Pengelompokan usia berdasarkan citra wajah menggunakan algoritma neural network dengan fitur face anthropometry dan kedalam kerutan
Pengelompokan usia (age prediction) merupakan salah satu topik penelitian yang terkait dengan prediksi usia berdasarkan citra wajah. Permasalahan terkait dengan pengelompokan usia berdasarkan citra wajah adalah bagaimana memilih fitur wajah yang tepat, sehingga dapat mempengaruhi hasil akhir pengelompokan. Penelitian ini bertujuan untuk mengelompokan usia berdasarkan citra wajah dengan menggunakan fitur penting yaitu face anthropometry dan kerutan (wrinkle). Di mana fitur kerutan yang digunakan selain memperhitungkan lebar kerutan (wrinkle density) juga digunakan fitur kedalaman kerutan (the dept of wrinkle). Metode penelitian ini terdiri dari 4 tahapan yaitu: Praproses, identifikasi lokasi titik wajah, ekstraksi fitur dan klasifikasi. Lokasi titik wajah diidentifikasi berdasarkan bentuk simetri wajah dan perbedaan nilai intensitas piksel. Sedangkan kerutan didapatkan dari gabungan metode deteksi tepi menggunakan operator Sobel dan histogram equalization. Algoritma yang digunakan untuk proses klasifikasi adalah algoritma Neural Network (NN) yang akan mengelompokan data citra input menjadi 3 kelas yaitu anak, remaja dan tua. Hasil akhir pengujian menunjukkan bahwa metode yang diusulkan telah mampu mengelompokan usia berdasarkan citra wajah dengan cukup baik dengan hasil akurasi pengujian sebesar 65 % dengan epochs = 1000, dan error rate = 0.0095, sebanyak 100 kali iterasi.
Kata kunci: Age prediction, face ratio, Neural Network, wrinkle.
Age prediction is one of the research topics related to the prediction of age based on facial image. The problems associated with age groupings based on the image of the face is how to choose the right facial features, that will affect the final result grouping. This study aims to categorize age based on facial image by using the important features, that is face anthropometry and wrinkles. Wherein the wrinkles features that used are wrinkles density and the depth of wrinkles. The research methodology consists of four stages: preprocessing, identification of the face point location , feature extraction and classification. The face point is identified based on facial symmetry and the difference of pixel intensities. While wrinkles was obtained from the combined edge detection method using Sobel operator and histogram equalization. The algorithm used for the classification process is a Neural Network (NN) algorithm that would classify the input image data into three classes, there are children, young and old. The final results of test-ing show that the proposed method was able to categorize age based on facial image fairly well with the results of the test accuracy of 65% with epochs = 1000, and the error rate = 0.0095, 100 iterations.
Keywords: Age prediction, face ratio, Neural Network, wrinkle.
Y. H. Kwon dan N. d. V. Lobo, “Age Classification from Facial Images,” Computer Vision and Image Understanding, vol. 74, no. 1, pp. 1-21, 1999.
W.-B. Horng, C.-P. Lee dan C.-W. Chen, “Classification of Age Groups Based on Facial Features,” Tamkang Journal of Science and Engineering, vol. 4, no. 3, pp. 183-192, 2001.
D. A. Rahayu, Karmilasari dan S. E. Saputro, “Klasifikasi Kelompok Usia Berdasarkan Ciri Wajah Pada Sistem Pengenalan Wajah,” dalam Seminar Ilmiah Nasional Komputer dan Sistem Intelijen (KOMMIT 2008), Depok, 2008.
M. M. Dehshibi dan A. Bastanfard, “A new algorithm for age recognition from facial images,” Signal Processing, vol. 90, no. 8, pp. 2431-2444, 2010.
J. Lu, X. Zhou dan Y.-P. Tan, “Neighborhood Repulsed Metric Learning for Kinship Verification,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 2, pp. 331 - 345, 2014.
S. K. Singh, D. S. Chauhan, M. Vatsa dan R. Singh, “A Robust Skin Color Based Face Detection Algorithm,” Tamkang Journal of Science and Engineering, vol. 6, no. 4, pp. 227-234, 2003.
Please find the rights and licenses in Teknologi: Jurnal Ilmiah Sistem Informasi. By submitting the article/manuscript of the article, the author(s) agree with this policy. No specific document sign-off is required.
The non-commercial use of the article will be governed by the Creative Commons Attribution license as currently displayed on Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
2. Author(s)' Warranties
The author warrants that the article is original, written by stated author(s), has not been published before, contains no unlawful statements, does not infringe the rights of others, is subject to copyright that is vested exclusively in the author and free of any third party rights, and that any necessary written permissions to quote from other sources have been obtained by the author(s).
3. User/Public Rights
Register's spirit is to disseminate articles published are as free as possible. Under the Creative Commons license, Register permits users to copy, distribute, display, and perform the work for non-commercial purposes only. Users will also need to attribute authors and Register on distributing works in the journal and other media of publications. Unless otherwise stated, the authors are public entities as soon as their articles got published.
4. Rights of Authors
Authors retain all their rights to the published works, such as (but not limited to) the following rights;
Copyright and other proprietary rights relating to the article, such as patent rights,
The right to use the substance of the article in own future works, including lectures and books,
The right to reproduce the article for own purposes,
The right to self-archive the article (please read out deposit policy),
The right to enter into separate, additional contractual arrangements for the non-exclusive distribution of the article's published version (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal (Register: Jurnal Ilmiah Teknologi Sistem Informasi).
If the article was jointly prepared by more than one author, any authors submitting the manuscript warrants that he/she has been authorized by all co-authors to be agreed on this copyright and license notice (agreement) on their behalf, and agrees to inform his/her co-authors of the terms of this policy. Register will not be held liable for anything that may arise due to the author(s) internal dispute. Register will only communicate with the corresponding author.
Being an open accessed journal and disseminating articles for free under the Creative Commons license term mentioned, author(s) aware that Register entitles the author(s) to no royalties or other fees.
Register will publish the article (or have it published) in the journal if the article’s editorial process is successfully completed. Register's editors may modify the article to a style of punctuation, spelling, capitalization, referencing and usage that deems appropriate. The author acknowledges that the article may be published so that it will be publicly accessible and such access will be free of charge for the readers as mentioned in point 3.