Local Binary Pattern (LBP) with application to variant object detection: A survey and method

Background: The unprecedented development of Artificial Intelligence has revolutionised the healthcare industry. In the next generation of healthcare systems, self-diagnosis will be pivotal to personalised healthcare services. During the COVID-19 pandemic, new screening and diagnostic approaches like mobile health are well-positioned to reduce disease spread and overcome geographical barriers. This paper presents a non-invasive screening approach to predict the health of a person from visually observable features using machine learning techniques. Images like face and skin surface of the patients are acquired using camera or mobile devices and analysed to derive clinical reasoning and prediction of the person’s health. Methods: In specific, a two-level classification approach is presented. The proposed hierarchical model chooses a class by training a binary classifier at the node of the hierarchy. Prediction is then made using a set of class-specific reduced feature set. Results: Testing accuracies of 86.87% and 76.84% are reported for the first and second-level classification. Empirical results demonstrate that the proposed approach yields favourable prediction results while greatly reduces the computational time. Conclusions: The study suggests that it is possible to predict the health condition of a person based on his/her face appearance using cost-effective machine learning approaches.

show abstract

“…In the second-level classification, the LBP model was also the only model that stood out among the other NN variants. 19 …”

Section: Resultsmentioning

confidence: 99%

Non-invasive health prediction from visually observable features

et al. 2022

View full text Add to dashboard Cite

show abstract

“…LBP merupakan metode yang terkenal dalam mengenali sebuah objek. Dalam hal ini, cara yang digunakan adalah membedakan objek dengan background [13].…”

Section: Selain Itu Terdapat Beberapa Metode Lain Yang Saat Ini Sedang Berkembang Seperti Speeded Up Robust Feature (Surf) Histogram Of Ounclassified

Penerapan Face Recognition Pada Sistem Presensi

Ramdhon

Febriya

2021

JACOST

View full text Add to dashboard Cite

The development of digital image technology is increasing nowadays. However, the use of image technology on surveillance cameras has not been optimally utilized. On the other hand, the various presence data monitoring systems that currently exist have their respective advantages and disadvantages, and need to be continuously developed so as to facilitate the data processing. The student attendance system at STT Bandung is basically good but it is still not optimal. The process of collecting student attendance data is still quite time-consuming and still allows human errors to occur in the data input process. Therefore, the author intends to help overcome this by utilizing face recognition technology in an integrated presence process. LBPH (Local Binary Pattern Histogram) is currently the best method in face recognition technology because the detection and recognition process is relatively fast and has the highest level of accuracy when compared to other methods. After testing the resilience of the system from the results of the prototyping that was built, the results obtained with a success rate of 86.85%.

show abstract

“…Local Binary Pattern (LBP) adalah operator sederhana dan efisien [7] untuk menggambarkan pola gambar lodal dan mendapatkan hasil yang baik dalam tekstur pengambilan gambar [8]. Keuntungan dari LBP adalah perubahan grayscale monotomik tidak berubah, kompleksitas komputasi yang rendah dan ekstensi multiskala yang mudah [9]. Sedangkan untuk klasifikasi daun menggunakan algoritma Naïve Bayes yang merupakan metode prediksi berbasis probabilitas sederhana yang berdasarkan Teorema Bayes.…”

Section: Pendahuluanunclassified

Fitur Esktraksi LBP dan Naive Bayes dalam Klasifikasi Jenis Pepaya Berdasarkan Citra Daun

Sari

Rachmawanto

2021

JMASIF

View full text Add to dashboard Cite

Tanaman merupakan bagian terpenting dalam kehidupan makhluk hidup sebagai oksigen untuk bernafas, selain itu juga digunakan sumber makanan, bahan bakar, obat-obatan dan masih banyak lagi manfaatnya. Salah satunya tanaman buah pepaya, bisa digunakan untuk bahan makanan maupun obat-obatan. Tanaman buah pepaya ini memiliki banyak jenis dan bisa diklasifikasikan berdasarkan bentuk daunnya. Jenis daun buah papaya yang digunakan dalam penelitian ini, yaitu : daun buah pepaya Sumatera, daun buah pepaya California, daun buah pepaya Hawai, daun buah pepaya cibinong dan daun buah pepaya Bangkok. Jumlah dataset yang digunakan adalah 150 citra dan akan dibagi menjadi 5 kelas yang terdiri dari 25 data training dan 5 data testing masing-masing kelas. Proses klasifikasi ini menggunakan metode Local Binary Pattern untuk ektraksi fitur dan metode Naïve Bayes Classifier sebagai metode klasifikasinya. Metode Local Binary Pattern operator sederhana dan efisien untuk menggambarkan pola gambar local dan mendapatkan hasil yang baik dalam tekstur pengambilan gambar. Sedangkan metode Naïve Bayes Classifier adalah metode yang paling sederhana dengan menggunakan peluang yang ada, dimana tempatnya mengasumsikan bahwa setiap variabel adalah independensi. Berdasarkan hasil pengujian yang dilakukan, penggunaan Naïve Bayes Classifier ditambah dengan ekstraksi fitur Local Binary Pattern didapatkan nilai akurasi 96% pada percobaan pertama dan 93% pada percobaan kedua.

show abstract

Local Binary Pattern (LBP) with application to variant object detection: A survey and method

Cited by 25 publications

References 14 publications

Non-invasive health prediction from visually observable features

Non-invasive health prediction from visually observable features

Penerapan Face Recognition Pada Sistem Presensi

Fitur Esktraksi LBP dan Naive Bayes dalam Klasifikasi Jenis Pepaya Berdasarkan Citra Daun

Contact Info

Product

Resources

About