scholarly journals Age-group Classification Using 3DHOG Descriptor Applied to Depth Maps

10.29007/rvq6 ◽  
2020 ◽  
Author(s):  
Nabila Mansouri ◽  
Hana Bougueddima ◽  
Yousra Ben Jemaa
Keyword(s):  
Age Estimation ◽  
Region Of Interest ◽  
Depth Map ◽  
Aging Effect ◽  
Customer Relationship ◽  
Age Group ◽  
Depth Maps ◽  
Security Control ◽  
Age Group Classification ◽  
Public Datasets

Age estimation has lots of real-world applications, such as security control, biometrics, customer relationship management, entertainment and cosmetology. In fact, facial age estimation has gained wide popularity in recent years. Despite numerous research efforts and advances in the last decade, traditional human age-group recognition with the sequence of 2D color images is still a challenging problem. The goal of this work is to recognize human age-group only using depth maps without additional joints information. As a practical solution, we present a novel representation of global appearance of aging-effect such as wrinkles’ depth. The proposed framework relay, first-of-all, on an extended version of Viola-Jones algorithm for face and region of interest (most affected by aging) extraction. Then, the 3D histogram of oriented gradients is used to describe local appearances and shapes of the depth map, for more compact and discriminative aging effect representation. The presented method has been compared with the state-of-the-art 2D-approaches on public datasets. The experimental results demonstrate that our approach achieves a better and more stable performances.

Age Classification Using Motif and Statistical Features Derived On Gradient Facial Images

2020 ◽  
Vol 13 (5) ◽  
pp. 965-976
Author(s):  
Ayaluri Mallikarjuna Reddy ◽  
Vakulabharanam Venkata Krishna ◽  
Lingamgunta Sumalatha ◽  
Avuku Obulesh
Keyword(s):  
Age Estimation ◽  
Spatial Relations ◽  
Local Features ◽  
Initial Position ◽  
Age Group ◽  
Human Beings ◽  
Face Images ◽  
Estimation Operator ◽  
Age Group Classification ◽  
Occurrence Matrix

Background: Age estimation using face images has become increasingly significant in the recent years, due to diversity of potentially useful applications. Age group feature extraction, the local features, has received a great deal of attention. Objective: This paper derived a new age estimation operator called “Gradient Dual-Complete Motif Matrix (GD-CMM)” on the 3 x 3 neighborhood of gradient image. The GD-CMM divides the 3 x 3 neighborhood in to dual grids of size 2 x 2 each and on each 2 x 2 grid complete motif matrices are derived. Methods: The local features are extracted by using Motif Co-occurrence Matrix (MCM) and it is derived on 2 x 2 grid and the main disadvantage of this Motifs or Peano Scan Motifs (PSM) is they are static i.e. the initial position on a 2 x2 grid is fixed in deriving motifs, resulting with six different motifs. The advantage 3 x 3 neighborhood approaches over 2x 2 grids is the 3x3 grid identify the spatial relations among the pixels more precisely. The gradient images represent facial features more efficiently and human beings are more sensitive to gradient changes than original grey level intensities. Results: The proposed method is compared with other existing methods on FGNET, Google and scanned facial image databases. The experimental outcomes exhibited the superiority of proposed method than existing methods. Conclusion: On the GD-CMM, this paper derived co-occurrence features and machine learning classifiers are used for age group classification.

COMPARISION OF DENTAL SCORING SYSTEM WITH RADIOGRAPHIC SKELETAL SYSTEM IN AGE ESTIMATION

JKCD ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. 9-11
Author(s):  
Sadaf Ambreen
Keyword(s):  
Age Estimation ◽  
Scoring System ◽  
Skeletal Age ◽  
Chronological Age ◽  
Age Group ◽  
Dental Age ◽  
Scoring Method ◽  
Cross Sectional ◽  
Study Results ◽  
Male Subjects

Objectives: To compare Demirjian Dental scoring method with Greulich-Pyle (GP) Skeletal method of age estimation in pubertal children. Materials and Methods: Sample of the study included 267 male healthy subjects of 11-16 years of age group.. Demirjian Scoring system was utilized to evaluate the orthopantomograms to assess their Dental age and the Hand-Wrist radiographs were analyzed to calculate the skeletal age by utilizing GP atlas. Chronological age was obtained from the date of birth of the subject .Both methods were compared with one another and with the chronological age. It was a cross-sectional study and only healthy male subjects without any clinical abnormalities were included in the study. Results: A total of 267 male subjects of 11-16 years of age group were assessed by Demirjian and Greulich Pyle Methods. Both were compared with Chronological Age. Data obtained was statistically analyzed and the Student “t” test was applied in the study population. The mean difference between Chronolgical age and dental age was 0.69years and that of chronological age and skeletal age was 0.87 years. It was observed from dental age assessment that it does not differ much from the skeletal age. Conclusion: It was concluded that Demirjian method of Age Estimation is more precise than Greulich Pyle method of Age Estimation. Furthermore both methods can be used selectively in Medicolegal cases to access bone age which can be easily correlated to chronological age.

scholarly journals A Residual Network and FPGA Based Real-Time Depth Map Enhancement System

Entropy ◽  
2021 ◽  
Vol 23 (5) ◽  
pp. 546
Author(s):  
Zhenni Li ◽  
Haoyi Sun ◽  
Yuliang Gao ◽  
Jiao Wang
Keyword(s):  
Real Time ◽  
Super Resolution ◽  
Depth Map ◽  
Acquisition System ◽  
Depth Image ◽  
Fpga Design ◽  
Depth Sensing ◽  
Residual Network ◽  
Real Time Processing ◽  
Depth Maps

Depth maps obtained through sensors are often unsatisfactory because of their low-resolution and noise interference. In this paper, we propose a real-time depth map enhancement system based on a residual network which uses dual channels to process depth maps and intensity maps respectively and cancels the preprocessing process, and the algorithm proposed can achieve real-time processing speed at more than 30 fps. Furthermore, the FPGA design and implementation for depth sensing is also introduced. In this FPGA design, intensity image and depth image are captured by the dual-camera synchronous acquisition system as the input of neural network. Experiments on various depth map restoration shows our algorithms has better performance than existing LRMC, DE-CNN and DDTF algorithms on standard datasets and has a better depth map super-resolution, and our FPGA completed the test of the system to ensure that the data throughput of the USB 3.0 interface of the acquisition system is stable at 226 Mbps, and support dual-camera to work at full speed, that is, 54 fps@ (1280 × 960 + 328 × 248 × 3).

Region of Interest Localization for Bone Age Estimation Using Whole-Body Bone Scintigraphy

2021 ◽  
Vol 10 (2) ◽  
pp. 22-29
Author(s):  
Thanh-Cong Do ◽  
Hyung Jeong Yang ◽  
Soo Hyung Kim ◽  
Guee Sang Lee ◽  
Sae Ryung Kang ◽  
...  
Keyword(s):  
Bone Scintigraphy ◽  
Age Estimation ◽  
Region Of Interest ◽  
Bone Age ◽  
Whole Body ◽  
Body Bone

Towards Accuracy Enhancement of Age Group Classification Using Generative Adversarial Networks

2021 ◽  
pp. 1-17
Author(s):  
Khaled ELKarazle ◽  
Valliappan Raman ◽  
Patrick Then
Keyword(s):  
Age Estimation ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Original Dataset ◽  
Age Group Classification ◽  
Facial Images

Age estimation models can be employed in many applications, including soft biometrics, content access control, targeted advertising, and many more. However, as some facial images are taken in unrestrained conditions, the quality relegates, which results in the loss of several essential ageing features. This study investigates how introducing a new layer of data processing based on a super-resolution generative adversarial network (SRGAN) model can influence the accuracy of age estimation by enhancing the quality of both the training and testing samples. Additionally, we introduce a novel convolutional neural network (CNN) classifier to distinguish between several age classes. We train one of our classifiers on a reconstructed version of the original dataset and compare its performance with an identical classifier trained on the original version of the same dataset. Our findings reveal that the classifier which trains on the reconstructed dataset produces better classification accuracy, opening the door for more research into building data-centric machine learning systems.

scholarly journals Establishment of age group classification for risk stratification in glioma patients

2020 ◽  
Author(s):  
Zhiying Lin ◽  
Runwei Yang ◽  
Yawei Liu ◽  
Kaishu Li ◽  
Guozhong Yi ◽  
...  
Keyword(s):  
Molecular Markers ◽  
Risk Stratification ◽  
Tumor Size ◽  
Age Groups ◽  
Tumor Location ◽  
Group Classification ◽  
Age Group ◽  
Ki 67 ◽  
Who Grade ◽  
Age Group Classification

Abstract Objective: Age is associated with the prognosis of glioma patients, but there is no uniform standard of age-group classification to evaluate the prognosis of glioma patients. In this study, we aimed to establish an age group classification for risk stratification in glioma patients. Methods: A total of 1502 patients diagnosed with gliomas at Nanfang Hospital between 2000 and 2018 were enrolled. The WHO grade of glioma was used as a dependent variable to evaluate the effect of age on risk stratification. The evaluation model was established by logistic regression, and the Akaike information criterion (AIC) value of the model was used to determine the optimal cutoff points for age-classification. The differences in gender, WHO grade, pathological subtype, tumor cell differentiation direction, tumor size, tumor location, and molecular markers between different age groups were analyzed. The molecular markers included GFAP, EMA, MGMT, p53, NeuN, Oligo2, EGFR, VEGF, IDH1, Ki-67, 1p/19q, PR, CD3, H3K27M, and TS. Results: The proportion of men with glioma was higher than that of women with glioma (58.3% vs 41.7%). Analysis of age showed that appropriate classifications of age group were 0-14 years old (pediatric group), 15-47 years old (youth group), 48-63 years old (middle-aged group), and ≥64 years old (elderly group).The proportions of glioblastoma and large tumor size (4-6 cm) increased with age (p = 0.000, p = 0.018, respectively ). Analysis of the pathological molecular markers across the four age groups showed that the proportion of patients with larger than 10% area of Ki-67 expression or positive PR expression increased with age (p = 0.000, p = 0.017, respectively). Conclusion: Age was effective evaluating the risk of glioblastoma in glioma patients. Appropriate classifications of age group for risk stratification were 0-14 years old (pediatric group), 15-47 years old (young group), 48-63 years old (middle age group) and ≥ 64 years old (elderly group). There was significant heterogeneity in WHO grade, tumor size, tumor location and some molecular markers among the four age groups.

scholarly journals A MEDIAN-BASED DEPTHMAP FUSION STRATEGY FOR THE GENERATION OF ORIENTED POINTS

2016 ◽  
Vol III-3 ◽  
pp. 115-122
Author(s):  
M. Rothermel ◽  
N. Haala ◽  
D. Fritsch
Keyword(s):  
Surface Reconstruction ◽  
Nearest Neighbor ◽  
State Of The Art ◽  
Depth Map ◽  
Median Filtering ◽  
Tree Structures ◽  
Fusion Strategy ◽  
Depth Maps ◽  
Disparity Maps ◽  
Nearest Neighbor Queries

Due to good scalability, systems for image-based dense surface reconstruction often employ stereo or multi-baseline stereo methods. These types of algorithms represent the scene by a set of depth or disparity maps which eventually have to be fused to extract a consistent, non-redundant surface representation. Generally the single depth observations across the maps possess variances in quality. Within the fusion process not only preservation of precision and detail but also density and robustness with respect to outliers are desirable. Being prune to outliers, in this article we propose a local median-based algorithm for the fusion of depth maps eventually representing the scene as a set of oriented points. Paying respect to scalability, points induced by each of the available depth maps are streamed to cubic tiles which then can be filtered in parallel. Arguing that the triangulation uncertainty is larger in the direction of image rays we define these rays as the main filter direction. Within an additional strategy we define the surface normals as the principle direction for median filtering/integration. The presented approach is straight-forward to implement since employing standard oc- and kd-tree structures enhanced by nearest neighbor queries optimized for cylindrical neighborhoods. We show that the presented method in combination with the MVS (Rothermel et al., 2012) produces surfaces comparable to the results of the Middlebury MVS benchmark and favorably compares to an state-of-the-art algorithm employing the Fountain dataset (Strecha et al., 2008). Moreover, we demonstrate its capability of depth map fusion for city scale reconstructions derived from large frame airborne imagery.

Sign in / Sign up

Export Citation Format

Share Document