Postprocessing for Skin Detection

2015

The extraction of the skin pixels in a human image and rejection of non-skin pixels is called the skin segmentation. Skin pixel detection is the process of extracting the skin pixels in a human image which is typically used as a pre-processing step to extract the face regions from human image. In past, there are several computer vision approaches and techniques have been developed for skin pixel detection. In the process of skin detection, given pixels are been transformed into an appropriate color space such as RGB, HSV etc. And then skin classifier model have been applied to label the pixel into skin or non-skin regions. Here in this research a “Region based elimination of noise pixels and performance analysis of classifier models for skin pixel detection applied on human images” would be performed which involve the process of image representation in color models, elimination of non-skin pixels in the image, and then pre-processing and cleansing of the collected data, feature sele...

Bulletin of Electrical Engineering and Informatics, 2021

With the advancement of data society today, pictures have turned out to be increasingly imperative. Automatic detection of human skin has been an area of active research for the past few years. Human skin detection assumes a vital job in a wide scope of picture preparing applications going from face detection, steganography, face tracking, age detection, discover pornographic images, the discovery of skin diseases gesture analysis and substance based picture recovery frameworks and to different human PC association spaces. Detecting human skin in complex pictures have ended up being a difficult issue since skin shading can fluctuate drastically in its appearance because of numerous variables, for example, illumination, race, maturing, imaging conditions, and complex foundation. In this study, we will study and analyze skin researches, where we will treat the weakness of previous research of survey on human skin detection methods. The reason for this investigation is to give a state-of-the-art study on human skin molding and detection methods in 1998-2019 periods. Furthermore, this research presented the statistical study for each issue stated before. We finish up with a few ramifications for a future course. Study results will benefit all researchers who are interested in human skin detection topic.

The performances of the skin detection approaches, which works based on statistical models estimated from the training dataset, depend largely on the labeled ground truth data. However, in the available benchmark datasets, the ground truth data for skin include many non-skin pixels as well as the pixels coming from the ambiguous regions falling on the boundaries of the skin regions. Moreover, the ground truth non-skin data are usually irrelevant to the available neighborhood. For such reasons, skin detection performances of the available methods are not always found to be as expected. This paper present a modified approach of using the ground truth datasets provided with the benchmark datasets for skin detection. The proposed approach takes only the ‘pure’ skin pixels and ‘relevant’ non-kin pixels into consideration while building the statistical models. Experimental results also show that the proposed approach increases the performances of different skin detection methods.

We used a data analysis approach for selecting colour components for skin detection. The criterion for this selection was to achieve a reasonable degree of generalisation and recognition, where skin points exhibit a well defined cluster. After evaluating each component of several colour models, we found that a mixure of components can cope well with such requirements. We list the top components, and from these we select one colour space: H-GY-Wr (Wr [15]). A nearly convex area of this space contains 97% of all skin points, whilst it encompass 5.16% of false positives. Even simple rules over this well-shaped space can achieve a high recognition rate and low overlap to non-skin points. This is a data analysis approach that will help to many skin detection systems.

2014

In the current era of World Wide Web, human skin detection is a critical parameter in computer vision and image processing applications. With diverse range of applications in forensic sciences, medical imaging, pornography filtering, image retrieval, video surveillance etc., skin detection algorithms are to face many challenges. The major problems in detection of human skin color are varying shades of human skin, color spaces, skin color daily life objects, and illumination conditions. This paper is a systematic study of human skin color detection methods and their classification. Moreover different domains of application are also discussed. The work presented in this paper is a survey of algorithmic techniques proposed so far, their implementation, numerical evaluation results, comparative analysis and discussion on complications.

2004

Skin detection is employed in tasks like face detection and tracking, naked people detection, hand detection and tracking, people retrieval in databases and Internet, etc. However, skin detection is not robust enough for dealing with some real-world conditions, like changing lighting conditions and complex background containing surfaces and objects with skin-like colors. This situation can be improved by incorporating context information in the skin detection process. For this reason in this article a skin detection approach that uses neighborhood information is proposed. A pixel will belong to the skin class only if a direct neighbor does. This idea is implemented through a diffusion process. Two new algorithms implementing these ideas are described and compared against state-of-the-art skin detection algorithms.

IEEE Access

This study review and analysis the literature on skin detector (SD), in order to establish the coherent taxonomy and figure out the gap on this pivotal research area. An extensive search is conducted to identify articles that deal with skin detection, skin segmentation, skin tone detector and skin recognition issues, related techniques are reviewed comprehensively and a coherent taxonomy of these articles is established. ScienceDirect, IEEE Xplore and Web of Science databases are checked for articles on skin detector. A total of 2803 papers are collected from 2007 to February 2018. The set comprised 173 articles. The largest portion of the papers (n=158/173) = 91% belong to Development and Design, that is aimed to develop an approach for skin classifier into skin and non-skin. A sum total of (n=5/173)=3% of the papers belong to Evaluation and Framework, (n=10/173) = 6% papers was categorized as Comparative Study. This study discusses the open challenges, motivations and recommendations of the related works. Furthermore, state-of-the-art is a step to demonstrate the novelty of the presented study by conducted a statistical analysis for previous studies such as (Dataset, Colour spaces, features, image type, and Classification techniques) as a future direction for other researchers who are interested in skin detector (SD).

Skin detection or segmentation is employed in many tasks related to the detection and tracking of humans and human-body parts. The goal of skin pixel detection is locate the pixels of the skins and discard other non-related pixels from regions of the image. Skin area detection has been focus research area in human-computer interactions. Most of the research done in the fields of skin detection has been trained and tested on human images. The approach of this research is to make a comparative analysis of learning classification algorithms to identify the better classifier model for skin pixel detection. Our adopted procedure is based on skin segmentation and human face features which are so called knowledge based approach for skin pixel segmentation. Based on the feature selection of the classified, we found the good detection rate by using the various classification algorithms. We have got the detection rate of above 95.79% in case of J48 algorithm and 95.04% detection rate in case of SMO algorithm. The experiment result shows that, the algorithm gives hopeful results. At last, we concluded this paper and proposed future work.

Skin detection is a well-known image processing technique that has been used in many applications such as video surveillance, naked image filters, and face detection. This paper proposes a reliable skin detection method that integrates both color and texture features. To increase the reliability of the skin detection process, neighborhood pixel information is incorporated into the proposed method. Texture features were estimated using statistical measures as range, standard deviation, and entropy. Back propagation artificial neural network is then used to learn features and classify any given input. In this work, three skin detectors based on pre-defined rules of skin color tones, texture features only, and a combination of both color and texture features have been constructed. Furthermore, the paper analyzes and compares the obtained results from the proposed skin detector with pre-defined color tones and texture feature-based skin detectors to show the level of robustness of the proposed skin detector. It found that the proposed skin detection method achieved a true positive rate of approximately 95.6176% and a false positive rate of approximately 0.8795%. Experimental results showed that our approach is more efficient compared with other state-of-the-art color-based or texture-based skin detector approaches.

Two types of combining strategies were evaluated namely combining skin features and combining skin classifiers. Several combining rules were applied where the outputs of the skin classifiers are combined using binary operators such as the AND and the OR operators, "Voting", "Sum of Weights" and a new neural network. Three chrominance components from the YC b C r colour space that gave the highest correct detection on their single feature MLP were selected as the combining parameters. A major issue in designing a MLP neural network is to determine the optimal number of hidden units given a set of training patterns. Therefore, a "coarse to fine search" method to find the number of neurons in the hidden layer is proposed. The strategy of combining C b /C r and C r features improved the correct detection by 3.01% compared to the best single feature MLP given by C b -C r . The strategy of combining the outputs of three skin classifiers using the "Sum of Weights" rule further improved the correct detection by 4.38% compared to the best single feature MLP.