On Color Texture Normalization for Active Appearance Models

Ionita, Mircea C.; Corcoran, Peter; Buzuloiu, Vasile

doi:10.1109/tip.2009.2017163

Cited by 15 publications

(10 citation statements)

References 9 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally color information is encoded via the normalization technique proposed by [24]. Constrained regression is used to build a person-specific ageing model.…”

Section: Methodsmentioning

confidence: 99%

“…A parameterised model is formed by using Principal Component Analysis (PCA) to combine shape and texture models thereby describing seen and unseen images [23]. Initially it was designed for greyscale images, however the technique has been extended to incorporate color information [24].…”

Section: Features Extraction Using Color Aammentioning

confidence: 99%

“…However, when dealing with color texture there is chromaticity variation in addition to the normal intensity variation [24]. It has been observed that these two variations are mixed within each of the three RGB color channels, and there is strong cross correlation between RGB channels thereby affecting performance [24]. While other color representations such as CIELAB have been considered in the past, the I1I2I3 color space [28] has been most successful [24].…”

Section: Features Extraction Using Color Aammentioning

confidence: 99%

“…It has been observed that these two variations are mixed within each of the three RGB color channels, and there is strong cross correlation between RGB channels thereby affecting performance [24]. While other color representations such as CIELAB have been considered in the past, the I1I2I3 color space [28] has been most successful [24]. This is because it uses PCA to decorrelate the RGB channels.…”

Section: Features Extraction Using Color Aammentioning

confidence: 99%

See 3 more Smart Citations

Individualised model of facial age synthesis based on constrained regression

Bukar

Ugail

Connah

2015

2015 International Conference on Image Processing Theory, Tools and Applications (IPTA)

View full text Add to dashboard Cite

-Faces convey much information. Interestingly we humans have a remarkable ability of identifying, extracting, and interpreting this information. Recently automatic facial ageing (AFA) has gained popularity due to its numerous applications which include search for missing people, biometrics, and multimedia. The problem of AFA is faced with various challenges, including incomplete training datasets, unrestrained environments, ethnic and gender variations to mention but a few. This work presents a new approach to automatic facial ageing which involves the development of a person specific facial ageing system. A color based Active Appearance Model (AAM) is used to extract facial features. Then, regression is used to model an age estimator. Age synthesis is achieved by computing a solution that minimises the distance from the original face with the use of constrained regression. The model is tested on a challenging database of single image per person. Initial results suggest that plausible images can be rerendered at different ages, automatically using the AAM representation. Using the constrained regressor we are guaranteed to get estimated ages that are exact for an individual at a given age.

show abstract

“…Additionally color information is encoded via the normalization technique proposed by [24]. Constrained regression is used to build a person-specific ageing model.…”

Section: Methodsmentioning

confidence: 99%

Section: Features Extraction Using Color Aammentioning

confidence: 99%

Section: Features Extraction Using Color Aammentioning

confidence: 99%

Section: Features Extraction Using Color Aammentioning

confidence: 99%

See 2 more Smart Citations

Individualised model of facial age synthesis based on constrained regression

Bukar

Ugail

Connah

2015

2015 International Conference on Image Processing Theory, Tools and Applications (IPTA)

View full text Add to dashboard Cite

show abstract

“…One of the more powerful techniques developed in recent years has been that of active appearance models (AAMs), originally developed by Tim Cootes [19], [20]. These models have been continually improved [16], [21]- [23] and extended to provide models for various facial features [24]- [26].…”

Section: Face and Face Feature Modelsmentioning

confidence: 99%

Digital Beauty: The good, the bad, and the (not-so) ugly

Corcoran

Stan²,

Florea³

et al. 2014

IEEE Consumer Electron. Mag.

View full text Add to dashboard Cite

Prediction and visualization of moisture content in Tencha drying processes by computer vision and deep learning

You,

Li,

Wang

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDMonitoring and controlling the moisture content throughout the Tencha drying processing procedure is crucial for ensuring its quality. Workers often rely on their senses to perceive the moisture content, leading to relative subjectivity and low reproducibility. The traditional drying methods for measuring moisture content is destructive to samples. This research was conducted using computer vision combined with deep learning for detecting moisture content during the Tencha drying process. Different color space components of Tencha drying samples’ image were first extracted by computer vision. The color components were preprocessed using MinMax and Z‐score. Subsequently, one‐dimensional convolutional neural network (1D‐CNN), partial least squares, and backpropagation artificial neural network models were built and compared.RESULTSThe 1D‐CNN model and Z‐score preprocessing achieved superior predictive accuracy, with correlation coefficient of prediction (Rp) = 0.9548 for moisture content. Furthermore, the migration of moisture content during the Tencha drying process was eventually visualized by mapping its spatial and temporal distributions.CONCLUSIONThe results indicated computer vision combined with 1D‐CNN was feasible for moisture prediction during Tencha drying process. This study provides technical support for the industrial and intelligent production of Tencha.This article is protected by copyright. All rights reserved.

show abstract

On Color Texture Normalization for Active Appearance Models

Cited by 15 publications

References 9 publications

Individualised model of facial age synthesis based on constrained regression

Individualised model of facial age synthesis based on constrained regression

Digital Beauty: The good, the bad, and the (not-so) ugly

Prediction and visualization of moisture content in Tencha drying processes by computer vision and deep learning

Contact Info

Product

Resources

About