A novel method for detecting lips, eyes and faces in real time

Chiang, Cheng‐Chin; Tai, Wen‐Kai; Yang, Mau-Tsuen; Huang, Yi-Ting; Huang, Chi-Jaung

doi:10.1016/j.rti.2003.08.003

Cited by 93 publications

(69 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We propose an online learning approach to extract sample data for lip and non-lip classes to estimate their distribution in real time. Chiang et al (2003) in their work provides hints for this approach. They pointed out that lip colors are distributed at the lower range of green channel in the (r,g) plane.…”

Section: Online Learning and Extraction Of Lip And Non-lip Data Samplesmentioning

confidence: 97%

“…Image based (top-down) approaches utilize statistical models of skin color pixels to find the face region first, accordingly pre-stored face templates or feature search algorithms are used to match the candidate face regions as in Chiang et al (2003). Feature based approaches use specialized filters directly such as templates or Gabor filter of different frequencies and orientations to locate the facial features.…”

Section: Face Roi Localizationmentioning

confidence: 99%

“…In order to alleviate the influence of ambient lighting on the sample class data, chromatic color transformation is adopted for color representation (Chiang et al, 2003;Yang et al, 1998). It was pointed out (Yang et al, 1998) that human skin colors are less variant in the chromatic color space than the RGB color space.…”

Section: Online Learning and Extraction Of Lip And Non-lip Data Samplesmentioning

confidence: 99%

See 2 more Smart Citations

Real-Time Vision Based Mouth Tracking and Parameterization for a Humanoid Imitation Task

Gurbuz¹,

Inoue²,

Cheng³

2007

Humanoid Robots: New Developments

View full text Add to dashboard Cite

Section: Online Learning and Extraction Of Lip And Non-lip Data Samplesmentioning

confidence: 97%

Section: Face Roi Localizationmentioning

confidence: 99%

Section: Online Learning and Extraction Of Lip And Non-lip Data Samplesmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Vision Based Mouth Tracking and Parameterization for a Humanoid Imitation Task

Gurbuz¹,

Inoue²,

Cheng³

2007

Humanoid Robots: New Developments

View full text Add to dashboard Cite

“…Examples of colour distribution geometrical model can be seen from the paper [6] proposed skin-segmentation color space of red and green chromatic color space. The paper uses two quadratic polynomials to create a boundary that separates skin colors from other colors which is used for classification.…”

Section: B Color Distribution Geometrical Modelmentioning

confidence: 99%

Adaptive Circular Enclosure Color Distribution Geometrical Model Utilizing Point In-Polygon for Segregation between Lips and Skin Pixels

Wei¹,

Phooi²,

Chong³

et al. 2013

IJFCC

View full text Add to dashboard Cite

Abstract-This paper is inspired from various boundary determination techniques which are used for segregating colours between background, skin and lips. Basic concept for this technique is based on colour segmentation with CIELAB colour-space utilized for justifiable reasons. Using LAB colourspace, lips colours were compiled into a colour-map and processed accordingly to our proposed algorithm of adaptive circular enclosure. Algorithm output was determined as a series of coordinates symbolizing boundary values surrounding colour-map. Separation of colours is based on these boundaries by creating a freeform polygon that defines if colour-value either belongs within colour-boundary polygon or not. This technique is famously known as the point in-polygon technique. Proposed technique evaluation uses XM2VTS database based on false-positive and false-negative to compute segmentation error. Simulation shows proposed algorithm yields segmented error of 5.55% with accuracy of 94.45%.

show abstract

“…The training data must be chosen carefully to include all possible lips configurations. Other image-based approaches proposed are rule-based approaches by features of a face (23) , pixelbased approaches using red exclusion (5) , optical-flow approaches to measure lips movement (24) , etc. However, these approaches cannot adapt to considerable geometric changes in lips in every frame.…”

Section: Related Workmentioning

confidence: 99%

High Speed Genetic Lips Detection by Dynamic Search Domain Control

et al. 2007

View full text Add to dashboard Cite

In this paper, high-speed size and orientation invariant lips detection of a talking person in an active scene using template matching and genetic algorithms is proposed (refer to Fig. 1). As part of the objectives, we also try to acquire numerical parameters to represent the lips. The information is very important for many applications, where high performance is required, such as audio-visual speech recognition, and personal mobile devices interfaces. The difficulty in lips detection is mainly due to deformations and geometric changes of the lips during speech and the active scene by free camera motion. In order to enhance the performance in speed and accuracy, initially, the performance is improved on a single still image, that is, the base of video processing.Our proposed system is based on template matching using genetic algorithms (GA). Only one template is prepared per experiment. The template is the closed mouth of a subject, because the application is for personal devices. In our previous study, the main problem was trade-off between search accuracy and search speed. To overcome this problem, we use two methods: scaling window and dynamic search domain control (SD-Control).The transition of the objective value on the proposed system and the no SD-Control are plotted in Fig. 2. At points from (a) to (d) in Figs. 2, the transition of GA exploration is exactly the same in both cases. The reason is that the same random numbers are used in both cases. Between points (d) and (e) in Fig. 2, the differences in the methods appear. This is because, the search domain is controlled from point (d) in Fig. 2. The elite individual of the no SD-Control do not change from point (c) to (g), hence it is concluded that the GA exploration gets trapped into a local optimum. The reason why the exploration was trapped into a local optimum is that the small population loses the population diversity and causes premature convergence.On the other hand, in case of the proposed system, the evolution make good progress from generation = 117 (point from (e) to (i)). This indicates that the GA of the proposed system can escape from the local maximum. The reason for this is that a search domain is reduced by the dynamic SD-Control and the GA can explore the reduced search domain with meticulous detail. This means that the GA in the proposed system performs not only global optimization but also local optimization. The result of our demonstration clearly shows that a trade-off between exploration accuracy and speed is overcome by the dynamic SD-Control.We achieved a lips detection accuracy of 91.33% at an average processing time of 33.70 milliseconds per frame. Stephen Karungaru * * Non-member Minoru Fukumi * * MemberIn this paper, high-speed size and orientation invariant lips detection of a talking person in an active scene using template matching and genetic algorithms is proposed. As part of the objectives, we also try to acquire numerical parameters to represent the lips. The information is very important for many applications, where ...

show abstract

A novel method for detecting lips, eyes and faces in real time

Cited by 93 publications

References 32 publications

Real-Time Vision Based Mouth Tracking and Parameterization for a Humanoid Imitation Task

Real-Time Vision Based Mouth Tracking and Parameterization for a Humanoid Imitation Task

Adaptive Circular Enclosure Color Distribution Geometrical Model Utilizing Point In-Polygon for Segregation between Lips and Skin Pixels

High Speed Genetic Lips Detection by Dynamic Search Domain Control

Contact Info

Product

Resources

About