Klasifikasi Kualitas Beras Delanggu Berdasarkan Ciri Tekstur Menggunakan Gray Level Co-Occurrence Matrix dan Naïve Bayes
نویسندگان
چکیده
Beras merupakan salah satu makanan wajib bagi masyarakat Indonesia. Salah daerah penghasil beras terbesar di Indonesia adalah Delanggu, tepatnya Kabupaten Klaten, Jawa Tengah. Banyak jenis yang beredar pasaran memiliki kualitas dari segi warna, tekstur, dan aroma berbeda-beda. Begitu pun, peran sebagai bahan pangan pokok menjadikan permintaan terhadap konsumsi juga tinggi. Namun, fluktuasi terjadi setiap tahunnya harga pokok, membuat tingkat daya beli mengalami penurunan mendorong tindak kecurangan berupa manipulasi oleh beberapa oknum dengan mengoplos berbeda. Maka diperlukan teknologi dapat membantu maupun pemerintah dalam mengidentifikasi untuk menentukan kelayakan tersebut. Dalam penelitian ini telah dirancang sistem berbasis machine learning menggunakan citra. pengklasifikasian, penulis metode Naïve Bayes. Sedangkan, pada ekstraksi ciri digunakan Gray Level Co-Occurrence Matrix (GLCM) nantinya akan tekstur beras. Berdasarkan pengujian lakukan, diketahui bahwa delanggu berdasarkan dua yaitu kelas super biasa. Pengujian dilakukan 40 citra mana masing-masing Sehingga didapatkan skenario parameter orde terbaik kombinasi GLCM hasil akurasi contrast-correlation 100,00 % waktu komputasi 82,59 detik sudut 135° jarak piksel d=1.
منابع مشابه
Rock Texture Retrieval Using Gray Level Co-occurrence Matrix
Nowadays, as the computational power increases, the role of automatic visual inspection becomes more important. Therefore, also visual quality control has gained in popularity. This paper presents an application of gray level co-occurrence matrix (GLCM) to texturebased similarity evaluation of rock images. Retrieval results were evaluated for two databases, one consisting of the whole images an...
متن کاملKategorisasi dokumen web secara otomatis berdasarkan folksonomy menggunakan multinomial naive Bayes classifier
Folksonomy is a non-hierarchical document categorizing system, that treats every category in a flat manner, dan every category is entered freely by anyone who submitted a document in these categories. Categorization is done automatically at the time a document is submitted, by entering the list of categories that best fit the document. del.icio.us (http://del.icio.us) site is one of the most po...
متن کاملShot boundary detection using second order statistics of gray level co- occurrence matrix
The readily and easily available nature of capturing devices made enormous amounts of video available in day-to-day life. Processing of such a lengthy video is a time consuming process, therefore researchers have introduced key frames. Key frame in short can be visualized as a frame that represents the information present in entire video shot. Detecting shot boundaries plays a vital role in ext...
متن کاملPerformance Analysis of Gray Level Co- Occurrence Matrix Texture Features for Glaucoma Diagnosis
Glaucoma is a multifactorial optic neuropathy disease characterized by elevated Intra Ocular Pressure (IOP). As the visual loss caused by the disease is irreversible, early detection is essential. Fundus images are used as input and it is preprocessed using histogram equalization. First order features from histogram and second order features from Gray Level Co-occurrence Matrix (GLCM) are extra...
متن کاملComputation of gray-level co-occurrence matrix based on CUDA and its optimization
Huichao Hong, Lixin Zheng, Shuwan Pan Engineering Research Center of Industrial Intelligent Technology and Systems of Fujian Providence College of Engineering,Huaqiao University,Quanzhou, China e-mail: [email protected] Abstract: As in various fields like scientific research and industrial application, the computation time optimization is becoming a task that is of increasing importance because of ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Jurnal Ilmu Komputer dan Informatika
سال: 2023
ISSN: ['2807-6664', '2807-6591']
DOI: https://doi.org/10.54082/jiki.47