*a*b* Color Moments as a color feature extraction method. The result of this study indicate that the MAP value is 97,604% when using combination of texture and color features, Minkowski distance algorithm and k = 10 with 1303 images of data training and 31 images of data testing. Based on these results, it can be concluded that GLCM and CIE L*a*b* color moments can be used on food image retrieval for searching cooking recipes.
Klasifikasi Citra Makanan Menggunakan Algoritme Learning Vector Quantization Berdasarkan Ekstraksi Fitur Color Histogram dan Gray Level Co-occurrence Matrix Sarah Yuli Evangelista Simarmata; Yuita Arum Sari; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (651.157 KB)

Abstract

Many photos of food we see on social media, but we forget and don't even know the name of the food. Humans ability to recognize and identify is also subjective to external such as fatigue, prejudice and etc. Computers can help by build a system that can recognize and identify food through images. Researches have been conducted that the process of automatically identifying and classifying using computer can save more time compared to identify manually. Food image has different colors and textures. The color feature extraction method used in this research is Color Histogram and for the texture feature extraction is Gray level co-occurrence matrix (GLCM). The classification algorithm used is Learning Vector Quantization (LVQ) with the best parameters that can be used are learning rate (α) 0.1, decreament learning rate 0.1, maximum epoch 2, minimum learning rate 0.01 and gives accuracy that is equal to 53,33%. The test gives 53.33% accuracy for using color and texture extraction. The use of color feature extraction only gives the highest accuracy that is equal to 67.00%, and the use of texture feature extraction only gives accuracy that is equal to 53.33%. From the results, concluded that LVQ algorithm based on Color Histogram feature extraction and GLCM can be used to classify food image but can not give a perfect accuracy.
Klasifikasi Jenis Citra Makanan Tunggal Berdasarkan Fitur Local Binary Patterns dan Hue Saturation Value Menggunakan Improved K-Nearest Neighbor Sarah Najla Adha; Yuita Arum Sari; Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (521.834 KB)

Abstract

To fulfill their basic needs, living things need foods. Foods that have poor quality can cause disease. To avoid this, digital image processing can be used to create a food classification system. Digital image processing is used to analyze features contained in food images. In this study, the feature used to classify the types of food images is a feature of color and texture. Color feature extraction is done by Hue Saturation Value (HSV) color space and texture features using the Local Binary Patterns (LBP) method. Classification is done by the Improved K-Nearest Neighbor (Improved K-NN) method. The test results for the k value indicate that the highest accuracy is obtained at 90.476% with the value of k = 1. When the feature used is only a color feature, the highest accuracy value is obtained at 90.476% with a value of k = 1. When the feature used is only a texture feature, the highest accuracy value is obtained 85.714% with a value of k = 1. The results of testing the classification method showed that the Improved K-NN method produced higher accuracy than the K-NN method with an average accuracy of 80.306%. So the best classification results are obtained by using a combination of color and texture features with the Improved K-NN classification method.
Seleksi Fitur Information Gain Pada Temu Kembali Citra Jenis Makanan Menggunakan Dominant Color Descriptor Dan Gray Level Co-occurence Matrix Sulaiman Triarjo; Yuita Arum Sari; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (511.887 KB)

Abstract

Nutritional information on social media is supported by image of food being reviewed. It requires hard work to explore similar foods that have almost same nutrition. Therefore an information search system is needed to speed up the information search process. This research has been conducted to be able to search for similar informations based on a query in form of image. It uses Dominant Color Descriptor method for color feature extraction and Gray Level Co-occurence Matrix method for texture feature extraction and information gain selection feature to select texture features. The data used were 29 types of food imaged with total is 435 images which each type has 15 images. Testing is done by comparing the performance of calculation of Euclidean distance, Chebyshev distance, and Manhattan distance for texture feature and Quadratic distance and Yang distance for color feature. The evaluation uses MAP value, test result using only the texture feature obtained MAP value of 0,5542 using Euclidean distance and without feature selection. The test result using only color feature obtained MAP value of 0,7488 when using Yang distance. And testing using color feature and texture feature obtained a value of 0,7118 by using Manhattan distance and Yang distance with 10 features. In this research, the use of DCD was more effective than GLCM by producing higher MAP value.
Rekomendasi Multilabel Otomatis Pada Artikel Dengan Algoritme Fuzzy C-Means Dan K-Nearest Neighbor Muhammad Bima Zehansyah; Yuita Arum Sari; Sigit Adi Nugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1039.618 KB)

Abstract

Perkembangan teknologi informasi saat ini sangat cepat khususnya pada media elektronik. Hal tersebut didukung dengan adanya sebuah wadah untuk menyalurkan suatu peristiwa, pendapat, serta gagasan yang berasal dari masyarakat yang disebut citizen journalism yang dikemas dalam bentuk artikel online. Besarnya antusiasme citizen journalism tersebut sayangnya kurang didukung pada pelabelan secara otomatis pada artikel yang akan dibuat, salah satunya terdapat pada situs kompasiana.com dengan adanya pelabelan otomatis diharapkan mempermudah pengguna tanpa perlu melakukan pelabelan secara manual. Salah satu cara melakukan pelabelan otomatis yaitu dengan cara melakukan klasifikasi multilabel yaitu memprediksi label pada suatu artikel yang memungkin artikel tersebut dapat memiliki lebih dari satu label, dengan adanya klasifikasi multilabel juga bertujuan dapat meningkatkan kualitas information retrieval. Metode klasifikasi multilabel salah satunya dengan menggunakan algoritme Fuzzy C- Means dan K Nearest Neighboar (FCM-KNN) dengan adanya proses pengelompokkan pada data diharapkan menghemat waktu komputasi dalam pencarian k tetangga terdekat pada proses klasifikasi Multilabel K Nearest Neighboar (ML-KNN). Pada penelitian ini didapatkan pengujian terbaik saat melakukan proses klasifikasi yaitu saat k = 1, yang mana didapatkan evaluasi F1 = 93,33 % dan evaluasi BEP sebesar 93,75%. Dari hasil didapat menunjukkan bahwa penerapan metode klasifikasi FCM-KNN dapat digunakan untuk melakukan multilabel secara otomatis pada artikel online
Klasifikasi Jenis Makanan dari Citra Smartphone Berdasarkan Ekstraksi Fitur Haralick dan CIE Lab Color Moment Menggunakan Learning Vector Quantization Akhmad Muzanni Safi'i; Yuita Arum Sari; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1388.279 KB)

Abstract

Choosing a food becomes something important for sufferers of certain diseases. However, choosing a food is a problem for people who taste a food for first time or tourists who are visiting a country for first time. To overcome these problems, research needs to be done to identify / classify a food image. The Haralick and CIE Lab Color Moments features are proven to produce good features for classification cases. The Learning Vector Quantization method is also an alternative for classification process. Based on the k-fold cross validation with k = 10 and accuracy as evaluation method, the maximum accuracy is 0.642051 with learning rate parameter value is 0.2, the learning rate multiplier is 0.8, the m value is 0.1, the epsilon value is 0.4, maximum iteration is 10 and minimum learning rate is 0.000001. This result shows that food image classification based on Haralick feature extraction and CIE Lab Color Moment using Learning Vector Quantization produces fairly good accuracy. In addition, the use of both texture (Haralick) and color features (CIE Lab Color Moments) has an effect on the results of accuracy. This is indicated by all the test results which show that the highest accuracy results are achieved using texture and color features.
Klasifikasi Pola Sidik Bibir Untuk Menentukan Jenis Kelamin Manusia Dengan Metode Gray Level Co-Occurrence Matrix Dan Support Vector Machine Eka Novita Shandra; Budi Darma Setiawan; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (515.702 KB)

Abstract

Identification is one way that can be done to recognize individual characteristics. Identification is needed to find out the clarity of personal identity, for both deceased and living people. In the world of forensic medicine, the role of identification is very important. Like fingerprints, lip prints also have unique characteristics for each individual. Lip prints can be used as a means to identify forensic and non-forensic cases. For nonforensic cases, lip prints can determine the sex of an individual. To help in the process of identifying gender based on lip prints, a classification system is needed that can classify the sex of women and men. The process begins with collecting lip print images which are then preprocessed and extracted texture features using the Gray Leveled Co-ocurrence (GLCM) method. There are 4 features that are used namely ASM, Contrast, Correlation and IDM with angles of 0o, 45o, 90o and 135o. Then the feature value is used by data for the training and testing process using the Support Vector Machine (SVM) method. The training data used in the test is 60 data. The results of this study have not provided a good level of accuracy because the system is only able to provide an accuracy of 51.4% by testing the GLCM parameter, namely distance = 1 and SVM parameters λ (lambda) = 0.5, C (complexity) = 1, constant (gamma) = 0.01, and itermax = 100.
Klasifikasi Citra Makanan Menggunakan K-Nearest Neighbor dengan Fitur Bentuk Simple Morphological Shape Descriptors dan Fitur Warna Grayscale Histogram Muhammad Rizky Setiawan; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (977.579 KB)

Abstract

Food is one of the energy sources needed by humans. The type of food consumed greatly affect the immune system. But the diversity of existing food causes people to be difficult to recognize the type of food they want to consume. The need for a system that can recognize types of food to make it easier for people to regulate their diet. Before entering the feature extraction process, the first step is to do preprocessing by separating the background from the food image object. Furthermore, color feature extraction is performed using the Grayscale Histogram method. The Grayscale Histogram method produces the mean, standard deviation, skewness features. Then form feature extraction was performed using the Simple Morphological Shape Descriptors (SMSD) method and produced area features, length, width, aspect ratio, rectangular N. After extracting feature results, classification was done using the K-Nearest Neighbor method. Based on the test results if only using the Grayscale Histogram method produces an accuracy value of 60%. If only using the SMSD method produces an accuracy value of 54.8%. If using the Grayscale Histogram method and the SMSD method produces an accuracy value of 77.8%. The Grayscale Histogram method and the SMSD method can be used to process images using the K-Nearest Neighbor classification method.
Prediksi Rating Novel Baru Berdasarkan Sinopsis Menggunakan Genre Based Collaborative Filtering dan Text Similarity Rhevitta Widyaning Palupi; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (778.469 KB)

Abstract

The novel is a story that has a long, imaginary plot. Based on the editor's choice on the Amazon.com website, 50 of the 100 best-selling books are novels. This shows that public interest in the novel is quite high as one type of reading. But when you want to choose a novel that you want to read, readers sometimes feel confused to know the quality of the novel. One reference in looking at the quality of a product is rating. The Goodreads site is one site that allows amateur reviewers to write reviews and ratings to help readers choose relevant books. But sometimes Goodreads users don't give ratings to a book so followers from that user want to know the rating given by the user in the book. This study uses the Genre Based Collaborative Filtering method as a calculation of rating predictions and Text Similarity to determine the value of similarity between documents with each other. The data used in this study were 31 users and 90 synopsis as training data and 35 synopsis as test data. System accuracy obtained from the classification results by using the similarity value on text similarity of 45,714286% and MAE value of 0,27742857 so that it can be concluded that the method of genre based collaborative filtering and text similarity can be used to make rating predictions.
Co-Authors Achmad Arwan Achmad Dinda Basofi Sudirman Ade Kurniawan Adella Ayu Paramitha Adi Mashabbi Maksun Adinugroho, Sigit Agus Wahyu Widodo Ahmad Efriza Irsad Ahmad Fauzi Ahsani Akbar Imani Yudhaputra Akhmad Muzanni Safi'i Akhmad Rohim Akmilatul Maghfiroh Alip Setiawan Amalia Safitri Hidayati Amelia Kosasih Andina Dyanti Putri Anggita Mahardika Ani Enggarwati Arrizal Amin Barbara Sonya Hutagaol Bayu Rahayudi Berlian Bidari Ratna Sari B Binti Najibah Agus Ratri Budi Darma Setiawan Cahya Chaqiqi Candra Dewi Chindy Putri Beauty Dea Valentina Delischa Novia Sabilla Destin Eva Dila Purnama Sari Devinta Setyaningtyas Atmaja Dhimas Anjar Prabowo Dian Eka Ratnawati Dika Perdana Sinaga Dyva Agna Fauzan Edy Santoso Eka Dewi Lukmana Sari Eka Novita Shandra Fachrul Rozy Saputra Rangkuti Fadhil Yusuf Rahadika Fajar Pradana Fakhruddin Farid Irfani Faraz Dhia Alkadri Farid Rahmat Hartono Fatwa Reza Rizqika Febriana Ranta Lidya Fida Dwi Febriani Fira Sukmanisa Fitra Abdurrachman Bachtiar Fitria Indriani Frisma Yessy Nabella Gabriel Mulyawan Gagas Budi Waluyo Galuh Fadillah Grandis Gregorius Ivan Sebastian Hafid Satrio Priambodo Hamim Fathul Aziz Haris Bahtiar Asidik Ian Lord Perdana Ibnu Rasyid Wijayanto Imam Cholissodin Imam Cholissodin Inas Istiqlaliyyah Indriati Indriati Irma Pujadayanti Ivan Ivan Juniman Arief Karunia Ayuningsih Kenza Dwi Anggita Kresentia Verena Septiana Toy Kukuh Wiliam Mahardika Lita Handayani Tampubolon M. Ali Fauzi M. Ali Fauzi Mala Nurhidayati Marji Marji Moch Alyur Ridho Moch. Ali Fauzi Mohammad Rizky Hidayatullah Muh. Arif Rahman Muhammad Abdan Mulia Muhammad Bima Zehansyah Muhammad Faiz Al-Hadiid Muhammad Rizky Setiawan Muhammad Sanzabi Libianto Muhammad Tanzil Furqon Muhammad Zaini Rahman Nadhif Sanggara Fathullah Noerhayati Djumaah Manis Nova Amynarto Novan Dimas Pratama Novanto Yudistira Nugroho Dwi Saksono Nur Aisyah Asriani Ofi Eka Novyanti Panji Gemilang Panji Prasuci Saputra Pretty Natalia Hutapea Putra Pandu Adika Putra Pandu Adikara Putri Harnis Raditya Rinandyaswara Randy Cahya Wihandika Randy Ramadhan Rasif Nidaan Khofia Ahmadah Ratih Kartika Dewi Ratna Tri Utami Refi Fadholi Renaza Afidianti Nandini Rendi Cahya Wihandika Restu Amara Rezza Pratama Rhevitta Widyaning Palupi Rifki Akbar Siregar Rizky Ardiawan Rizky Maulana Iqbal Rosintan Fatwa Safira Dyah Karina San Sayidul Akdam Augusta Sarah Najla Adha Sarah Yuli Evangelista Simarmata Sigit Adi Nugroho Sigit Adinugroho Sinta Kusuma Wardani Sulaiman Triarjo Supraptoa Supraptoa Sutrisno Sutrisno Tibyani Tibyani Tri Rahayuni Tuahta Ramadhani Utaminingrum, Fitri Vriza Wahyu Saputra Wahyuni Lubis Willy Karunia Sandy Yosua Dwi Amerta