Main Article Content
Abstract
Abstract
Factors affecting the quality of a product is one of them is the color and shape. Color and shape factor was used as a parameter the most attention in the selection of a product. Farmer level, the separation between the seed heads intact and damaged seeds have not done this led to lower prices nutmeg. Separation based on a whole seed and grain merchants and level damage done is done by direct observation. This separation process requires large amounts of labor, the cost is relatively large and long enough. Development of separation methods based on the nutmeg seed quality classes can be done with image processing technology in combination with artificial neural networks. The use of color and shape parameter in the selection of quality seeds in non-destructive nutmeg is needed to address the separation of nutmeg manually. This study aims to identify the quality of nutmeg by color and shape by digital image processing technology in combination with artificial neural networks. Color parameters of the model used consists of a color Red Green Blue, Hue Saturation Value color model, color model Lαb shape parameter consists of area, perimeter, roundness, compactness. Discriminant analysis based on parameters derived mean color saturation and a significant area as the network input. The results showed the mean saturation parameter and the area identified quality class ABCD head, and BWP Rimpel with 100% accuracy.
Key words: nutmeg, quality, color, shape, discriminant analysis, neural networks
Abstrak
Faktor yang mempengaruhi kualitas sebuah produk salah satunya adalah warna dan bentuk. Faktor warna dan bentuk digunakan sebagai salah satu parameter yang paling diperhatikan dalam pemilihan sebuah produk. Ditingkat petani pala proses pemisahan antara biji utuh dan biji rusak belum dilakukan hal ini menyebabkan harga biji pala menjadi rendah. Pemisahan berdasarkan biji utuh dan biji rusak dilakukan ditingkat pedagang dan dilakukan dengan pengamatan langsung. Proses pemisahan ini membutuhkan tenaga kerja dalam jumlah banyak, biaya relatif besar dan waktu yang cukup lama. Pengembangan metode pemisahan biji pala berdasarkan kelas mutu dapat dilakukan dengan teknologi pengolahan citra yang dikombinasi dengan jaringan saraf tiruan. Penggunaan parameter warna dan bentuk dalam pemilihan mutu biji pala secara non-destruktif sangat dibutuhkan untuk mengatasi permasalahan pemisahan biji pala secara manual. Penelitian ini bertujuan untuk mengidentifikasi mutu pala berdasarkan warna dan bentuk dengan teknologi pengolahan citra digital yang dikombinasi dengan jaringan saraf tiruan. Parameter warna yang digunakan terdiri dari model warna Red Green Blue, model warna Hue Saturation Value, model warna Lab parameter bentuk terdiri dari area, perimeter, roundness dan compactness. Berdasarkan analisis diskriminan diperoleh parameter warna mean saturation dan area yang signifikan sebagai input jaringan. Hasil penelitian menunjukan parameter mean saturation dan area berhasil mengidentifikasi kelas mutu pala ABCD, Rimpel dan BWP dengan akurasi 100%.
Kata kunci : Biji pala, mutu, warna, bentuk, analisis diskriminan , jaringan saraf tiruan
Diterima: 03 Januari 2012; Disetujui: 29 Maret 2012
Article Details
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).