A Comparative Study of Three Pre-trained Convolutional Neural Networks in the Detection of Violence Against Women

被引：0

作者：

Aguilar, Ivan Gaytan ^{[1
]}

Contreras, Alejandro Aguilar ^{[1
]}

Eleuterio, Roberto Alejo ^{[1
]}

Lara, Erendira Rendon ^{[1
]}

Pina, Grisel Miranda ^{[1
]}

Gutierrez, Everardo E. Granda ^{[2
]}

机构：

[1] Tecnol Nacl Mexico, Campus Toluca, Metepec, Mexico

[2] Univ Autonoma Estado Mexico, Toluca De Lerdo, Mexico

来源：

CIENCIA ERGO-SUM | 2023年 / 31卷 / 02期

关键词：

artificial intelligence; deep learning; violence against women; transfer learning; CNN; VGG16; ResNet50; Mobile Net; IMPACT;

D O I：

暂无

中图分类号：

C [社会科学总论];

学科分类号：

03 ; 0303 ;

摘要：

This paper presents a performance comparison between 3 models of pre-trained CNN networks (VGG16, ResNet50, and MobileNet) in detecting physical violence against women in video. To carry out the classification of images that include physical violence against women and those that do not, 2800 images (1400 violent and 1400 non-violent) were collected from a public dataset and subsequently divided into training (1200 images), validation (1000 images) and test (600 images). To evaluate their performance, accuracy values for each model were considered, positioning the MobileNet network as the best-performing classifier for this classification task with 89% accuracy.

引用

页数：1

共 50 条

[21] Recognizing Malaysia Traffic Signs with Pre-Trained Deep Convolutional Neural Networks
How, Dickson Neoh Tze
Sahari, Khairul Salleh Mohamed
Hou, Yew Cheong
Basubeit, Omar Gumaan Saleh
2019 4TH INTERNATIONAL CONFERENCE ON CONTROL, ROBOTICS AND CYBERNETICS (CRC 2019), 2019, : 109 - 113
[22] Age Estimation Based on Face Images and Pre-trained Convolutional Neural Networks
Anand, Abhinav
Labati, Ruggero Donida
Genovese, Angelo
Munoz, Enrique
Piuri, Vincenzo
Scotti, Fabio
2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2017, : 3357 - 3363
[23] Efficient Aspect Object Models Using Pre-trained Convolutional Neural Networks
Wilkinson, Eric
Takahashi, Takeshi
2015 IEEE-RAS 15TH INTERNATIONAL CONFERENCE ON HUMANOID ROBOTS (HUMANOIDS), 2015, : 284 - 289
[24] Object detection and classification of butterflies using efficient CNN and pre-trained deep convolutional neural networks
Mattins, R. Faerie
Sarobin, M. Vergin Raja
Aziz, Azrina Abd
Srivarshan, S.
MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (16) : 48457 - 48482
[25] The Impact of Padding on Image Classification by Using Pre-trained Convolutional Neural Networks
Tang, Hongxiang
Ortis, Alessandro
Battiato, Sebastiano
IMAGE ANALYSIS AND PROCESSING - ICIAP 2019, PT II, 2019, 11752 : 337 - 344
[26] Filter pruning by image channel reduction in pre-trained convolutional neural networks
Chung, Gi Su
Won, Chee Sun
MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (20) : 30817 - 30826
[27] Filter pruning by image channel reduction in pre-trained convolutional neural networks
Gi Su Chung
Chee Sun Won
Multimedia Tools and Applications, 2021, 80 : 30817 - 30826
[28] Assessment of Convolutional Neural Network Pre-Trained Models for Detection and Orientation of Cracks
Qayyum, Waqas
Ehtisham, Rana
Bahrami, Alireza
Camp, Charles
Mir, Junaid
Ahmad, Afaq
MATERIALS, 2023, 16 (02)
[29] A Combination of Light Pre-trained Convolutional Neural Networks and Long Short-Term Memory for Real-Time Violence Detection in Videos
bin Abdullah, Muhammad Shahril Nizam
Karim, Hezerul Abdul
AlDahoul, Nouar
INTERNATIONAL JOURNAL OF TECHNOLOGY, 2023, 14 (06) : 1228 - 1236
[30] Fine-tuning of pre-trained convolutional neural networks for diabetic retinopathy screening: a clinical study
Roshan, Saboora M.
Karsaz, Ali
Vejdani, Amir Hossein
Roshan, Yaser M.
INTERNATIONAL JOURNAL OF COMPUTATIONAL SCIENCE AND ENGINEERING, 2020, 21 (04) : 564 - 573

← 1 2 3 4 5 →