Skin Color Pixels Research Articles

CBIF-M: A content-based image filtering and retrieval scheme using multi-classifier filtering framework

Recently, the image retrieval process appears to be a challenging task to filter out a huge volume of objectionable images from retrieval. It is very easy for people of all ages to obtain such obscene images with just a few clicks on the internet, which could harm the adolescent. To prevent such serious social problems, this paper introduces a content-based image filtering (CBIF) framework in an image retrieval system. The proposed CBIF approach is split into two components. In the first component, the skin region of exposed human body parts is extracted based on a color segmentation method, and an efficient feature vector generation process is introduced based on frequent skin color pixels and scale-invariant structural features. A novel texture feature representation is presented in the retrieval and filtering process obtained by block-paired local binary pattern (BP-LBP). The final component introduces a novel image filtering framework for the retrieved images found from the first component based on a majority of voting method on three different machine learning classifiers backed by SVM, MLP, and CNN. The retrieval efficiency is analyzed with standard performance indicators such as precision, recall, and F-score on two large datasets: NPDI and NSFW.

DETECÇÃO DE NUDEZ EM IMAGENS POR SEGMENTAÇÃO E RECONHECIMENTO DE PADRÕES

With the emergence of the INTERNET and the growth of social networks, the sharing of content, such as images, audios and videos, and access to this content through websites and social networks, has become much greater. Shared content, consisting of images, audio and/or videos, may not be appropriate for all audiences or environments, for various reasons. One of them is in relation to nudity and pornography, which is very present on the INTERNET and social networks, and can cause negative impacts when accessed in business environments, as well as it can cause problems in the development and behavior of children and adolescents. In order to control access to these types of content, it is necessary to develop resources that perform filtering. Therefore, this work seeks to contribute to the development of a tool capable of detecting nudity in images by combining existing image processing techniques, such as the detection of skin color pixels, counting of related elements, zoning techniques and nudity classifiers using machine learning algorithms. Tests carried out on showed an accuracy of 90.5% in the best case.

A new model for small target adult image recognition

Abstract With the advent of the era of 5G high speed and massive information, the audience of netizens is developing at a younger age, and the proliferation of adult images on the Internet is becoming more and more serious. The recognition and filtering of adult pictures has become very important to prevent young people from contacting harmful information. But, because of the wide variety of adult images, automatic recognition in these pictures is a very difficult task. This paper proposes a new model based on Residual neutral network. Our method consists of two parts. The first part is to divide images into large target skin color image and target skin color image according to the proportion of skin color pixels of the image; The second part is to input the two types of images into two different models for recognition. According to the results of comparative experiments, the proposed network can further improve the classification accuracy of adult images of small targets with excessive background noise, which is better than other single model.

Image Segmentation for Skin Detection

Human skin detection, which usually performed before image processing, is the method of discovering skin-colored pixels and regions that may be of human faces or limbs in videos or photos. Many computer vision approaches have been developed for skin detection. A skin detector usually transforms a given pixel into a suitable color space and then uses a skin classifier to mark the pixel as a skin or a non-skin pixel. A skin classifier explains the decision boundary of the class of a skin color in the color space based on skin-colored pixels. The purpose of this research is to build a skin detection system that will distinguish between skin and non-skin pixels in colored still pictures. This performed by introducing a metric that measures the distances of pixel colors to skin tones. Results showed that the YCbCr color space performed better skin pixel detection than regular Red Green Blue images due to its isolation of the overall energy of an image in the luminance band. The RGB color space poorly classified images with wooden backgrounds or objects. Then, a histogram-based image segmentation scheme utilized to distinguish between the skin and non-skin pixels. The need for a compact skin model representation should stimulate the development of parametric models of skin detection, which is a future research direction.

A Method for Obtaining Human Skin Color Pixels Based on Surrounding Factors

A Method for Obtaining Human Skin Color Pixels Based on Surrounding Factors

GPU accelerated face detection from low resolution surveillance videos using motion and skin color segmentation

Surveillance systems are being used at most of the places nowadays for the security purpose, which involves face biometrics as an essential step. However, frequently the resolution of faces in surveillance videos is small owing to the various factors such as the distance between CCTVs and place of footage, wide coverage angle, installation problems, environmental factors and hardware constraints which make it difficult to detect and extract the human faces from surveillance videos. In this paper, we have worked on using the motion and skin color based segmentation to extract the region of interest which is subsequently subjected to face detection. Further GPU acceleration has been employed to facilitate real-time face detection. There are following main contributions made in this work: firstly, the adaptability in the selection of lowest and highest values of scaling factors to facilitate the multi-scale face detection based on the analysis of regions segmented by motion and skin color pixels. Secondly, the use of a band of pre-trained Haar-classifiers and image scaling to facilitate multi-scale face detection has been done unlike Viola–Jones algorithm which is based on detector scaling. Pre-trained classifiers of base size in the range of 13 by 13 to 30 by 30 pixels have been used for the face detection in this range. The faces of size higher than 30 by 30 pixels are detected by applying the image scaling. The proposed algorithm has been successfully tested on surveillance videos from dataset ChokePoint to detect the low-resolution faces of minimum size of the order of 8 by 8 pixels.

Skin color modeling for face detection and segmentation: a review and a new approach

Detecting skin-colored pixels, although seems a straightforward easy task, has proven to be quite a challenging task in images that are captured under complex unconstrained imaging conditions. Color segmentation is an important method of segmenting the body in images. In this paper, we first provides a review of skin color modeling research works for face detection. In particular, we focus on discussing the challenges of skin color modeling, detection, and segmentation, and then we present the skin color modeling and region-based skin segmentation. We also propose a new approach to analyze the hue characteristics of monitoring personnel in coal mine. We determine the skin color boundaries of the miners using the boundary detection method based on the response of visual hue. And then, we apply to determining hue area method using dual hue detector to segment skin color for miners. Experiments show that the method has excellent ability to segment skin regions of miners. We also summarize the most widely used methods for skin detection approaches and collecting their numerical evaluation results.

An Improved Adaptive Threshold Skin Color Model

To solve the problem that traditional threshold segmentation model is not very robust in skin segmentation under different skin colors and different illuminations, an improved adaptive skin color model is proposed. This model detects the change rate of the skin color pixels by modifying the certain threshold while fixing others, then selects the optimum threshold adaptively. The experimental results show that this algorithm can effectively distinguish skin color regions and background regions, and has strong robustness on light disturbance.

Skin Segmentation Using YUV and RGB Color Spaces

Skin detection is used in many applications, such as face recognition, hand tracking, and human-computer interaction. There are many skin color detection algorithms that are used to extract human skin color regions that are based on the thresholding technique since it is simple and fast for computation. The efficiency of each color space depends on its robustness to the change in lighting and the ability to distinguish skin color pixels in images that have a complex background. For more accurate skin detection, we are proposing a new threshold based on RGB and YUV color spaces. The proposed approach starts by converting the RGB color space to the YUV color model. Then it separates the Y channel, which represents the intensity of the color model from the U and V channels to eliminate the effects of luminance. After that the threshold values are selected based on the testing of the boundary of skin colors with the help of the color histogram. Finally, the threshold was applied to the input image to extract skin parts. The detected skin regions were quantitatively compared to the actual skin parts in the input images to measure the accuracy and to compare the results of our threshold to the results of other's thresholds to prove the efficiency of our approach. The results of the experiment show that the proposed threshold is more robust in terms of dealing with the complex background and light conditions than others.

Research and Improvement on the Algorithm of Face Region Detection Based on Skin Color Model

In face image with complex background, the CbCr skin color region will have offset when considering the illumination change. Therefore, the non-skin color pixels which luminance is less than 80 will be mistaken as skin color pixels and the skin color pixels which luminance is greater than 230 will be mistaken as non-skin color pixels. In order to reduce the misjudgments, an improved skin color model of nonlinear piecewise is put forward in this paper. Firstly, the skin color model of non-piecewise is analyzed and the experimental results show that by this model there is an obvious misjudgment in face detection. Then the skin color model of nonlinear piecewise is mainly analyzed and is demonstrated by mathematics method. A large number of training results show that the skin color model of nonlinear piecewise has better clustering distribution than the skin color model of non-piecewise. At lastly, the face detection algorithm adopting skin color model of nonlinear piecewise is analyzed. The results show that this algorithm is better than the algorithm adopting skin color model of non-piecewise and it makes a good foundation for the application of face image.

Skin colour correction and faces detection techniques based on HSL and R colour components

Human face detection is the first step towards face recognition, video surveillance and bioinformatics applications. The first step in faces detection is skin colour detection. Skincolour detection in visible spectrum is a very challenging task as the skin colour in an image is sensitive to various factors such as sensor characteristics, illumination, optics and ethnicity. Many researchers emphasise that there is a relationship between surface colours and illumination which is closely related problem of colour constancy. Colour correction stage should come first before applying skin colour detection to get better recognition rate. In this paper, a new approach Illumination Reflection Problem (IRP) has been proposed to correct the skin colour in the image that suffers from illumination reflection problem. IRP approach succeeded to correct the colour of 95% of affected pixels from illumination reflection problem. Also, a new approach to solve colour constancy problem is proposed named MMCrCb (Mean of Medians of Cr Cb). The purpose of this correction approach is to prepare the image prior to applying skin detection technique. Its methodology based on transforming the image to YCbCr then correcting the values of Y, Cb and Cr. After doing correction, transform the image back to RGB. Images from Caltech Image Database that suffer from colour constancy problem were used to test the MMCrCb approach. Also nine skin colour detection techniques were investigated and compared with a new proposed technique for skin detection using HSL and R colour components. The data base used for testing that approach was the MUCT database. The MUCT database provides more diversity of lighting, age and ethnicity. The testing results proved that the proposed skin detection technique using HSL and R is the best among techniques in the literature. In addition to that, the use of MMCrCb colour constancy correction approach with the proposed skin detection technique increases the skin colour pixels classification rate of unbalanced colour images by 20%.

A Hybrid Hand Detection Algorithm for Human Computer Interaction using Skin Color and Motion Cues

complex background, a hybrid hand detection algorithm based on the hand motion and the skin color is introduced. Gaussian Mixture Model (GMM) is used for the Foreground Detection. Skin Detection is performed on Foreground objects. For the purpose of Skin Detection a Look-up Table (LUT) is generated by collecting large number of skin color pixels in YCbCr color space. Skin segmentation is performed by thresholding each frame to obtain a binary image of the skin color area. Morphological operations are used to enhance the segmentation results. Experimental results show that the proposed algorithm can accurately detect different hand shapes under complex background, which is the most necessary step in the HCI. KeywordsColor Segmentation, Computer Vision, hand Detection, Foreground detection.

색상과 얼굴 특징 정보를 이용한 얼굴 추적

TIn this paper, we find the face in color images and the ability to track the face was implemented. Face tracking is the work to find face regions in the image using the functions of the computer system and this function is a necessary for the robot. But such as extracting skin color in the image face tracking can not be performed. Because face in image varies according to the condition such as light conditions, facial expressions condition. In this paper, we use the skin color pixel extraction function added lighting compensation function and the entire processing system was implemented, include performing finding the features of eyes, nose, mouth are confirmed as face. Lighting compensation function is a adjusted sine function and although the result is not suitable for human vision, the function showed about 4% improvement. Face features are detected by amplifying, reducing the value and make a comparison between the represented image. The eye and nose position, lips are detected. Face tracking efficiency was good.

An Improved Skin Color Detection Algorithm Model

The main objective of designing skin color model is to determine whether the pixel is skin color pixels and generate the skin color mask images. The paper discusses the choise of color space and skin color model designing in skin color detection system, analysis the problems often needed to solve in it and put forward an improved skin color detection algorithm model based on ellipse boundary. The skin color detection experiment is completed. The result of experiment shows the skin color detection algorithm model is good.

Genetic eigenhand selection for handshape classification based on compact hand extraction

This study proposes compact hand extraction to assist in computerized handshape recognition. First, we devised an image enhancement technique based on singular value decomposition to remove dark backgrounds by reserving the skin color pixels of a hand image. Then, the polynomial approximation YCbCr color model was used to extract the hand. After alignment, we applied lighting compensation to the adaptable singular value decomposition. Finally, a hierarchical pyramid sampling algorithm was used to reduce the impact of variations in handshape. We also constructed a self-eigenhand recognizer with genetic algorithms (GA) for selecting discriminant eigenvector subsets for classification. Although our approach maximizes the differences in hand images for various handshapes, it also minimizes variations in lighting and pose for the same handshape. Experimental results for images from our database and a live sequence showed that our method functioned more efficiently than conventional ones that do not use compact hand extraction against complex scenes. For the 768 images included in inside testing, our classification system achieved an AAR of 99.55% and an FAR of 0.0001%. For live testing, the classification system achieved an accuracy rate of 91.7%, with an error rate of 8.3%. Regarding speed, our system was faster than conventional ones. Our images size was 160×120 pixels, operating at an average processing time of less than 1s per handshape (using an AMD64 Athlon CPU 2.0GHz personal computer).

A Context-aware Approach for Detecting Skin Colored Pixels in Images

Detecting the human skin and its analysis has number of important applications. This is a challenging task as. in images, the skin color is quite sensitive to the chrominance and intensity of the pixels. So the techniques with a single model for skin fail to cope up with the variation in skin colors because of ethnicity, age, lighting etc. This paper proposes a novel technique for skin detection in color images. The proposed technique has two steps; (i) first the faces of humans are detected in the color images (ii) then based on the statistics captured from the sampling of the face area, the rest of the skin is detected. For face detection purpose, we train a binary classifier using machine learning approach. After face detection, the sampled pixels are matched to find the other exposed skin areas using an approach based on Gaussian model for skin.

Fusion of Multi Color Space for Human Skin RegionSegmentation

This paper proposes a technique to extract human skin color regions from the color images based on combination of both RGB and YU'V color spaces. Since skin pixels can vary with ambient light, to find the range of values for which most skin pixels fall in the skin color space becomes a hard task. Therefore, other techniques based on normalized rg, HSV, YUV, YIQ, YCbCr, RGB, YCbCr-YU'V color spaces are presented and compared in this paper in order to select the appropriate control limits for the purpose of skin color segmentation. From the experimental results, the skin detection results obtained by the proposed technique based on RGB-YU'V color model is found to be the most appropriate color model compared to other methods. I. I NTRODUCTION Skin color contains relatively concentrated information in human's faces color images. A skin color detection system is always used in many vision systems, such as gesture recognition, hand tracking, video indexing, region of interest extraction and face detection. The main work of skin color detection is to build a noise filter for removing the non-skin color pixels, so that the remaining skin color pixels will fall in the given color space. A color space is a specification of a coordinate system where each color is represented by a single value. Various color spaces are used for processing digital images. A face detection method based on YCbCr is proposed in (1). In their method, skin color regions are extracted which excludes the non-skin color regions using the sigma control limits for color variations. This skin color detection system is very efficient in accuracy. Apart from this method which utilizes merely one color space, there are also methods which employ more than one color space. Two major methods utilizing more than one color space are based on combination of YCbCr-YU'V and RGB-YU'V color spaces. Both YCbCr-YU'V and RGB-YU'V color spaces are shown to be robust and reliable for human skin color detection. These two approaches are based on saturation parameter control limits. In this paper, a series of skin color segmentation methods based on normalized rg, HSV, YUV, YIQ, YCbCr, RGB,

Dynamic approach for real-time skin detection

Human face and hand detection, recognition and tracking are important research areas for many computer interaction applications. Face and hand are considered as human skin blobs, which fall in a compact region of colour spaces. Limitations arise from the fact that human skin has common properties and can be defined in various colour spaces after applying colour normalization. The model therefore, has to accept a wide range of colours, making it more susceptible to noise. We have addressed this problem and propose that the skin colour could be defined separately for every person. This is expected to reduce the errors. To detect human skin colour pixels and to decrease the number of false alarms, a prior face or hand detection model has been developed using Haar-like and AdaBoost technique. To decrease the cost of computational time, a fast search algorithm for skin detection is proposed. The level of performance reached in terms of detection accuracy and processing time allows this approach to be an adequate choice for real-time skin blob tracking.

Fast Face Detection Algorithm Based on Improved Skin-Color Model

Automatic face recognition is one of the most challenging tasks in fields of computer vision and pattern recognition, and face detection is the first critical step in full automatic face recognition system. The skin-color feature is an effective feature, but this feature is interfered easily. This paper proposes a method of face detection from a picture based on an improved skin-color model. Firstly, use an improved “reference white” method to remove the interference of non-skin-color region, and then design color- classifier based on statistic large number of skin-color pixels and detect each pixel in color picture is skin-color or non-skin-color through the color-classifier; finally, detect face on the candidate regions and remove the non-face regions, and then locate the face regions. Experimental results show that the algorithm can effectively detect face with skin-color interference under complex background.

A Skin Detection Algorithm Based on Bayes Decision in the YCbCr Color Space

Skin color detection is a hot research of computer vision, pattern identification and human-computer interaction. Skin region is one of the most important features to detect the face and hand pictures. For detecting the skin images effectively, a skin color classification technique that employs Bayesian decision with color statistics data has been presented. In this paper, we have provided the description, comparison and evaluation results of popular methods for skin modeling and detection. A Bayesian approach to skin color classification was presented. The statistics of skin color distribution were obtained in YCbCr color space. Using the Bayes decision rule for minimum cot, the amount of false detection and false dismissal could be controlled by adjusting the threshold value. The results showed that this approach could effectively identify skin color pixels and provide good coverage of all human races, and this technique is capable of segmenting the hands and face quite effectively. The algorithm allows the flexibility of incorporating additional techniques to enhance the results.