Honeycomb model based skin colour detector for face detection

Pai, Yu-Ting; Lee, Li-Te; Ruan, Shanq-Jang; Chen, Yen-Hsiang; Mohanty, Saraju P.; Kougianos, Elias

doi:10.1504/ijcat.2010.034736

Cited by 9 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pai et al [246] presented honeycomb model for skin segmentation. First, possible skin colors are estimated from the pixels of database and the honeycomb structure is built in HSV color space according to the training samples.…”

Section: H Mixuret Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Survey on Human Skin Detection

Mahmoodi

Sayedi

2016

IJIGSP

View full text Add to dashboard Cite

Human Skin detection is one of the most widely used algorithms in vision literature which has been numerously exploited both directly and indirectly in multifarious applications. This scope has received a great deal of attention specifically in face analysis and human detection/tracking/recognition systems. As regards, there are several challenges mainly emanating from nonlinear illumination, camera characteristics, imaging conditions, and intra-personal features. During last twenty years, researchers have been struggling to overcome these challenges resulting in publishing hundreds of papers. The aim of this paper is to survey applications, color spaces, methods and their performances, compensation techniques and benchmarking datasets on human skin detection topic, covering the related researches within more than last two decades. In this paper, different difficulties and challenges involved in the task of finding skin pixels are discussed. Skin segmentation algorithms are mainly based on color information; an in-depth discussion on effectiveness of disparate color spaces is elucidated. In addition, using standard evaluation metrics and datasets make the comparison of methods both possible and reasonable. These databases and metrics are investigated and suggested for future studies. Reviewing most existing techniques not only will ease future studies, but it will also result in developing better methods. These methods are classified and illustrated in detail. Variety of applications in which skin detection has been either fully or partially used is also provided.

show abstract

Section: H Mixuret Methodsmentioning

confidence: 99%

“…Fig.12. The Method Proposed in [246] Hai-bo [247] combined explicitly defined boundary method with single Gaussian in HS color space to detect skin pixels. Jmal et al [248] combined the result of applying boundary rules on RGB space and Bhattacharyya distance between the histogram of these pixels and offline trained histograms.…”

Section: H Mixuret Methodsmentioning

confidence: 99%

A Comprehensive Survey on Human Skin Detection

Mahmoodi

Sayedi

2016

IJIGSP

View full text Add to dashboard Cite

show abstract

“…As stated in the survey by Morerio et al . [ 58 ], colour is a simple, but good feature for detecting the location of hands, particularly if a proper colour space is considered, such as Lab, HSV [ 59 ] and YCbCr [ 60 ]. This feature is usually combined with others, such as texture and contours [ 50 , 53 ].…”

Section: Recognition Of Elements Of Activities At the Motion Levelmentioning

confidence: 99%

Recognition of Activities of Daily Living with Egocentric Vision: A Review

Nguyen

Nebel

Flórez-Revuelta

2016

Sensors

101

View full text Add to dashboard Cite

Video-based recognition of activities of daily living (ADLs) is being used in ambient assisted living systems in order to support the independent living of older people. However, current systems based on cameras located in the environment present a number of problems, such as occlusions and a limited field of view. Recently, wearable cameras have begun to be exploited. This paper presents a review of the state of the art of egocentric vision systems for the recognition of ADLs following a hierarchical structure: motion, action and activity levels, where each level provides higher semantic information and involves a longer time frame. The current egocentric vision literature suggests that ADLs recognition is mainly driven by the objects present in the scene, especially those associated with specific tasks. However, although object-based approaches have proven popular, object recognition remains a challenge due to the intra-class variations found in unconstrained scenarios. As a consequence, the performance of current systems is far from satisfactory.

show abstract

“…2 shows the ROC (Receiver Operating Characteristic) curves with 637 Pareto-optimal solutions of the classification rates (TPR and FPR) derived using the last 1000 test skin images. Moreover, the ETM based threshold decision rules proposed in the early 70 published bibliographies [19][20][21][22][23][24][25][26][27][28][29][30][31][32][33][34][35][36] were calculated utilizing the same skin and non-skin data sets for fair comparison. Clearly the Pareto-optimal solutions obtained in this study dominate those of the other 70 publications.…”

Section: Skin Detectionmentioning

confidence: 99%

“…The ETM is commonly used to classify skin and face due to its simplicity of detection rules and computational efficiency [9,18]. In the bibliography various color spaces have been employed to label skin pixels with ETM approach including RGB [19][20][21][22], nRGB [23][24][25], HSV [26-28], HSI [29], YCbCr [30][31][32][33], YCgCr [34,35], YIQlYUV [36] and combination of various color spaces [37][38][39][40]. The main difficulty achieving high performance employing ETM is to find adequate threshold ranges empirically [41] and it is difficult to find accurate threshold settings to obtain desirable performance.…”

mentioning

confidence: 99%

Face detection using combination of skin color pixel detection and Viola-Jones face detector

Luh

2014

2014 International Conference on Machine Learning and Cybernetics

View full text Add to dashboard Cite

This paper presents a human face detection scheme by combining a novel hybrid color models and Viola-Jones face detector. A hybrid skin color model RGB-CbCrCg was proposed for classifying skin and non-skin pixels. The extraction of skin region is carried out using a set of bounding rules optimized employing multi-objective differential evolution method. Afterward the segmented face regions are identified using Viola-Jones algorithm built in MATLAB Computer Vision System Toolbox™. The performances of skin and face detection were evaluated using the ECU face and skin database. Experimental results show that the proposed scheme outperforms the other skin color space methods.

show abstract

Honeycomb model based skin colour detector for face detection

Cited by 9 publications

References 15 publications

A Comprehensive Survey on Human Skin Detection

A Comprehensive Survey on Human Skin Detection

Recognition of Activities of Daily Living with Egocentric Vision: A Review

Face detection using combination of skin color pixel detection and Viola-Jones face detector

Contact Info

Product

Resources

About