Skin Pixels Research Articles

Skin Detection and Segmentation of Human Face in Color Images

This paper presents the procedures of face segmentation in the color image based on skin detection through the establishment of skin model and the segmentation of skin region. Firstly, in order to reduce the effect of factors on the segmentation of face region, a method for compensating the color of input images is used to alleviate the interferences from bad illuminating conditions. Secondly, Gaussian model about skin information is established which can be used to detect skin pixels in color images and transform color images to gray-scale images. Thirdly, a new algorithm of Otsu is used to find out the skin regions in binary images. Finally, mathematical morphology operator and prior knowledge are used to find out the face regions and discard regions that are similar to the skin in color. This method can deal with various sizes of faces, different illumination conditions, diverse poses and changeable expressions. In particular, the scheme significantly increases the execution speed of the face segmentation algorithm in the case of complex backgrounds. The experiments show that this method reduces the computation of the procedure, and at the same time improves the detection speed and efficiency.

Face Segmentation Based on Skin Color in Complicated Background and Its Sex Recognition

Human skin color distribution is relatively compact in a color space, and it changes from frame to frame following illumination variations, also it is subject to camouflage interruption in complicated background for skin segmentation. This paper mainly talks about face detection based on skin color feature in complicated background. We assume that skin pixels in each frame are closed together as a “dot cloud” in a color space, its shape evolution from frame to frame is modeled as the mixture of translation, scaling and rotation. We introduce linear combination of forecasts to predict these parameters related to the above shape evolutions, so that skin distribution of next frame to be segmented can be predicted and skin segmentation for face detection can be improved against illumination variations. Additionally human skin biological feature is then introduced to remove camouflage noise. For face gender recognition we adopt 2-D Gabor transform for feature extraction and SVM for recognition. Extensive tests prove that this algorithm is quite sensitive to human color, and more accurate for human skin segmentation with Bayes classifier; Good performance of gender classification test is also achieved on a relative large scale and low-resolution video database.

A Secure Skin Tone based Steganography Using Wavelet Transform

Steganography is the art of hiding the existence of data in another transmission medium to achieve secret communication. Steganography method used in this paper is based on biometrics. And the biometric feature used to implement Steganography is skin tone region of images (1). Here secret data is embedded within skin region of image that will provide an excellent secure location for data hiding. For this skin tone detection is performed using HSV (Hue, Saturation and Value) color space. Additionally secret data embedding is performed using frequency domain approach - DWT (Discrete Wavelet Transform), DWT outperforms than DCT (Discrete Cosine Transform). Secret data is hidden in one of the high frequency sub-band of DWT by tracing skin pixels in that sub-band. For data hiding two cases are considered, first is with cropping and other is without cropping. In both the cases different steps of data hiding are applied either by cropping an image interactively or without cropping i.e. on whole image. Both cases are compared and analyzed from different aspects. This is concluded that both cases offer enough security. Main feature of with cropping case is that this results into an enhanced security because cropped region works as a key at decoding side. Where as without cropping case uses embedding algorithm that preserves histogram of DWT coefficient after data embedding also by preventing histogram based attacks and leading to a more security. This study shows that by adopting an object oriented steganography mechanism, in the sense that, we track skin tone objects in image, we get a higher security. And simulation result shows that satisfactory PSNR (Peak-Signal-to-Noise Ratio) is also obtained.

Skin Color Detection Model Using Neural Networks and its Performance Evaluation

Problem statement: Skin color detection is used as a preliminary step in numerous computer vision applications like face detection, nudity recognition, hand gesture detection and person identification. In this study we present a pixel based skin color classification approach, for detecting skin pixels and non skin pixels in color images, using a novel neural network symmetric classifier. The neural classifiers used in the literature either uses a symmetric model with single neuron in the output layer or uses two separate neural networks (asymmetric model) for each of the skin and non-skin classes. The novelty of our approach is that it has two output layer neurons; one each for skin and non-skin class, instead of using two separate classifiers. Thus by using a single neural network classifier we have improved the separability between these two classes, eliminating additional time complexity that is needed in asymmetric classifier. Approach: Skin samples from web images of people from different ethnic groups were collected and used for training. Ground truth skin segmented images were obtained by using semiautomatic skin segmentation tool developed by the authors. The ground truth database of skin segmented images, thus obtained was used to evaluate the performance of our NN based classifier. Results: With proper selection of optimum classification threshold that varies from image to image the classifier gave the detection rate of more than 90% with 7% false positives on an average, Conclusion/Recommendations: It is observed that the neural network is capable of detecting skin in complex lighting and background environments. The classifier has the ability to classify the skin pixels belonging to people from different ethnic groups even when they are present simultaneously in an image. The proper choice of optimum classification threshold that varies from image to image is an issue here. Automatic computation of this optimum threshold for each image is desired in practical skin detection applications. This issue can be taken up as a future study, which will enable us to perform fully automatic skin segmentation with reduced false positives.

계층화된 3차원 피부색 모델을 이용한 피부색 분할

In order to detect the skin color area from input images, many prior researches have divided an image into the pixels having a skin color and the other pixels. In a still image or videos, it is very difficult to exactly extract the skin pixels because lighting condition and makeup generate a various variations of skin color. In this thesis, we propose a method that improves its performance using hierarchical merging of 3D skin color model and context informations for the images having various difficulties. We first make 3D color histogram distributions using skin color pixels from many YCbCr color images and then divide the color space into 3 layers including skin color region(Skin), non-skin color region(Non-skin), skin color candidate region (Skinness). When we segment the skin color region from an image, skin color pixel and non-skin color pixels are determined to skin region and non-skin region respectively. If a pixel is belong to Skinness color region, the pixels are divided into skin region or non-skin region according to the context information of its neighbors. Our proposed method can help to efficiently segment the skin color regions from images having many distorted skin colors and similar skin colors.

얼굴을 관심 영역으로 사용하는 자동 초점을 위한 얼굴 영역 추적 향상 방법 및 하드웨어 구현

본 논문은 얼굴을 관심 영역(ROI)으로 사용하는 자동 초점(AF, Auto Focusing) 시스템을 위 한 얼굴 검출 기능(Face Detection)의 얼굴 추적 향상 방법에 관한 것이다. 피부색을 바탕으로 얼굴을 검출하는 기존의 얼굴 검출 기능에서는 얼굴을 추적하기 위하여 이전 프레임에 검출된 얼굴 영역에 대하여 현재 프레임의 스킨 픽셀 비율을 사용한다. 이 방법은 동영상에서 얼굴 영역의 안정성은 뛰어나지만, 얼굴 추적 성능은 다소 떨어진다. 따라서 얼굴 추적 성능을 향상 시키기 위하여, 이전 프레임에 검출된 얼굴 영역과 현재 프레임에 검출된 얼굴 영역의 겹침을 조사하여 겹치는 영역의 면적을 이용하여 얼굴을 추적하는 방법을 제안하였다. 검증을 위하여 FPGA 보드와 모바일 폰 카메라용 CIS를 이용하여 실시간으로 얼굴 검출을 촬영하였고, 검출된 얼굴의 이동 궤적을 이용하여 성능을 검증하였다. In this paper, we proposed a method about improving face tracking efficiency of face detection for AF system using the faces to the ROI. The conventional face detection system detecting faces based skin color uses the ratio of skin pixels of the present frame to detected face regions of the past frame to track the faces. The tracking method is superior in the stability of the regions but it is inferior in the face tracking efficiency. We proposed a face tracking method using the area of the overlapping region in the detected face regions of the past frame and the present frame to improve the tracking efficiency. The proposed face tracking efficiency demonstration was performed by making a film of face detection with face tracking in real-time and using the moving traces of the detected faces.

Special issue on advances in image and video processing techniques

[1. Background and Motivation] This special issue of the Multimedia Tools and Applications Journal contains extended papers selected from the image and video processing sessions and multimedia sessions of ELMAR symposia held in Zadar, Croatia, in 2008 and 2009 (more information about ELMAR symposia can be found here: www.elmar-zadar.org). Eight selected papers provide a coverage of recent advances in image and video processing. Papers were selected by the Guest Editors of this special issue in September 2009, and the respective authors were invited to submit the extended versions of their papers, along with further research they conducted on the subject. // Multimedia is all around us and we are often reminded that we live in the age of multimedia. It is in products and services like digital TV, IPTV, video and image databases, social networking etc. Time between research and final consumer product has never been shorter and this is one of the reasons why multimedia is still an attractive and widely researched area. Given the wide area of multimedia tools and applications usage in real life, it is necessary to research and develop algorithms and methods in various fields, and this special issue reflects this fact in its wide range of topics covered. // [2. Scanning the Special Issue] The two papers that open this special issue deal with an important subject of video quality assessment. The first paper is of HDTV Formats using Objective Video Quality Measures by Emil Dumic, Sonja Grgic and Mislav Grgic. By combining subjective and objective quality measures the authors show that progressive scanning should be preferred to interlaced for all future HDTV emissions. The second paper is Mean Squared Error - A Novel Video Quality Metric where Snjezana Rimac-Drlje, Mario Vranjes and Drago Zagar propose a new video quality measure called Foveated Mean Squared Error (FMSE) that takes into account the non-uniform sampling corresponding to the visual information acquisition process at the human retina. FMSE shows high correlation to the subjective quality assessment. // is the central theme of the next three papers in this special issue. In Segmentation of Optic Disc in Retinal Images using an Improved Gradient Vector Flow Algorithm by Huiyu Zhou, Gerald Schaefer, Tangwei Liu and Faquan Lin, a novel medical image segmentation algorithm is presented. It is based on gradient vector flow and is used for segmenting the optic disc in retinal images to support automatic screening. Michal Kawulok addressed the problem of precise skin segmentation for sign language purposes in his article entitled Energy-based Blob Analysis for Improving Precision of Skin Segmentation. The presented approach uses blob analysis and takes into account skin pixel topology which is usually disregarded by other color-based skin detectors. The paper Automatic MPEG-4 Sprite Coding - Comparison of Integrated Object Algorithms, by Alexander Glantz, Andreas Krutz, Thomas Sikora, Paulo Nunes and Fernando Pereira, proposes an automatic object segmentation algorithm for video sequences with a moving camera towards automatic object representation for sprite coding as standardized in MPEG-4 Visual. In their experiments, the authors have showed that their algorithm performs comparable to manually segmented groundtruth masks, implying almost perfect segmentation. // The last three papers cover areas of content retrieval, watermarking and face recognition. In the paper entitled: Interactive Search and Browsing Interface for Large-scale Visual Repositories, Kan Ren, Risto Sarvas and Janko Calic present a way in which a user can intuitively navigate through a large image and video collections. In the paper Two Dimensional Time-Frequency Analysis based Eigenvalue Decomposition Applied to Image Watermarking, Srdjan Stankovic, Irena Orovic, Nikola Zaric and Cornel Ioana propose applying spatial-frequency analysis and eigenvalue decomposition to provide an efficient image watermarking method. The efficiency of the proposed method and its robustness in the presence of various attacks is proven in extensive reported experiments. The last paper of this special issue is Aligned Texture Map Creation for Pose Invariant Face Recognition by Antonio Rama, Francesc Tarres and Jurgen Rurainsky. The paper deals with a novel face recognition method called Partial Principal Component Analysis. The method has been proved to be efficient in pose-varying recognition scenarios. The paper also presents a novel approach for the automatic creation of 180 degrees aligned cylindrical projected face images using different views, which are then used for training purposes in the presented face recognition method. // [Acknowledgements] The Guest Editors would like to thank all those who have helped to make this special issue possible, especially to ELMAR symposium organizers and committee members, all authors and the reviewers. The Guest Editors would like to gratefully acknowledge Prof. Borko Furht, Editor-in-Chief of the Multimedia Tools and Applications Journal, for giving them the opportunity to publish this special issue.

컬러 정보를 이용한 실시간 표정 데이터 추적 시스템

온라인 기반의 3차원 얼굴 애니메이션을 위해서 실시간으로 얼굴을 캡처하고 표정 데이터를 추출하는 것은 매우 중요한 작업이다. 최근 동영상 입력을 통해 연기자의 표정을 캡처하고 그것을 그대로 3차원 얼굴 모델에 표현하는 비전 기반(vision-based) 방법들에 대한 연구가 활발히 이루어지고 있다. 본 논문 에서는 실시간으로 입력되는 동영상으로부터 얼굴과 얼굴 특징점들을 자동으로 검출하고 이를 추적하는 시스템을 제안한다. 제안 시스템은 얼굴 검출과 얼굴 특징점 추출 및 추적과정으로 구성된다. 얼굴 검출은 3차원 YCbCr 피부 색상 모델을 이용하여 피부 영역을 분리하고 Harr 기반 검출기를 이용해 얼굴 여부를 판단한다. 얼굴 표정에 영향을 주는 눈과 입 영역의 검출은 밝기 정보와 특정 영역의 고유한 색상 정보를 이용한다. 검출된 눈과 입 영역에서 MPEG-4에서 정의한 FAP를 기준으로 10개의 특징점을 추출하고, 컬러 확률 분포의 추적을 통해 연속 프레임에서 특징점들의 변위를 구한다 실험 결과 제안 시스템 은 약 초당 8 프레임으로 표정 데이터를 추적하였다. It is very important to extract the expression data and capture a face image from a video for online-based 3D face animation. In recently, there are many researches on vision-based approach that captures the expression of an actor in a video and applies them to 3D face model. In this paper, we propose an automatic data extraction system, which extracts and traces a face and expression data from realtime video inputs. The procedures of our system consist of three steps: face detection, face feature extraction, and face tracing. In face detection, we detect skin pixels using YCbCr skin color model and verifies the face area using Haar-based classifier. We use the brightness and color information for extracting the eyes and lips data related facial expression. We extract 10 feature points from eyes and lips area considering FAP defined in MPEG-4. Then, we trace the displacement of the extracted features from continuous frames using color probabilistic distribution model. The experiments showed that our system could trace the expression data to about 8fps.

Face detection using template matching and skin-color information

A face-detection approach is proposed in the paper. Firstly, a luminance-conditional distribution model of skin-color information is used to detect skin pixels in color images; then, morphological operations are used to extract skin-region rectangles; finally, template matching based on a linear transformation is used to detect face in each skin-region rectangle. Experimental results on some color images from the FERET database and from the Internet are encouraging. The proposed algorithm is shown to be effective and efficient in detecting frontal faces in color images.

An adaptive real-time skin detector based on Hue thresholding: A comparison on two motion tracking methods

Various applications like face and hand tracking and image retrieval have made skin detection an important area of research. However, currently available algorithms are based on static features of the skin colour, or require a significant amount of computation. On the other hand, skin detection algorithms are not robust to deal with real-world conditions, like background noise, change of intensity and lighting effects. This situation can be improved by using dynamic features of the skin colour in a sequence of images. This article proposes a skin detection algorithm based on adaptive Hue thresholding and its evaluation using two motion detection technique. The skin classifier is based on the Hue histogram of skin pixels, and adapts itself to the colour of the skin of the persons in the video sequence. This algorithm has demonstrated improvement in comparison to the static skin detection method.

Pixel-based skin color detection technique

One of the simplest features used for the human face detection problem is the skin color information. A simple and relatively efficient histogram-based algorithm to segment skin pixels from a compl...

Blocking Adult Images Based on Statistical Skin Detection

This work is aimed at the detection of adult images that appear in Internet. Skin detection is of the paramount importance in the detection of adult images. We build a maximum entropy model for this task. This model, called the First Order Model in this paper, is subject to constraints on the color gradients of neighboring pixels. Parameter estimation as well as optimization cannot be tackled without approximations. With Bethe tree approximation, parameter estimation is eradicated and the Belief Propagation algorithm permits to obtain exact and fast solution for skin probabilities at pixel locations. We show by the Receiver Operating Characteristics (ROC) curves that our skin detection improves the performance in the previous work in the context of skin pixel detecton rate and false positive rate. The output of skin detection is a grayscale skin map with the gray level indicating the belief of skin. We then calculate 9 simple features from this map which form a feature vector. We use the fit ellipses to catch the characteristics of skin distribution. Two fit ellipses are used for each skin map---the fit ellipse of all skin regions and the fit ellipse of the largest skin region. They are called respectively Global Fit Ellipse and Local Fit Ellipse in this paper. A multi-layer perceptron classifier is trained for these features. Plenty of experimental results are presented including photographs and a ROC curve calculated over a test set of 5,084 photographs, which show stimulating performance for such simple features.

HUMAN FACE DETECTION IN COLOR IMAGES

In this paper we have used a simple and efficient color-based approach to segment human skin pixels from background, using a 2D histogram-based approach as a preprocess stage for human face detection. For skin segmentation, a total of 446,007 skin samples from the training set is manually cropped from the RGB color images, to calculate three lookup tables based on the relationship between each pair of the triple components (R, G, B). Derivation of skin classifier rules from the lookup tables are based on how often each attribute value (interval) occurs, and their associated certainty values. For face detection, we assume the face-appearance as blob-like, and that the face has an approximately elliptical shape. Accordingly, an ellipse-fitting algorithm is appropriate, which is based on statistical moments, and those blobs that have an elliptical shape are retained as face candidates.

Automatic scalable face model design for 2D model-based video coding

Scalable low bit-rate video coding is vital for the transmission of video signals over wireless channels. A scalable model-based video coding scheme is proposed in this paper to achieve this. This paper mainly addresses automatic scalable face model design. Firstly, a robust and adaptive face segmentation method is proposed, which is based on piecewise skin-colour distributions. 43 million skin pixels from 900 images are used to train the skin-colour model, which can identify skin-colour pixels reliably under different lighting conditions. Next, reliable algorithms are proposed for detecting the eyes, mouth and chin that are used to verify the face candidatures. Then, based on the detected facial features and human face muscular distributions, a heuristic scalable face model is designed to represent the rigid and non-rigid motion of head and facial features. A novel motion estimation algorithm is proposed to estimate the object model motion hierarchically. Experimental results are provided to illustrate the performance of the proposed algorithms for facial feature detection and the accuracy of the designed scalable face model for representing face motion.

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

This paper presents a real-time face detection algorithm for locating faces in images and videos. This algorithm finds not only the face regions, but also the precise locations of the facial components such as eyes and lips. The algorithm starts from the extraction of skin pixels based upon rules derived from a simple quadratic polynomial model. Interestingly, with a minor modification, this polynomial model is also applicable to the extraction of lips. The benefits of applying these two similar polynomial models are twofold. First, much computation time are saved. Second, both extraction processes can be performed simultaneously in one scan of the image or video frame. The eye components are then extracted after the extraction of skin pixels and lips. Afterwards, the algorithm removes the falsely extracted components by verifying with rules derived from the spatial and geometrical relationships of facial components. Finally, the precise face regions are determined accordingly. According to the experimental results, the proposed algorithm exhibits satisfactory performance in terms of both accuracy and speed for detecting faces with wide variations in size, scale, orientation, color, and expressions.

Do mixture models in chromaticity space improve skin detection?

This note reports an experiment where a single Gaussian model and several Gaussian mixture models were used to model skin color in the rg chromaticity space. By using training and test databases containing millions of skin pixels, we show that mixture models can improve skin detection, but not always. There is a relevant operating region where no performance gain is observed.

A robust scheme for live detection of human faces in color images

In this paper, an efficient algorithm for detecting human faces in color images is proposed. The first step of our algorithm is to segment the possible skin-like regions in an image by using color information. One of the major problems of using skin color is that a face region may not be detected under poor lighting conditions, or if the lighting conditions vary over the face region. Our approach considers the distributions of the color components of skin pixels under different illuminations. This information can be used to identify skin-color pixels reliably under varying lighting conditions. The skin-color regions are then clustered and verified as human face regions. In order to improve the reliability and accuracy, an eigenmask that has a large magnitude at the important facial features of a human face is used in the detection. Experimental results show that this algorithm can detect human faces under varying lighting conditions reliably and fast.

Adaptive skin color modeling using the skin locus for selecting training pixels

Techniques for color-based tracking of faces or hands often assume a static skin model yet skin color, as measured by a camera, can change when lighting changes. Therefore, for robust skin pixel detection, an adaptive skin color model must be employed. We demonstrate a chromaticity-based constraint to select training pixels in a scene for updating a dynamic skin color model under changing illumination conditions. The method makes use of the ‘skin locus’ of a camera, that is, the area in chromaticity space where skin chromaticity under various lighting and camera calibration conditions is observed. Skin color models derived from the technique are compared with that derived by a common spatial constraint and is shown to be more consistent with manually extracted ground truth skin model per frame even as localization errors increase. The technique is applied to color-based face tracking in indoor and outdoor videos and is shown to succeed more often than other color model adaptation techniques.

Statistical color models with application to skin detection

The existence of large image datasets such as photos on the World Wide Web make it possible to build powerful generic models for low-level image attributes like color using simple histogram learning techniques. We describe the construction of color models for skin and non-skin classes from a dataset of nearly 1 billion labeled pixels. These classes exhibit a surprising degree of separability which we exploit by building a skin pixel detector that achieves an equal error rate of 88%. We compare the performance of histogram and mixture models in skin detection and find histogram models to be superior in accuracy and computational cost. Using aggregate features computed from the skin detector we build a remarkably effective detector for naked people. We believe this work is the most comprehensive and detailed exploration of skin color models to date.