2014 ◽  
pp. 114-125
Author(s):  
Ihor Paliy

The paper presents the improved human face detection method using the combined cascade of classifiers with the improved face candidates’ verification approach, as well as methods and algorithms for the verification level (convolutional neural network) structure generation and training. The combined cascade shows a high detection rate with a very small number of false positives and the proposed candidates’ verification approach is in almost 3 times faster in comparison with the classic verification scheme. The network’s structure generation method allows creating the sparse asymmetric structure of the convolutional neural network automatically. The improved training method uses the adaptive training examples ratio to obtain a trained network with a very low classification error for the positive examples.


2019 ◽  
Vol 5 (3) ◽  
Author(s):  
Ni Komang Sri Julyantari ◽  
Rukmi Sari Hartati ◽  
Made Sudarma

ABSTRACT The importance of the biggest age that is utilized in sharing information technology is one of them is registering online games. Nowadays the proliferation of online games among the wider community is no exception in the class of children who fall into the category of not enough age. When playing online games, players are required to register early to log in. In registering the player is realized to enter the date of birth and this can be manipulated by players who really should be old enough or do not deserve to play online games. To overcome the falsehood or manipulation of data, the player who will register can provide a format photo. JPG with this photo issued the system to be built to know us really from the person who made the registration. To be able to perform face detection and age classification using the Viola Jones method which will be used for human face detection and the backpropagation artificial neural network method is used for classification. In this study the data used is https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/ by entering 100 data as test data and 200 as training data, then the findings obtained are 75% appropriate results Keywords: Age Classification, Online Game, Face Recognition<br />ABSTRAK<br />Pentingnya usia banyak dimanfaatkan dalam berbagi bidang teknologi informasi salah satunya adalah. Saat ini maraknya game online dikalangan masyarakat luas tidak terkecuali di kalangan anak-anak yang termasuk dalam kategori belum cukup umur. Pada saat melakukan permainan game online, pemain wajib melakukan register awal untuk dapat melakukan login. Dalam melakukan register pemain diwajibkan untuk memasukkan tanggal lahir dan hal ini dpat dimanipulasi oleh pemain yang memang seharunya cukup umur atau belum pantas memainkan game online. Untuk mengatasi kepalsuan atau manipulasi data maka pemain yang akan melakukan register dapat memberikan foto dengan format. JPG dengan foto ini nantinya system yang akan dibangun dapat mengenal usis sebenarnya dari orang yang melakukan register tersebut. Untuk dapat melakukan deteksi wajah dan klasifikasi usia menggunakan metode viola jones yang akan digunakan untuk deteksi wajah manusia dan metode jaringan saraf tiruan backpropagation digunakan untuk klasifikasi. Dalam penelitian ini data yang digunakan 100 data sebagai data uji dan 200 sebagai data latih dari https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/, maka hasil akurasi yang didapat adalah 75% hasil sesuai.<br />Kata kunci : Kalsifikasi Usia, Game Online, Deteksi Wajah


2018 ◽  
Vol 106 (6) ◽  
pp. 603 ◽  
Author(s):  
Bendaoud Mebarek ◽  
Mourad Keddam

In this paper, we develop a boronizing process simulation model based on fuzzy neural network (FNN) approach for estimating the thickness of the FeB and Fe2B layers. The model represents a synthesis of two artificial intelligence techniques; the fuzzy logic and the neural network. Characteristics of the fuzzy neural network approach for the modelling of boronizing process are presented in this study. In order to validate the results of our calculation model, we have used the learning base of experimental data of the powder-pack boronizing of Fe-15Cr alloy in the temperature range from 800 to 1050 °C and for a treatment time ranging from 0.5 to 12 h. The obtained results show that it is possible to estimate the influence of different process parameters. Comparing the results obtained by the artificial neural network to experimental data, the average error generated from the fuzzy neural network was 3% for the FeB layer and 3.5% for the Fe2B layer. The results obtained from the fuzzy neural network approach are in agreement with the experimental data. Finally, the utilization of fuzzy neural network approach is well adapted for the boronizing kinetics of Fe-15Cr alloy.


1997 ◽  
Author(s):  
Daniel Benzing ◽  
Kevin Whitaker ◽  
Dedra Moore ◽  
Daniel Benzing ◽  
Kevin Whitaker ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document