Rehanullah Khan

Color based skin classification

Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. In this paper, we investigate and evaluate (1) the effect of color space transformation on skin detection performance and finding the appropriate color space for skin detection, (2) the role of the illuminance component of a color space, (3) the appropriate pixel based skin color modeling technique and finally, (4) the effect of color constancy algorithms on color based skin classification. The comprehensive color space and skin color modeling evaluation will help in the selection of the best combinations for skin detection. Nine skin modeling approaches (AdaBoost, Bayesian network, J48, Multilayer Perceptron, Naive Bayesian, Random Forest, RBF network, SVM and the histogram approach of Jones and Rehg (2002)) in six color spaces (IHLS, HSI, RGB, normalized RGB, YCbCr and CIELAB) with the presence or absence of the illuminance component are compared and evaluated. Moreover, the impact of five color constancy algorithms on skin detection is reported. Results on a database of 8991 images with manually annotated pixel-level ground truth show that (1) the cylindrical color spaces outperform other color spaces, (2) the absence of the illuminance component decreases performance, (3) the selection of an appropriate skin color modeling approach is important and that the tree based classifiers (Random forest, J48) are well suited to pixel based skin detection. As a best combination, the Random Forest combined with the cylindrical color spaces, while keeping the illuminance component outperforms other combinations, and (4) the usage of color constancy algorithms can improve skin detection performance.

Skin detection: A random forest approach

Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking objectionable content. For robust skin segmentation and detection, we investigate color classification based on random forest. A random forest is a statistical framework with a very high generalization accuracy and quick training times. The random forest approach is used with the IHLS color space for raw pixel based skin detection. We evaluate random forest based skin detection and compare it to Bayesian network, Multilayer Perceptron, SVM, AdaBoost, Naive Bayes and RBF network. Results on a database of 8991 images with manually annotated pixel-level ground truth show that with the IHLS color space, the random forest approach outperforms other approaches. We also show the effect of increasing the number of trees grown for random forest. With fewer trees we get faster training times and with 10 trees we get the highest F-score.

Skin Paths for Contextual Flagging Adult Videos

User generated video content has become increasingly popular, with a large number of internet video sharing portals appearing. Many portals wish to rapidly find and remove objectionable material from the uploaded videos. This paper considers the flagging of uploaded videos as potentially objectionable due to sexual content of an adult nature. Such videos are often characterized by the presence of a large amount of skin, although other scenes, such as close-ups of faces, also satisfy this criterion. The main contribution of this paper is to introduce to this task two uses of contextual information in the form of detected faces. The first is to use a combination of different face detectors to adjust the parameters of the skin detection model. The second is through the summarization of a video in the form of a path in a skin-face plot. This plot allows potentially objectionable segments of videos to be found, while ignoring segments containing close-ups of faces. The proposed approach runs in real-time. Experiments are done on per pixel annotated and challenging on-line videos from an on-line service provider to prove our approach. Large scale experiments are carried out on 200 popular public video clips from web platforms. These are chosen from the community (top-rated) and cover a large variety of different skin-colors, illuminations, image quality and difficulty levels. We find a compact and reliable representation for videos to flag suspicious content efficiently.

Generation of Multiple Fano Resonances in Plasmonic Split Nanoring Dimer

We present a computational study of the plasmonic response of a split nanoring dimer resonator which supports multiple plasmonic Fano-like resonances that arises by the coupling and interference of the dimer plasmon modes. For the generation of Fano resonances with large modulation depths, numerous configurations of the dimer resonator are analyzed which are observed to be highly dependent on the polarization of incident light. Moreover, the influence of dimension of the split nanoring structure on the spectral positions and intensities of the higher order Fano resonances are also investigated, and it is found that the asymmetric Fano line shapes can be flexibly tuned in the spectrum by varying various geometrical parameters. Such Fano resonators are also discovered to offer high values of figure of merit and contrast ratio due to which they are suitable for high-performance biological sensors.

An adaptive multiple model approach for fast content-based skin detection in on-line videos

We propose a straightforward skin detection method for online videos. To overcome varying illumination circumstances and a variety of skin colors, we introduce a multiple model approach which can be carried out independently per model. The color models are initiated by skin detection based on face detection and adapted in real time. Our approach outperforms static approaches both in precision and runtime. If we detect a face in a scene, the number of false positives can be diminished significantly. Evaluation is carried out on publicly available on-line videos showing that adaptive multiple model outperforms static methods in classification precision and suppression of false positives.

Systematic skin segmentation: merging spatial and non-spatial data

Skin detection is used in applications ranging from face detection, tracking of body parts, hand gesture analysis, to retrieval and blocking objectionable content. We present a systematic approach for robust skin segmentation using graph cuts. The skin segmentation process starts by exploiting the local skin information of detected faces. The detected faces are used as foreground seeds for calculating the foreground weights of the graph. If local skin information is not available, we opt for the universal seed. To increase the robustness, the decision tree based classifier is used to augment the universal seed weights when no local information is available in the image. With this setup, we achieve robust skin segmentation, outperforming off-line trained classifiers. The setup also provides a generic skin detection system, using positive training data only. With face detection, we take advantage of the contextual information present in the scene. With the weight augmentation, we provide a setup for merging spatial and non-spatial data. Experiments on two datasets with annotated pixel-level ground truth show that the systematic skin segmentation approach outperforms other approaches and provides robust skin detection.

Twin Dipole Fano Resonances in Symmetric Three-Layered Plasmonic Nanocylinder

A unique metal-dielectric structure composed of symmetric multilayered nanocylinder is demonstrated to support unconventional superradiant and subradiant plasmon modes. Here, the twin distinctive dipole-dipole Fano resonances are observed in the structure within the visible spectrum by carefully selecting the geometrical parameters. The spectral features of these Fano resonances are controlled by changing the incident field polarization and parameters of the nanoparticle. Eventually, an RLC circuit model is proposed to reproduce the optical response of the nanostructure.

Multiple color space channel fusion for skin detection

Skin detection is used in applications ranging from face detection, tracking body parts and hand gesture analysis, to retrieval and blocking of objectionable content. We investigate color based skin detection. We linearly merge different color space channels representing it as a fusion process. The aim of fusing different color space channels is to achieve invariance against varying imaging and illumination conditions. The non-perfect correlation between the color spaces is exploited by learning weights based on an optimization for a particular color space channel using the mathematical financial model of Markowitz. The weight learning process develops a color weighted model using positive training data only. Experiments on a database of 8991 images with annotated pixel-level ground truth show that the fusion of color space channels approach is well suited to stable and robust skin detection. In terms of precision and recall, the fusion approach provides a competitive performance to other state-of-the-art approaches which require negative and positive training data with the exception of the decision tree based classifier (J48). As a real-time application, we show that the weight based color channel fusion approach can be used for learning of weights for skin detection based on detected faces in image sequences.

FeEval A Dataset for Evaluation of Spatio-temporal Local Features

The most successful approaches to video understanding and video matching use local spatio-temporal features as a sparse representation for video content. Until now, no principled evaluation of these features has been done. We present FeEval, a dataset for the evaluation of such features. For the first time, this dataset allows for a systematic measurement of the stability and the invariance of local features in videos. FeEval consists of 30 original videos from a great variety of different sources, including HDTV shows, 1080p HD movies and surveillance cameras. The videos are iteratively varied by increasing blur, noise, increasing or decreasing light, median filter, compression quality, scale and rotation leading to a total of 1710 video clips. Homography matrices are provided for geometric transformations. The surveillance videos are taken from 4 different angles in a calibrated environment. Similar to prior work on 2D images, this leads to a repeatability and matching measurement in videos for spatio-temporal features estimating the overlap of features under increasing changes in the data.

Comparison of reconstruction and example-based Super-Resolution

By comparing two classes of Super-Resolution (SR) namely Example-Based Super-Resolution (EBSR) and Reconstruction-Based Super-Resolution (RBSR), we investigate two points: Firstly, which SR technique EBSR or RBSR will produce SR image that preserves Structure Similarity (SSIM) to the original image? Secondly, which SR technique will produce SR image that is more appealing to human eyes? For resultant SR image, EBSR predicts the relation between high and low frequencies in an image, whereas RBSR algorithms rely on a sequence of frames. From the experimental results on test images, we find that compared to RBSR, EBSR preserves the structure of the original image. Knowing this capability is important for detection and recognition systems. In terms of visual appearance, RBSR is preferred except when there are large motions in consecutive frames. Moreover, the aliasing artifacts cannot be removed by EBSR algorithms.