Mixing deep learning with classical vision for object recognition

Stefańczyk, Maciej; Bocheński, Tomasz

doi:10.24132/jwscg.2020.28.18

Cited by 4 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Age estimation from a facial image has become an important yet challenging problem in many applications, such as human-computer interaction [1], identification [2], security [5], and precision advertising [3]. In recent years, deep learning has made impressive works on various computer vision tasks [4], including age estimation [8,7]. However, all these works have used datasets including only frontal facial images, which cannot adequately reflect the conditions of reallife applications.…”

Section: Introductionmentioning

confidence: 99%

A Deep CNN Model For Age Estimation

Zhang¹,

Bao²

2022

CSRN

View full text Add to dashboard Cite

Age estimation from human faces is an important yet challenging task in computer vision because of the large differences between physical age and apparent age. Although many inspiring works have focused on the age estimation of a single human face through deep learning, the existing methods still have lower performance when dealing with faces in videos because of the differences in head pose between frames. In this paper, a combined system of age estimation and head pose estimation is proposed to improve the performance of age estimation from faces in videos. We use deep regression forests (DRFs) to estimate the age of facial images, while a multi-loss convolutional neural network is also utilized to estimate the head pose. Accordingly, we estimate the age of faces only for head poses within a set degree threshold to enable value refinement. First, we divided the images in the Cross-Age Celebrity Dataset (CACD) and the Asian Face Age Dataset (AFAD) according to the estimated head pose degrees and generated separate age estimates for images with different poses. The experimental results showed that the accuracy of age estimation from frontal facial images was better than that for faces at different angles. Further experiments were conducted on several videos to estimate the age of the same person with his or her face at different angles, and the results show that our proposed combined system can provide more precise and reliable age estimates than a system without head pose estimation.

show abstract

Section: Introductionmentioning

confidence: 99%

A Deep CNN Model For Age Estimation

Zhang¹,

Bao²

2022

CSRN

View full text Add to dashboard Cite

show abstract

“…Besides visual analysis, an automated system can help a physician find skin cancer types faster and easier and reduce patient life risk. Classification algorithms such as K-nearest neighbour, decision tree, deep learning, [8] logistic regression, support vector machine etc. are used to describe how well these classifiers perform on dermoscopic images.…”

Section: Introductionmentioning

confidence: 99%

A Deep CNN Model for Skin Cancer Detection and Classification

Junayed¹,

Anjum²,

Sakib³

et al. 2021

CSRN

View full text Add to dashboard Cite

Skin cancer is one of the most dangerous types of cancers that affect millions of people every year. The detection ofskin cancer in the early stages is an expensive and challenging process. In recent studies, machine learning-basedmethods help dermatologists in classifying medical images. This paper proposes a deep learning-based modelto detect and classify skin cancer using the concept of deep Convolution Neural Network (CNN). Initially, wecollected a dataset that includes four skin cancer image data before applying them in augmentation techniques toincrease the accumulated dataset size. Then, we designed a deep CNN model to train our dataset. On the test data,our model receives 95.98% accuracy that exceeds the two pre-train models, GoogleNet by 1.76% and MobileNetby 1.12%, respectively. The proposed deep CNN model also beats other contemporaneous models while beingcomputationally comparable.

show abstract