Human model for people detection in dynamic scenes

Objective. Using New Zealand as a case study, to determine whether ethnicity is appropriate for communicating sun exposure health promotion messages. Design. This study reviews recent literature on minimising skin cancer risk and achieving sufficient serum vitamin D levels. It draws on a variety of scientific literature, reports and media statements to determine appropriate sun exposure messages for minimising skin cancer risk and achieving sufficient vitamin D status among the New Zealand population, which is diverse with regards to both ethnicity and skin colour. Result(s). Due to a unique combination of factors, New Zealand and Australia lead the world in melanoma incidence. Devising ways of minimising skin cancer risk and achieving optimal vitamin D blood levels among the New Zealand population provide major challenges for researchers and health promoters. These challenges include the many unknowns and uncertainties about vitamin D, such as determining what constitutes an optimal level as well as its association with specific diseases. There is strong evidence that skin cancer, including melanoma, is caused by excess harmful sun exposure with skin colour having long been established as a risk factor. More recently, there has been significant focus in New Zealand on the potential beneficial aspects of sun exposure, mainly in assisting vitamin D synthesis, especially for Māori and Pacific people. But research also shows that Māori and Pacific people are increasingly at risk of developing melanoma. In New Zealand, where there is a high rate of ethnic intermarriage and ethnicity is culturally constructed, there is likely to have been a weakening of the relationship between ethnicity and skin colour. Skin colour information is required to understand both the risks and benefits of sun exposure. In the immediate future, ethnicity appears likely to remain an important reference point for assessing the risks and benefits of sun exposure in New Zealand. However, we contend that while ethnic-based channels may be useful for communicating appropriate sun exposure messages, there are dangers in such advice based on membership of particular ethnic group(s). Rather skin colour, along with other key variables, such as season and time of day, should be the core considerations for assessing and discussing risk. In the longer term, direct measures of skin type are needed when assessing the risks and benefits of sun exposure, including the potential protective effects against various illnesses. Conclusion. While ethnic-based dissemination channels may be useful for communicating about the risks and benefits of sun exposure in New Zealand, discussion of risk factors should focus on skin colour.

Improved Cherenkov Imaging across a Wide Range of Skin Pigmentation Levels for the Inclusion of Diverse Patient Populations

Human skin colour information is important for the cosmetic industries and hospitals to develop a skin product and suggest an appropriate treatment. Human skin has multi-layered structures with non-flat surface and the colour of the human skin is unevenly distributed over the body. It is difficult to get skin colour information both exhaustively and precisely. Different ethnicities exhibit significantly different skin colour. To supply the data to the CIETC 1-92 Skin Colour Database and to achieve successful colour reproduction of skin colours on multimedia, two most widely used instruments, tele-spectroradiometers (TSRs) and spectrophotometers (SPs), were employed to collect large numbers of human skin colour, including 188 subjects from four ethnic groups (Oriental Caucasian, South Asian and African). Five or ten locations from each subject were measured. At each location, three repeated measurements performed by using both instruments and their mean values were used as the measurement results. The measurement results were reported using CIELAB colour system, in terms of lightness, chroma and hue. The colour distribution between different locations of different ethnic groups was studied by plotting the data points in a * b * and \( L^{*} C_{ab}^{*} \) planes. Systematic trends were found between different ethnicities and instruments. The result shows a significant trend of the colour shifting between different ethnicities and instruments.

Characterization and functional analysis of pax3 in body color transition of polychromatic Midas cichlids (Amphilophus citrinellus).

In this paper, we propose the objectionable image detection system based on ROI. The proposed system excels in that ROI detection method is specialized in objectionable image detection. In addition, we propose the novel feature consisting of weighted SCD based on ROI and skin color structure descriptor for classifying objectionable image. Using the ROI detection method, we can reduce the noisy information in image and extract more accurate features for classifying objectionable image. We can also increase the performance of classification system using the skin color information which is the most representative characteristic of objectionable image. An objectionable image is classified as follows. First, the proposed system extracts the ROI from an input image, and then generates the feature using the color information of ROI image and the skin color structure information. The generated feature is used as an input to the SVMs which determines whether an image is objectionable or not. Experimental results show that the proposed ROI detection method can detect ROI exactly. Additionally, the proposed system can achieve the better performance than existing system.

646 Analysis of statistics for facial image color between ages

This paper proposes a novel technique for detecting faces in color images using AdaBoost algorithm combined with skin color segmentation. First,skin color model in the YCbCr chrominance space is built to segment the non-skin-color pixels from the image. Then, mathematical morphological operators are used to remove noisy regions and fill holes in the skin-color region, so we can extract candidate human face regions. Finally, these face candidates are scanned by cascade classifier based on AdaBoost for more accurate face detection. This system detects human face in different scales, various poses, different expressions, lighting conditions, and orientation. Experimental results show the proposed system obtains competitive results and improves detection performance substantially.

Existing facial image shadow removal methods predominantly rely on pre‐extracted facial features. However, these methods often fail to capitalize on the full potential of these features, resorting to simplified utilization. Furthermore, they tend to overlook the importance of low‐frequency information during the extraction of prior features, which can be easily compromised by noises. In our work, we propose a frequency‐aware shadow removal network (FSRNet) for facial image shadow removal, which utilizes the skin color and texture information in the face to help recover illumination in shadow regions. Our FSRNet uses a frequency‐domain image decomposition network to extract the low‐frequency skin color map and high‐frequency texture map from the face images, and applies a color‐texture guided shadow removal network to produce final shadow removal result. Concretely, the designed fourier sparse attention block (FSABlock) can transform images from the spatial domain to the frequency domain and help the network focus on the key information. We also introduce a skin color fusion module (CFModule) and a texture fusion module (TFModule) to enhance the understanding and utilization of color and texture features, promoting high‐quality result without color distortion and detail blurring. Extensive experiments demonstrate the superiority of the proposed method. The code is available at https://github.com/laoxie521/FSRNet.

Moving objects' detection in dynamic scenes is a very important task in video processing. In the applications of image processing (for example, video-surveillance), more attention is paid to whether there is an interested object in the scene rather than where the object is located. As a matter of fact, similar to static backgrounds, the statistical histograms of the most dynamic backgrounds have favorable stability, and these histograms would change clearly only when big and contrasting objects enter or move out of the scenes. This is a very important and interesting property for dynamic background. We propose a fast and simple algorithm, combining histograms in multiple color spaces and the superposition principle of statistical histogram, called Multiple Color Space Histogram Models (MCSHM). MCSHM first calculates statistical histograms of many color components in multiple color space and then use the changes of statistical histograms to determine whether there is an object rather than the changes in pixels or pixel-level regions. Thus, the computational complexity of MCSHM is kept at a very low level. The basic steps are as follows: firstly, convert each frame from RGB space to other color spaces and calculate the histograms of selected color components, then we can obtain the background histogram model; secondly, detect the objects using statistical histogram superposition principle; finally, update MCSHM by the result of detection. The experimental results demonstrate that our method can quickly and accurately detect moving objects in dynamic scenes.

In this paper, we propose a multi-camera video stitching approach, which conducts borderline adjusting based on foreground information. In real time applications of video stitching, one problem is to deal with dynamic scenes, where foreground objects often cause broken objects like artifacts in panoramic video. To address this problem, we propose a foreground based borderline adjusting method to achieve smooth video stitching. In this method, foreground objects are extracted from different viewpoints, and the stitching borderlines are adjusted according to the foreground content in dynamic scenes. Guided by the adjusted borderlines, foreground objects are smoothly synthesized into panoramic video. Experiment results show that this approach obtains more than 81% correct rate for dynamic scenes, compared with 25%~50% correct rate on the condition of not utilizing foreground information, and achieves processing speed of 10~13 frames per second.

Accuracy of skin segmentation algorithms is highly sensitive to changes in lighting conditions. When the lighting condition in a scene is different from that in the training examples, miss-classification rate of the skin segmentation algorithms is high. Using color constancy approach we aim to compensate for skin color variations to achieve accurate skin color segmentation. Skin color constancy is realized in an unsupervised manner by using the color changes observed on a face for different illuminations to drive the model. By training on few faces of different ethnicities, our model is able to generalize the color mapping for any unseen ethnicity. The color changes observed are used to learn the color mapping from one lighting condition to the other. These mappings are represented in a low dimensional subspace to obtain basis vector fields. Using these basis vector fields we can model the nonlinear color changes to transform skin colors in arbitrary lighting conditions to a reference lighting condition. We show the proof of concept of unsupervised skin color constancy on faces from the PIE database. Skin segmentation is performed on the color compensated faces using a Skin Distribution Map (SDM), which is trained on skin colors in reference lighting condition.

Melanoma is a type of skin cancer that is particularly dangerous to people with dark skin. This is due to the disease's late diagnosis and detection in people with dark skin. When melanoma is detected, the prognosis is often poor. Advancement in Artificial Intelligence (AI) technology and image classification has brought about tremendous progress and applications in medicine and diagnosis of skin cancer. Albeit, these techniques continue to produce unsatisfactory results when applied to people with dark skin. This work considered the trend in cancer detection using AI techniques. Dark skin melanoma clinical images were acquired and pre-processed to remove illumination and noise to aid the other stages such as segmentation and data augmentation. The acquired images were combined with a curated and augmented version of the Human Against Machines 10000 image (HAM10000) dataset and split into two classes: melanoma and non-melanoma. A pre-trained DenseNet121 was used as a base model for training and in addition, a transfer learning process was performed to exclude the top layer and fine-tune all the layers in the final Dense Block of the model pre-trained on ImageNet. The model achieved an accuracy of 99% for melanoma detection in white skin color and 98% for dark skin. The results show that the proposed model is effective in detecting melanoma in skin.

Abstract. The automatic analysis of 3D point clouds has become a crucial task in photogrammetry, remote sensing and computer vision. Whereas modern range cameras simultaneously provide both range and intensity images with high frame rates, other devices can be used to obtain further information which could be quite valuable for tasks such as object detection or scene interpretation. In particular thermal information offers many advantages, since people can easily be detected as heat sources in typical indoor or outdoor environments and, furthermore, a variety of concealed objects such as heating pipes as well as structural properties such as defects in isolation may be observed. In this paper, we focus on thermal 3D mapping which allows to observe the evolution of a dynamic 3D scene over time. We present a fully automatic methodology consisting of four successive steps: (i) a radiometric correction, (ii) a geometric calibration, (iii) a robust approach for detecting reliable feature correspondences and (iv) a co-registration of 3D point cloud data and thermal information via a RANSAC-based EPnP scheme. For an indoor scene, we demonstrate that our methodology outperforms other recent approaches in terms of both accuracy and applicability. We additionally show that efficient straightforward techniques allow a categorization according to background, people, passive scene manipulation and active scene manipulation.

We propose a computer vision system that can automatically detect people in dynamic real-world scenes, enabling people with vision impairments to have more awareness of, and interactions with, other people in their surroundings. As an initial step, we investigate the feasibility of four camera systems that vary in their placement, field-of-view, and image distortion for: (i) capturing people generally; and (ii) detecting people via a specific person-pose estimator. Based on our findings, we discuss future opportunities and challenges for detecting people in dynamic scenes, and for communicating that information to visually impaired users.

Negative pressure of cupping induces skin deformation such as ecchymosis and purpura in a circular shape. Thus, there is a desire to treat skin before depigmentation and scarring occurs. Therefore, we introduce laser therapy, a widely used technique treat pigmentation in dermatology. Various parameters of laser therapy can be applied, so to determine the optimal exposure parameters that do not damage the surrounding tissues, the subjects were divided into four groups: a non-stimulation group and three laser groups (4 J/cm2 group, 6 J/cm2 group, and 8 J/cm2 group). We selected the wavelength and output of laser as follows: 660nm and 50mW. The 40 were divided into four groups of 10. In the first experiment, we measured skin temperature using Digital infrared thermography in order to observe whether the laser could cause heat damage. In the second experiment, each group received the assigned laser therapy protocol every 24 hours for 72 hours. We obtained a skin image using a cross polarization technique. Previous studies have shown that a*and E.I (erythema index) represent the degree of skin erythema (hemoglobin content). M.I (melanin index) indicates the degree of skin pigmentation (melanin content). Hence, skin color information was analyzed with the a*, erythema index (E.I), and melanin index (M.I) for 72 hours. None of the laser exposure parameters led to skin damage by heating or energy dissipation. The results of a*, E.I, and M.I of all groups showed the different recovery rates towards the normal skin color information before cupping. As energy density increases, the result of a* and E.I showed the fast recovery rate. There was no significant different between M.I at non-stimulation group and M.I at 4 J/cm². Therefore, the least energy density as 6 J/cm² is need for the recovery of melanin content. The a*, E.I, and M.I at 8 J/cm² group rather than other groups were significantly recovered to normal skin color. In conclusion, the laser therapy (energy density: 8 J/cm²) has a significant recovery of the skin erythema and skin pigmentation except to skin damage.