Skin Pixels Research Articles

Unsupervised skin tissue segmentation for remote photoplethysmography

Segmentation is a critical step for many algorithms, especially for remote photoplethysmography (rPPG) applications as only the skin surface provides information. Moreover, it has been shown that the rPPG signal is not distributed homogeneously across the skin. Most of the time, algorithms get input information from face detection provided by a supervised learning of physical appearance and skin pixel selection. However, both methods show several limitations. In this paper, we propose a simple approach to implicitly select skin tissues based on their distinct pulsatility feature. The input video frames are decomposed into several temporal superpixels from which the pulse signals are extracted. A pulsatility measure from each temporal superpixel is then used to merge the pulse traces and estimate the photoplethysmogram signal. Since the most pulsatile signals provide high quality information, areas where the information is predominant are favored. We evaluated our contribution using a new publicly available dataset dedicated to rPPG algorithms comparison. The results of our experiments show that our method outperforms state of the art algorithms, without any critical face or skin detection.

Hair segmentation using adaptive threshold from edge and branch length measures

BackgroundNon-invasive imaging techniques allow the monitoring of skin structure and diagnosis of skin diseases in clinical applications. However, hair in skin images hampers the imaging and classification of the skin structure of interest. Although many hair segmentation methods have been proposed for digital hair removal, a major challenge in hair segmentation remains in detecting hairs that are thin, overlapping, of similar contrast or color to underlying skin, or overlaid on highly-textured skin structure. MethodsTo solve the problem, we present an automatic hair segmentation method that uses edge density (ED) and mean branch length (MBL) to measure hair. First, hair is detected by the integration of top-hat transform and modified second-order Gaussian filter. Second, we employ a robust adaptive threshold of ED and MBL to generate a hair mask. Third, the hair mask is refined by k-NN classification of hair and skin pixels. ResultsThe proposed algorithm was tested using two datasets of healthy skin images and lesion images respectively. These datasets were taken from different imaging platforms in various illumination levels and varying skin colors. We compared the hair detection and segmentation results from our algorithm and six other hair segmentation methods of state of the art. Our method exhibits high value of sensitivity: 75% and specificity: 95%, which indicates significantly higher accuracy and better balance between true positive and false positive detection than the other methods.

A Skin Segmentation Algorithm Based on Stacked Autoencoders

A good skin detector that is capable of capturing skin tones under different conditions is important for human–machine interaction applications. In a general situation, skin detectors, such as skin probability maps or Gaussian mixture models, achieve acceptable skin segmentation results. However, the false positive rate increases significantly when the skin tones are in shadow or when skin-like background objects are under similar illumination. In this paper, we propose a novel skin feature learning algorithm based on stacked autoencoders, which are deep neural networks. To overcome the problems encountered in skin segmentation that are caused by different ethnicities and varying illumination conditions, the stacked autoencoders are utilized to learn more discriminative representations of the skin area in both the RGB color space and the HSV color space. Unlike traditional machine learning methods, instead of predicting each pixel individually, our algorithm utilizes blocks to learn the representations and detect the skin areas. The algorithm exploits the learning ability of deep neural networks to learn high-level representations of skin tones. Experiments on test images show that the proposed algorithm achieves acceptable results on several publicly available data sets. To reduce the difficulty of detecting skin pixels in these data sets, the ground truths of these data sets are commonly focused on foreground skin area detection. Our skin detector is also able to detect background areas, as shown in our experiments.

A Multi-Scale Approach to Skin Pixel Detection

A Multi-Scale Approach to Skin Pixel Detection

Human skin detection through correlation rules between the YCb and YCr subspaces based on dynamic color clustering

This paper presents a novel rule-based skin detection method that works in the YCbCr color space. The method is based on correlation rules that evaluate the combinations of chrominance values to identify the skin pixels in the YCb and YCr subspaces. The correlation rules depend on the shape and size of dynamically generated skin color clusters, which are computed on a statistical basis in the YCb and YCr subspaces for each single image, and represent the areas that include most of the candidate skin pixels. Comparisons with six well-known rule-based methods in literature carried out on four publicly available databases show that the proposed method outperforms the others in terms of quantitative performance evaluation parameters. Moreover, the qualitative analysis shows that the method achieves satisfactory results also in critical scenarios, including severe variations in illumination conditions.

A simple weighted thresholding method for the segmentation of pigmented skin lesions in macroscopic images

This work proposes a simple and yet effective thresholding method to segment pigmented skin lesions in macroscopic photographs automatically. Segmentation is one of the first steps in computer-aided diagnosis of skin cancers. Therefore, an accurate segmentation may play an important clinical role. We develop an algorithm that searches for a thin rectangular-shaped region near the image borders that is likely to contain mostly skin pixels. Segmentation is obtained by adapting Otsu's thresholding method by combining independent threshold estimates computed from histograms of different parts of a new intensity image designed to discriminate lesions from background skin. The proposed approach exploits the fact that the object of interest is approximately centered in the input photograph. A cross-diagonal sampling scheme helps to balance the size of the classes when the area of the lesion and the area of the surrounding skin are very different. A post-processing stage that includes morphological filtering and a weighted scheme to select the most salient object follows. The experimental results suggest that the method potentially can be used successfully to segment atypical nevi and melanomas in lesions with a highly heterogeneous background skin. The proposed algorithm is of interest for use in clinical settings as part of a CAD system.

Development of an Efficient Hand Gesture Recognition system for human computer interaction

Human computer interaction technique has become a bottleneck in the effective utilization of the available information. The development of user interfaces influences the change in the human computer interaction (HCI). Dynamic hand posture recognition is one of the difficult tasks due to its complex background. The proposed method is implemented for hand postures taken in the natural environment. Challenges such as change of illumination and similar background are taken into consideration. Working system is based on two steps, namely hand detection and hand gesture recognition. In the hand detection process, normalized colour space skin locus is used to threshold the skin pixels from its varying background. Morphological filtering and canny edge detection is used efficaciously for removing object noise and obtain counter edges of hand gestures. Normalized cross correlation is used for pixel-wise comparison between the input image and the depository images and the best matching is considered as region of interest.

A Hybrid Skin Detection Model from Multiple Color Spaces Based on a Dual-Threshold Bayesian Algorithm

As a preliminary step of many applications, skin detection serves as an irreplaceable role in image processing applications, such as face recognition, gesture recognition, web image filtering, and image retrieval systems. Combining information from multiple color spaces improves the recognition rate and reduces the error rate because the same color is represented differently in other color spaces. Consequently, a hybrid skin detection model from multiple color spaces based on a dual-threshold Bayesian algorithm (DTBA) has been proposed. In each color space, the pixels of images are divided into three categories, namely, skin, nonskin, and undetermined, when using the DTBA. Then, nearly all skin pixels are obtained by using a specific rule that combines the recognition results from multiple color spaces. Furthermore, skin texture filtering and morphological filtering are applied to the results by effectively reducing false identified pixels. In addition, the proposed skin model can overcome interference from a complex background. The method has been validated in a series of experiments using the Compaq and the high-resolution image datasets (HRIDs). The findings have demonstrated the proposed approach produced an improvement, the true positive rate (TPR) improves more than 6% and the false positive rate (FPR) reduces more than 11%, compared with the Bayesian classifier. We confirm that the method is competitive. Meanwhile, this model is robust against skin distribution, scaling, partial occlusions, and illumination variations.

Color-based skin segmentation in videos using a multi-step spatial method

Recently, skin detection has been employed in multifarious applications of computer vision including face detection, gesture recognition, etc. This is mainly due to the appealing characteristics of skin color and its potency to segment objects. However, there are certain challenges involved in utilizing human complexion as a feature to detect faces, and they have led to the inefficiency of many methods. In order to counteract these factors, in this paper, a skin segmentation method which exploits a multi step diffusion algorithm to detect skin regions is presented. The method starts with conservative extraction of skin seeds in each frame which is accomplished by using fusion of ternary-based human motion detection, modified Bayesian classifier, and a feedback mechanism. Subsequently, these candidate skin pixels are utilized in a 2-stage diffusion scheme to detect other skin pixels. Both quantitative and qualitative results demonstrate the effectiveness of the proposed system in comparison with other works.

A Comprehensive Survey on Human Skin Detection

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.

Indian sign language recognition using SVM

Needs and new technologies always inspire people to make new ways to interact with machines. This interaction can be for a specific purpose or a framework which can be applied to many applications. Sign language recognition is a very important area where an easiness in interaction with human or machine will help a lot of people. At this time, India has 2.8M people who can't speak or can't hear properly. This paper targets Indian sign recognition area based on dynamic hand gesture recognition techniques in real-time scenario. The captured video was converted to HSV color space for pre-processing and then segmentation was done based on skin pixels. Also Depth information was used in parallel to get more accurate results. Hu-Moments and motion trajectory were extracted from the image frames and the classification of gestures was done by Support Vector Machine. The system was tested with webcam as well as with MS Kinect. This type of system would be helpful in teaching and communication of hearing impaired persons.

A New Data Hiding Approach in Images for Secret Data Communication with Steganography

In this paper, a new secret data hiding and communication is proposed for natural images.in this proposed methodology. The aim of steganography is to hide an information message within harmless cover medium in such way that it's not possible even to observe that secrete message. It doesn't replace cryptography however rather boosts the security using its obscurity options. In the projected its obscurity features. In the proposed algorithm we have used second order differential equation to hide the data which improve the security level of hidden data. In encryption, information is transformed in such a way that it cannot be detect by hacker. But during encryption, message is changed so it become distorted and intruder may suspect about the presence of important information. For this skin tone detection is performed using HSV (Hue, Saturation and Value) color space. Additionally secret data embedding is performed victimization frequency domain approach – DWT (Discrete wavelet Transform), DWT outperforms than DCT (Discrete cosine Transform). Secret information is hidden in one of the high frequency sub-band of DWT by tracing skin pixels therein sub-band. Totally different steps of data hiding are applied by cropping a picture interactively. The output of our technique provides higher results because with the assistance of cropping an increased security than hiding data while not cropping i.e. in whole image, thus cropped region works as a key at decryption aspect. thus with this object destined steganography we have a tendency to track skin tone objects in image with the higher security and satisfactory PSNR (Peak-Signal-to-Noise Ratio).Modern steganography’s goal is to stay its more presence undetectable.

Robust video steganography algorithm using adaptive skin-tone detection

Human skin regions have recently drawn attention in the literature of data hiding due to its promising robustness characteristics. In this paper, we propose a blind adaptive data hiding algorithm for video files where human skin regions are regarded as the Regions Of Interest (ROI) hosting the embedding process. A skin map is created for each frame using an adaptive skin detection algorithm with reduced number of false positives. Then the skin map is converted to a skin-block-map in order to eliminate the error-prone skin pixels that can result in inefficient retrieval of the hidden data. Moreover, the embedding process is done using a wavelet quantization technique over the red and blue channels of the host frames for increased robustness. Experimental results showed the high imperceptibility of the proposed method as well as its robustness against MPEG-4 compression.

Motion-based skin region of interest detection with a real-time connected component labeling algorithm

This paper presents a motion-based skin Region of Interest (ROI) detection method using a real-time connected component labeling algorithm to provide real-time and adaptive skin ROI detection in video images. Skin pixel segmentation in video images is a pre-processing step for face and hand gesture recognition, and motion is a cue for detecting foreground objects. We define skin ROIs as pixels of skin-like color where motion takes place. In the skin color estimation phase, RGB color histograms are utilized to define the skin color distribution and specify the threshold to segment skin-like regions. A parallel computed connected component labeling algorithm is also proposed to group the segmentation results into several clusters. If a cluster covers any motion pixel, this cluster is identified as a skin ROI. The method's results for real images are shown, and its speed is evaluated for various parameters. This technology is compatible with monitoring systems, scene understanding, and natural user interfaces.

Robust skin segmentation using color space switching

Skin detection is very popular and has vast applications among researchers in computer vision and human computer interaction. The skin-color changes beyond comparable limits with considerable change in the nature of the light source. Different properties are taken into account when the colors are represented in different color spaces. However, a unique color space has not been found yet to adjust the needs of all illumination changes that can occur to practically similar objects. Therefore a dynamic skin color model must be constructed for robust skin pixel detection, which can cope with natural changes in illumination. This paper purposes that skin detection in a digital color image can be significantly improved by employing automated color space switching. A system with three robust algorithms has been built based on different color spaces towards automatic skin classification in a 2D image. These algorithms are based on the statistical mean of value of the skin pixels in the image. We also take Bayesian approaches to discriminate between skin-alike and non-skin pixels to avoid noise. This work is tested on a set of images which was captured in varying light conditions from highly illuminated to almost dark.

Patch-wise skin segmentation of human body parts via deep neural networks

In human-centric technologies, skin segmentation of body parts is a prerequisite for high-level processing. The traditional method of skin detection is pixel-wise detection coupled with morphological operations. Pixel-wise methods usually generate a number of false samples and outlier skin pixels, which can make it difficult for morphological operations to provide satisfactory results in complex scenarios. Furthermore, in many cases only a coarse region is required (e.g., the bounding-box of the face) rather than detailed pixel-wise labeling. A patch-wise skin segmentation method is proposed based on deep neural networks. Our method treats image patches as processing units instead of pixels, which directly exploits the spatial information of pixels in the detection stage rather than using morphological operations on isolated pixels after detection. An image patch dataset is built and deep skin models (DSMs) are trained based on the new dataset. Trained DSMs are then integrated into a sliding window framework to segment skin regions of the human body parts. Experiments on standard benchmarks demonstrate that DSMs provide more explicit skin region of interest candidates than pixel-wise methods in complex scenarios, and achieve competitive performance on pixel-wise skin detection.

PRIVATE CONFIDENTIAL DATA HIDING BY USING WAVELET APPROACH

This paper introduces a secret data hiding method which is based on the biometric features. In this rapid technically developing world sharing multimedia on an internet has become a trend, digital media like audio, video and images are being shared through social networks. Also there is a possibility of threatening these digital media whichever sent through internet so to address this issue one need to take security measure to get strong communication system which should be able to withstand against hackers. Steganography by using discrete wavelet transform (DWT). Here in this context skin region particularly face area is opted out. Because, compared to all other skin area like hand, neck etc., face region will be brighter. Skin classifier Adaboost is used. In this paper graphic manipulation process called cropping is introduced, also cropped value helps in extraction process. Here, data is embedded by tracing skin pixel in frequency band and strictly speaking data is embedded in G and B plane. Simulation is carried out by using MATLAB software.

Hair enhancement in dermoscopic images using dual-channel quaternion tubularness filters and MRF-based multilabel optimization.

Hair occlusion is one of the main challenges facing automatic lesion segmentation and feature extraction for skin cancer applications. We propose a novel method for simultaneously enhancing both light and dark hairs with variable widths, from dermoscopic images, without the prior knowledge of the hair color. We measure hair tubularness using a quaternion color curvature filter. We extract optimal hair features (tubularness, scale, and orientation) using Markov random field theory and multilabel optimization. We also develop a novel dual-channel matched filter to enhance hair pixels in the dermoscopic images while suppressing irrelevant skin pixels. We evaluate the hair enhancement capabilities of our method on hair-occluded images generated via our new hair simulation algorithm. Since hair enhancement is an intermediate step in a computer-aided diagnosis system for analyzing dermoscopic images, we validate our method and compare it to other methods by studying its effect on: 1) hair segmentation accuracy; 2) image inpainting quality; and 3) image classification accuracy. The validation results on 40 real clinical dermoscopic images and 94 synthetic data demonstrate that our approach outperforms competing hair enhancement methods.

FUSION OF COLOR AND MODIFIED WEBER’S LAW DESCRIPTOR BASED HUMAN SKIN DETECTION

Skin detection in images or videos plays a vital ro le in a wide range of image processing applications like face detection, face tracking, gesture analysis, hu man-computer interaction etc. Due to its high proce ssing speed and invariant against rotation, it has receiv ed significant interest in pattern recognition and computer vision. The robustness of skin detection using colo r information depends on real world conditions such as background, noise, change of intensity and lighteni ng effects. This situation can be improved by using texture as a descriptor to extract skin pixels in i mages. This study proposes color based skin detecti on algorithm (fusion of Cheddad’s approach with Cr of YC bCr color space) with a texture based skin location algorithm called Modified Weber’s Law Descriptions (MWLD) to evaluate region features. MWLD is based on the fact that the Human Visual System (HVS) is more sensitive in lumens contrast than absolut e luminance values. In MWLD, the differential excitat ion and gradient orientation of the current pixel a re considered to extract the texture features. For dif ferential excitation, Just Noticeable Distortion (J ND) is also used. Due to the absence of red component in C heddad’s new color space for skin detection, the detection rate is not good for real time applicatio ns. To improve this situation, the Cr component of YC bCr color space is included to obtain the color feature s. According to experimental results, the proposed method exhibits satisfactory performance in terms of True Positive Rate (TPR), False Positive Rate (FPR) and Accuracy with wide variations in size, color and or ientation. Different window sizes for differential excitation such as 3◊3, 5◊5 and 7◊7 are also taken to check the performance.

A NEW SYMMETRY APPROACH FOR FRONTAL-VIEW FACE DETECTION

An efficient algorithm for detecting frontal-view faces in color images is proposed. The proposed algorithm has a special task; it detects faces in the presence of skin-tone regions (human body, clothes, and background) Firstly, a pixel based color classifier is applied to segment the skin pixels from background. Next, a hybrid cluster algorithm is applied to partition the skin region. We introduce a new symmetry approach, which is the main distinguishing feature of the proposed algorithm. It measures a symmetrical value, searches for the real center of the region, and then removes the extra unsymmetrical skin pixels. The cost functions are adopted to locate the real two eyes of the candidate face region. A template matching process is preformed between an aligning frontal face model and the candidate face region as a verification step. Experimental results reveal that our algorithm can perform the detection of faces successfully under wide variations.