New face features to detect multiple faces in complex background

Bencheriet, Chemesse ennehar

doi:10.1007/s12530-017-9211-y

Cited by 8 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pada penelitian-penelitian sebelumnya sudah ada yang mampu mendeteksi objek bergerak, namun kebanyakan menggunakan metode Gaussian (Waliulu 2018;Zhu et al, 2018;Athira et al, 2018), Support Vector Machine (SVM) (Komorkiewicz et al, 2012;Bencheriet 2018) dan Independent Component Analysis (ICA) (Déniz et al, 2003). Sedangkan berdasarkan lokasinya, tentang pendeteksian objek hanya untuk mendeteksi objek yang ada di darat (Komorkiewicz et al, 2012;Waliulu 2018), serta untuk mendeteksi objek yang ada di laut (Borghgraef et al, 2010;Hinojosa et al, 2011).…”

Section: Pendahuluanunclassified

“…Metode Gaussian merupakan metode yang mempresentasikan latar belakang secara otomatis pada setiap posisi pixel dengan mengoreksi fungsi probabilitas distribusi dari Gaussian (Athira,Vijayan and Mohan, 2018). Model parametrik yang didasarkan pada model campuran Gaussian diterapkan pada daerah warna citra yang tersegmentasi dengan memproses citra warna dengan cara yang akan mengurangi area citra yang harus dipindai (Bencheriet, 2018).…”

Section: Metode-metode Terdahulu Untuk Deteksi Objekunclassified

“…Metode SVM merupakan metode yang didasarkan pada meminimalisasi resiko struktural dari kesalahan pengujian training data (Déniz, Castrillón and Hernández, 2003). Klasifikasi fitur menggunakan SVM memiliki kompleksitas yang cukup tinggi dan tidak mungkin menjalankanya pada CPU secara real time ( Komorkiewicz, Kluczewski and Gorgon,2012;Al Jarouf and Kurdy, 2018;Bencheriet, 2018) Metode ICA menemukan transformasi linier untuk data input dengan representasi berdasarkan variabel independen secara stastistik. Metode ini merupakan generalisasi dari metode PCA yang merepresentasi input berdasarkan variabel yang tidak berkolerasi (Déniz, Castrillón and Hernández, 2003).…”

Section: Metode-metode Terdahulu Untuk Deteksi Objekunclassified

“…Pada dasarnya metode ini sudah pernah digunakan pada penelitian-penelitian terdahulu, namun untuk mendeteksi wajah (Sabuari et al, 2016;Deshpande et al, 2016;Déniz et al, 2003;Bencheriet 2018).…”

Section: Metode Haar Like Feature (Hlf)unclassified

See 3 more Smart Citations

Deteksi Objek Terapung pada Sungai Martapura dengan Metode Haar Like Feature Menggunakan Kamera Smart Phone

Saubari¹,

Ansari²,

Gazali³

2019

J. Sistem Info. Bisnis

View full text Add to dashboard Cite

Martapura river is the center of Banjarmasin’s local life, especially for water transportation and its famous floating market tourism spot. Due to various floating objects in Martapura river, a method to detect those objects is needed to control the condition of the river. In general, there are several methods to detect objects such as Gaussian, Support Vector Machine (SVM), Independent Component Analysis (ICA) and the newest method called Haar Like Feature (HLF). Those first three methods often used to detect moving object, while HLF mostly used to detect human’s face. This research aimed to examine the use of HLF method to detect floating objects in Martapura river by using smartphone’s camera with the specification of 16Megapixel and 1080p resolution. The data collected with random sampling technique in two different spots in Banjarmasin at different times. Images and videos then examined using HLF method. The result shows that HLF method by using smartphone camera cannot be used to identify any floating objec

show abstract

Section: Pendahuluanunclassified

Section: Metode-metode Terdahulu Untuk Deteksi Objekunclassified

Section: Metode Haar Like Feature (Hlf)unclassified

See 2 more Smart Citations

Deteksi Objek Terapung pada Sungai Martapura dengan Metode Haar Like Feature Menggunakan Kamera Smart Phone

Saubari¹,

Ansari²,

Gazali³

2019

J. Sistem Info. Bisnis

View full text Add to dashboard Cite

show abstract

“…By applying various phoneme classes as input features, GMM embedded posteriorgram design outperformed standard practise by introducing implicit constraints into probability assignment initialization[14]. To allow face detection under dim setting, GMM is employed in determining related variance based Haar-like features for skin tone segmentation[15].A revised GMM is performed by taking into account the input parameter as a function of Gaussian[16]. The benefit is threefold for atomic models and electron microscopy 3D density map application: identify similar atomic radius as to input, eliminate singularity issue altogether with least computation time.…”

mentioning

confidence: 99%

A hybrid k-means-GMM machine learning technique for turbomachinery condition monitoring

et al. 2019

View full text Add to dashboard Cite

Industrial practise typically applies pre-set original equipment manufacturers (OEMs) limits to turbomachinery online condition monitoring. However, aforementioned technique which considers sensor readings within range as normal state often get overlooked in the developments of degradation process. Thus, turbomachinery application in dire need of a responsive monitoring analysis in order to avoid machine breakdown before leading to a more disastrous event. A feasible machine learning algorithm consists of k-means and Gaussian Mixture Model (GMM) is proposed to observe the existence of signal trend or anomaly over machine active period. The aim of the unsupervised k-means is to determine the number of clusters, k according to the total trend detected from the processed dataset. Next, the designated k is input into the supervised GMM algorithm to initialize the number of components. Experiment results showed that the k-means-GMM model set up not only capable of statistically define machine state conditions, but also yield a time-dependent clustering image in reflecting degradation severity, as a mean to achieve predictive maintenance.

show abstract

Improving Usability and Intrusion Detection Alerts in a Home Video Surveillance System

Abásolo

Castañeda

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

New face features to detect multiple faces in complex background

Cited by 8 publications

References 13 publications

Deteksi Objek Terapung pada Sungai Martapura dengan Metode Haar Like Feature Menggunakan Kamera Smart Phone

Deteksi Objek Terapung pada Sungai Martapura dengan Metode Haar Like Feature Menggunakan Kamera Smart Phone

A hybrid k-means-GMM machine learning technique for turbomachinery condition monitoring

Improving Usability and Intrusion Detection Alerts in a Home Video Surveillance System

Contact Info

Product

Resources

About