2021
DOI: 10.31449/inf.v45i5.3262
|View full text |Cite
|
Sign up to set email alerts
|

CNN Based Features Extraction for Age Estimation and Gender Classification

Abstract: In recent years, age estimation and gender classification was one of the issues most frequently discussed in the field of pattern recognition and computer vision. This paper proposes automated predictions of age and gender based features extraction from human facials images. Contrary to the other conventional approaches on the unfiltered face image, in this study, we show that a substantial improvement be obtained for these tasks by learning representations with the use of deep convolutional neural networks (C… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
15
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 22 publications
(16 citation statements)
references
References 16 publications
0
15
0
1
Order By: Relevance
“…The sigmoid activation function was used in the convolutional layer [15]. The pooling layer used to maxpool.…”
Section: Analysis Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…The sigmoid activation function was used in the convolutional layer [15]. The pooling layer used to maxpool.…”
Section: Analysis Methodsmentioning
confidence: 99%
“…In this paper, the density peak clustering algorithm used for color extraction does not require a prior determination of the number of clustering types and clustering centers. First, the image is converted into the color space of CIE Lab, and then the local density and relative distance of every pixel are calculated: ④ The texture and color extracted in steps ② and ③ are input into the CNN model [15] for calculation. The basic structure of the CNN model includes the input layer, convolutional layer, pooling layer, and output layer.…”
Section: Clothing Design Evaluation Model Combined With Image Process...mentioning
confidence: 99%
“…У дослідженні [6] показано, що для оцінки віку та гендерної класифікації можна отримати значне покращення, вивчаючи уявлення з використанням глибоких згорткових нейронних мереж (CNN). Метод нейронної мережі з прямим зв'язком, використаний у цьому дослідженні, підвищує надійність для дуже варіабельних завдань розпізнавання без обмежень для визначення статі та вікової групи.…”
Section: аналіз досліджень та публікаційunclassified
“…Figure 3 shows that the CapsNet optimized recognition algorithm had a high convergence speed. The CapsNet optimized recognition algorithm was compared with other algorithms, including Random Forest (RF) [12], C4.5 [13], Support Vector Machine (SVM) [14], and Convolutional Neural Network (CNN) [15], and the results are shown in Figure 4.…”
Section: Experimental Analysismentioning
confidence: 99%