Adaptive Skin Detection Research Articles

An Adaptive Skin Detection Approach of Face Images with Unequal Luminance, Color Excursion, and Background Interference

Face detection and recognition are affected greatly by unequal luminance, color excursion and background interference. For improving skin detection rates of color face images in the presence of unequal luminance, color excursion and background interference, this paper proposes an approach for automatic skin detection. This approach globally corrects the color excursion using the X, Y, Z color components. Then it establishes a self-adaptive nonlinear amendment function using the a', b'and L' components, and locally corrects the R, G, B color components of row-column transformed sub-block images to balance the global luminance and color. Finally, it constructs an L'a'b'three-dimensional semi-supervised dual-probability skin model, based on which automatic skin detection can be realized. The experimental results demonstrated that this approach has great adaptability, a high detection rate and speed.

Adaptive skin detection using face location and facial structure estimation

Reliable and accurate facial skin extraction is the most critical and urgent issue for adaptive skin detection. Aiming at resolving this issue, the authors propose an adaptive skin detection method using face location and facial structure estimation. The face location algorithm is developed to improve the reliability of face detection and extract a face region with a high proportion of skin. Facial structure estimation is exploited to further reduce the impact of non-skin factors on dynamic skin colour modelling. The colour space distribution model of extracted facial skin is very close to that of real facial skin. Finally, the skin in an image is obtained by using a hybrid colour space strategy. Extensive experimental comparisons with some state-of-the-art methods have shown the superior performance of the proposed method.

Skin color model adaptation under varying lighting conditions

Skin region detection is crucial for face recognition, hand tracking, and motion detection. In the detection process, a skin color model is usually required to confine the distribution of skin colors. However, skin color models are sensitive to lighting conditions. Skin segmentation under varying lighting conditions produces poor results. This article presents a skin detection procedure for human–computer interaction sessions under varying lighting conditions. The proposed method requests a skin sample from the user to estimate the color temperature of the light source. Then, the color temperature is used to correct the skin sample. At the subsequent step, the mean of the corrected skin sample is utilized to adapt the skin color model. Finally, the adapted skin color model is employed to segment skin regions in the video stream. Tests using the proposed method and some adaptive skin detection algorithms have been conducted. Statistical data show that the proposed method is superior to color constancy methods and the Gaussian mixture model in skin region segmentation. The proposed method improves the true positive rate by more than 13% in segmenting skin regions of a database. Its true positive rate is 20% better if real-life images are used as test data.

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.

Chip-based adaptive skin color detection using trajectory constraints on hue

Abstract Background In a construction site, the safety of workers can be better secured if vehicle or robot can be properly maneuvered by using image-based gesture guidance. This kind of semi-automatic motion control is based on the features extracted in colors, outlines, textures, and motion intentions. Among these features, detecting worker’s skin color on face and hands could serve as an essential method for enabling robot to determine the region of interest (ROI). However, the performance of skin detection is usually unreliable due to interferences from reflections and shadows. Although many efficient skin color detection methods had been developed in past years, those are mostly based on complicated learning and statistical processes and are unsuitable for embedded systems. The exploration of a concise and efficient skin color detector, therefore, becomes a challenge for applications in mobile robots. Method In this paper, we propose a novel adaptive skin detector on face and hands as a fundamental capability of a gesture tracking system. This approach enhances the detection performance of traditional HSV color space but only requires a low computing power. For the design criteria of small size, low-power, low-cost, and minimum computing resource usages on mobile robots, the entire detecting system is built on single field-programmable-gate-array (FPGA) chip. Meanwhile, besides the contributions of adaptive algorithms and FPGA chip designs, the proposed skin detector also employs a touch screen to designate expected skin color of worker as the human-robot interaction (HRI) in real-time. Results The chip design of the FPGA is based on hardware circuits in register-transfer-level (RTL) for real-time image processing. A reasonable amount of hardware resource usages of FPGA have consumed 8% of logic elements (LEs) and 1.4% for embedded random access memory (RAM). Demonstrations with various pictures had indicated that sufficient ROI can be efficiently identified by using the proposed adaptive skin color detector. Conclusions According to our experimental results, the proposed adaptive skin detection can work well for non-ideal illumination. It has demonstrated the reliability and feasibility on supporting the embedded robotic control in the future.

Novel Haar features for real-time hand gesture recognition using SVM

Due to the effect of lighting and complex background, most visual hand gesture recognition systems work only under restricted environments. Here, we propose a robust system which consists of three modules: digital zoom, adaptive skin detection, and hand gesture recognition. The first module detects user face and zooms in so that the face and upper torus take the central part of the image. The second module utilizes the detected user facial color information to detect the other skin color regions like hands. The last module is the most important part for doing both static and dynamic hand gesture recognition. The region of interest next to the detected user face is for fist/waving hand gesture recognition. To classify the dynamic hand gestures under complex background, motion history image and four groups of novel Haar-like features are investigated to classify the dynamic up, down, left, and right hand gestures. A simple efficient algorithm using Support Vector Machine is developed. These defined hand gestures are intuitive and easy for user to control most home appliances. Five users doing 50 dynamic hand gestures at near, medium, and far distances, respectively, were tested under complex environments. Experimental results showed that the accuracy was 95.37 % on average and the processing speed was 3.93 ms per frame. An application integrated with the developed hand gesture recognition was also given to demonstrate the feasibility of proposed system.

A Comparison of Dynamic Naive Bayesian Classifiers and Hidden

In this paper we present a study to assess the performance of dynamic naive Bayesian classifiers (DNBCs) versusstandard hidden Markov models (HMMs) for gesture recognition. DNBCs incorporate explicit conditional independence among gesture features given states into HMMs. We show that this factorization offers competitive classification rates and error dispersion, it requires fewer parameters and it improves training time considerably in the presence of several attributes. We propose a set of qualitative and natural set of posture and motion attributes to describe gestures. We show that these posture-motion features increase recognition rates significantly in comparison to motion features. Additionally, an adaptive skin detection approach to cope with multiple users and different lighting conditions is proposed. We performed one of the most extensive experimentation presented in the literature to date that considers gestures of a single user, multiple people and with variations on distance and rotation using a gesture database with 9441 examples of 9 different classes performed by 15 people. Results show the effectiveness of the overall approach and the reliability of DNBCs in gesture ecognition.