Results 71 to 80 of about 468,003 (169)

Wavelet-enhanced Haar framework for face detection with convolutional neural networks

Measurement. Digitalization
The process of face detection in real-world scenarios is influenced by lighting conditions, background environment, and the possibility of classical techniques to produce false positives, whereas deep learning models require more computing power.
Adesh Kumar, Harsh Amrik Saini
doaj   +1 more source

Robustness Analysis of Distributed CNN Model Training in Expression Recognition

IET Biometrics, Volume 2026, Issue 1, 2026.
Facial expression recognition is vital in pattern recognition and affective computing. With the advancement of deep learning, its performance has improved, yet challenges remain in nonlaboratory environments due to occlusion, poor lighting, and varying head poses.
Jun Li, Jun Wan
wiley   +1 more source

Monitoring System of Drowsiness and Lost Focused Driver Using Raspberry Pi

Iranian Journal of Public Health, 2020
Background: Drowsiness condition is one of the significant factors often encountered when an accident occurs. We aimed to detect a method to prevent accidents caused by drowsiness and lost a focused driver.
Kusworo ADI, Catur Edi WIDODO, Aris Puji WIDODO, Hilda Nurul ARISTIA   +3 more
doaj   +1 more source

A Novel Lightweight and High‐Performance Detection Framework for Signal Detection in Wideband Spectrogram

Electronics Letters, Volume 62, Issue 1, January/December 2026.
With the proliferation of Internet of Things (IoT) devices, broadband signal detection in low‐signal‐to‐noise ratio (SNR) non‐cooperative environments presents significant challenges. This letter proposes two lightweight modules integrated into the YOLOv8 framework, which effectively reduces computational complexity while improving detection accuracy ...
Deming Hu, Shudong Yuan, Yongjie Zhao, Honghe Huang, Longqing Li   +4 more
wiley   +1 more source

Advanced CNN Architecture for Intelligent Driver Drowsiness Detection

Electronics Letters, Volume 62, Issue 1, January/December 2026.
The paper proposes a hybrid Drowsiness Detection Network (DDN) based on Convolutional Neural Network (CNN) and Long Short‐Term Memory (LSTM). The Dlib's 68‐point model approach is used for extracting the Region of Interest (ROI). The proposed DDN model achieves 99.65% precision, 99.78% recall, 99.61% F1‐score and 99.73% accuracy on YawDD and 98.34 ...
Jyoti Pandey, Abhijit Asati
wiley   +1 more source

Facial Landmark Localization Optimization for Live Streaming Scenarios

IET Image Processing, Volume 20, Issue 1, January/December 2026.
To address the problems of low accuracy and poor robustness in facial landmark localization caused by complex conditions such as partial body appearance and large pose variations in live streaming scenarios, this paper proposes a joint optimization scheme for face detection and facial landmark localization tailored for live streaming.
Di Wang, Boqiang Shi, Wenying Zhu
wiley   +1 more source

Detection and classification of vehicles and pedestrians using Haar cascade classifier

U radu je detaljno objašnjen koncept prepoznavanja ljudi i objekata pomoću Haar kaskadnog klasifikatora. U ovom radu je glavni fokus na prepoznavanju vozila i pješaka u prometu. Cilj je stvoriti što bolji klasifikator korištenjem prikupljenih podataka te
Batur, Jure
core   +2 more sources

Design and Development of a System for Monitoring Student Attention and Concentration during Learning using CNN Model and Face Landmark Detection

JOIV: International Journal on Informatics Visualization
Mobile learning media has been wide and provides a tendency for lecturers to identify students' concentration levels in online classes. To bring the class into active learning, efforts are needed from lecturers and educational institutions to return ...
Syamsul Arifin, Aulia Siti Aisjaha, Azzezza Nurul Fatima, Haniah Mahmudah   +3 more
doaj   +1 more source

IMPLEMENTASI FACE RECOGNITION BERBASIS HAAR-CASCADE CLASSIFIER PADA SISTEM KEAMANAN RUMAH MENGGUNAKAN DUAL-CAMERA [PDF]

, 2022
Pencurian biasanya terjadi pada rumah yang terkesan sepi atau rumah yang terlihat mewah. Sistem pengaman yang biasa digunakan adalah CCTV. Kelemahan CCTV tidak dapat memberitahu pemilik bahwa ada orang asing di depan rumah.
Sutarti, Siswanto, Putri Jutika, Alin
core  

Penggunaan Metode Viola-Jones dan Algoritma Eigen Eyes dalam Sistem Kehadiran Pegawai

Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems), 2014
Pelaksanaan pengisian daftar kehadiran secara manual dapat menjadi penghambat bagi organisasi untuk memantau kedisiplinan karyawan. Sistem kehadiran manual dapat diganti dengan sistem kehadiran terkomputerisasi yang mendasarkan proses identifikasi ...
Andrianus Hendro Triatmoko, Sholeh Hadi Pramono, Harry S. Dachlan   +2 more
doaj   +1 more source