A robust deep learning approach for glasses detection in non‐standard facial images

This paper presents a deep learning approach for age estimation of human beings using their facial images. The different racial groups based on skin colour have been incorporated in the annotations of the images in the dataset, while ensuring an adequate distribution of subjects across the racial groups so as to achieve an accurate Automatic Facial Age Estimation (AFAE). The principle of transfer learning is applied to the ResNet50 Convolutional Neural Network (CNN) initially pretrained for the task of object classification and finetuning it’s hyperparameters to propose an AFAE system that can be used to automate ages of humans across multiple racial groups. The mean absolute error of 4.25 years is obtained at the end of the research which proved the effectiveness and superiority of the proposed method.

Download Full-text

Presensi Kelas Berbasis Pola Wajah, Senyum dan Wi-Fi Terdekat dengan Deep Learning

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v5i1.2575 ◽

2021 ◽

Vol 5 (1) ◽

pp. 31-38

Author(s):

Miftakhurrokhmat ◽

Rian Adam Rajagede ◽

Ridho Rahmadi

Keyword(s):

Pattern Recognition ◽

Deep Learning ◽

Learning Approach ◽

Time Data ◽

Location Data ◽

Academic System ◽

Facial Pattern ◽

Testing Accuracy ◽

Data Location ◽

Facial Images

Students' attendance in class is often mandatory in education and becomes a benchmark for assessing students. Sometimes there are still fraudulent practices by students to achieve minimum attendance. From the administrative perspective, a paper-based presence system is potentially wasteful and extends the administrative stage because it requires manual recapitulation. This study aims to design a class attendance application based on facial pattern recognition, smile, and closest Wi-Fi. The method used in this research is a deep learning approach with CNN based architecture, FaceNet, to recognize faces. In addition to facial images, the system will also validate the attendance with location and time data. Location data is obtained from matching SSID from the database, and time data is taken when the user sends attendance data through API. This attendance system consists of three applications: web, mobile, and services installed on a mini-computer, which are integrated to sending attendance data to the academic system automatically. As confirmation, students are required to smile selfies to strengthen the validity of their presence. The testing model's accuracy results are 92.6%, while for live testing accuracy the model obtained 66.7%.

Download Full-text

Comparison of various Activation Functions A Deep Learning Approach

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i3.122126 ◽

2018 ◽

Vol 6 (3) ◽

pp. 122-126

Author(s):

Mohammed Ibrahim Khan ◽

◽

Akansha Singh ◽

Anand Handa ◽

◽

...

Keyword(s):

Deep Learning ◽

Learning Approach ◽

Activation Functions

Download Full-text

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

The International Arab Journal of Information Technology ◽

10.34028/iajit/17/3/3 ◽

2020 ◽

Vol 17 (3) ◽

pp. 299-305 ◽

Cited By ~ 1

Author(s):

Riaz Ahmad ◽

Saeeda Naz ◽

Muhammad Afzal ◽

Sheikh Rashid ◽

Marcus Liwicki ◽

...

Keyword(s):

Deep Learning ◽

Character Recognition ◽

Data Augmentation ◽

Short Term Memory ◽

Recognition System ◽

Learning Approach ◽

Arabic Text ◽

Data Set ◽

Processing Step ◽

Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Download Full-text