Multi-color Space Research Articles

Thermal Image Enhancement Algorithm Based on Adaptive Fusion Technique of Multi Color Space

This paper presents an improvement of the enhancement algorithm of thermal images in order to increase the quality of low contrast and low Illumination Infrared images. Our approach based on Fusion of Multi-Color Spaces, two main stages are tested: in the first stage the thermal images mapped from RGB color space to LAB and HSV Color Spaces where enhancement is done and reconverted to the RGB space, the luminance component (V) in HSV Color Space and the luminance component (L) in LAB Color Space are enhance using CLAHE method. In the second stage, the contrast improving is done by the fusing of both results. The results of the experimental demonstrate the performance of the proposed algorithm for improving the quality of thermal images in comparison with the published works.

Spectral Reflectance Recovery from Tristimulus Values under Multi-Illuminants

An efficient procedure for recovering spectral reflectance using an object’s tristimulus values under multi-illuminants is proposed by adapting with the characteristics of the testing sample to obtain the transformation matrix of pseudoinverse. Specifically, we propose the reference illuminants selection strategy and local sample weighted strategy to obtain the optimal transformation matrix under multi-illuminants condition. Selecting the reference illuminants are based on the result of the spectral angle mapper (SAM) statistics. The number of the selected local training samples and the weighted local samples can be determined by using the multicolor space Euclidean distance. To compare the experimental results, the proposed method significantly increases the spectral and colorimetric accuracy for the spectral reflectance recovery process.

Multi-color space learning for image segmentation based on a support vector machine

Image segmentation is one of the most important research directions in computer fields and is also an important component of pattern recognition. In RoboCup competitions, the accurate positioning of the target object is particularly important to the control of the robots. An image segmentation method based on edge and color features is proposed in the present paper. Firstly, the image pixel color features are extracted in multi-color space, and the edge features of the objects are extracted by an adaptive Canny operator. The color features set the entropy, mean, and variance of the pixels in the component image. Then the color and edge features of the image are clustered by Fuzzy C-means. The clustering result of FCM is used as the input of the RBF-SVM model. Finally, the training model is applied to segment the image and output the position of the target object. The present experiment first verified the performance of the multi-color space model by simulation experiments, then conducted image segmentation experiments in images from RoboCup competition, and used Region Circularity and Boundary Center Deviation as evaluation indicators to analyze the performance of the algorithm. The experimental results showed that this method has better performance in image segmentation. Compared with existing methods, it reduced the segmentation time and improved the image segmentation performance.

Mobile terminal trajectory recognition based on improved LSTM model

Mobile terminal hand trajectory recognition is challenged by spatio-temporal variations, complex background, light variations as well as the limited computing resources for mobile devices. The authors propose a hand trajectory recognition method based on improved Long-Short Term Memory network (LSTM) model. First, for the sake of eliminating the effects of complex background and light, the SSD hand detector and multi-color space are combined to segment gesture. To eliminate the influence of trajectory points' overlap, the sparseness of the trajectory points is used to determine the start and end of the trajectory; then, to maintain the feature difference while decreasing the feature extraction time, they extract the trajectory feature sequence based on the central point direction angle; Finally, a new loss function (M-Softmax loss) is proposed in LSTM training process to maximise the inter-class variations and minimise intra-class variations. At the same time, the adaptive training iteration number is proposed to ensure the convergence of the model and reduce the training time cost. The experimental results illustrate that the improved model learned features are more compact, and the model is easier to deal with external data changes. Authors’ proposed method has great significance in practical applications.

Multi-color Space Features Analysis from Rock Shin-section Image for Rock-type classification

To fully analyze the features extracting from multi-color space for rock classification, each feature will be evaluated in this paper. And, to enhance correlation between features and reduce dimensionality of feature space, a PCA approach will be used and the result of PCA will also be fully analyzed. A C-SVM model is chosen to test analysis result. Data set consist of 500 images from Ordos basin. The classification result between single color space and multi-color space will be compared, and the cooperation result shows that features from multi-color space can support classifier like C-SVM to take higher accuracy and higher reliability.

Mobile terminal gesture recognition based on improved FAST corner detection

Mobile terminal gesture recognition is an extreme challenge, not only because its limited computing resource make it complicated to identify feature points but also the complex background can easily affect the recognition result. This study proposes a gesture recognition method based on improved features from accelerated segment test (FAST) corner detection. First, in order to eliminate the effects of complex background and light, the intersection of the two frame images is obtained through background subtraction and the multi-colour space to realise the detection of the hand. Second, in order to improve the performance of the algorithm, an improved FAST corner detection method combined with the back propagation neural network (BPNN) is proposed in accordance with the characteristics of fingertips. Subsequently, the feature points are screened by method of non-maximum suppression. Finally, gesture recognition is realised by matching feature points. Experimental results illustrate that this method has strong anti-interference ability in complex background, and it is good at performance.

An Improved GMM-Based Algorithm With Optimal Multi-Color Subspaces for Color Difference Classification of Solar Cells

Automatic color classification for solar cells is challenging because of the tiny color difference and low contrast. To address this problem, a color feature selection and classification frame is proposed in this paper. First, an intuitive multi-color space feature performance evaluation scheme is presented to select the optimal color subspaces that help to enormously enlarge the tiny color difference of solar cell images. And the optimal color subspaces can also be illustrated by employing multi-color space visualization method with combinational Mosaic images. Second, a nine-dimensional feature vector consisting of mean, variance, and skewness in the three optimal subspaces is extracted by utilizing the serial fusion technique. Third, an improved Gaussian mixture model in supervised manner for color classification is proposed by employing a k-means method based on adjacent rules, which helps to eliminate isolated points and enhances the classification performance. Finally, experimental results show that the overall performance of the proposed method achieves 97.9%, and outperform other algorithms especially for the tiny color difference of solar cell images.

Multi-color space local binary pattern-based feature selection for texture classification (Erratum)

Multi-color space local binary pattern-based feature selection for texture classification (Erratum)

Multi-color space local binary pattern-based feature selection for texture classification

This paper deals with multi-color space texture classification. Two approaches are proposed and compared: a multi-color space histogram selection (MCSHS) and a multi-color space bin selection. These approaches select local binary pattern (LBP) histograms or LBP bins that have been processed from images coded in multiple color spaces. On the one hand, the proposed LBP-based feature selection scheme overcomes the difficulty of choosing a relevant color space, and on the other hand, it takes advantage of the specific properties of several color spaces by combining them. Experiments show that the MCSHS approach is relevant for color texture classification issues that require good performances whether in accuracy or classification computation time.

Machine-learning identification of galaxies in the WISE × SuperCOSMOS all-sky catalogue

The two currently largest all-sky photometric datasets, WISE and SuperCOSMOS, were cross-matched by Bilicki et al. (2016) (B16) to construct a novel photometric redshift catalogue on 70% of the sky. Galaxies were therein separated from stars and quasars through colour cuts, which may leave imperfections because of mixing different source types which overlap in colour space. The aim of the present work is to identify galaxies in the WISExSuperCOSMOS catalogue through an alternative approach of machine learning. This allows us to define more complex separations in the multi-colour space than possible with simple colour cuts, and should provide more reliable source classification. For the automatised classification we use the support vector machines learning algorithm, employing SDSS spectroscopic sources cross-matched with WISExSuperCOSMOS as the training and verification set. We perform a number of tests to examine the behaviour of the classifier (completeness, purity and accuracy) as a function of source apparent magnitude and Galactic latitude. We then apply the classifier to the full-sky data and analyse the resulting catalogue of candidate galaxies. We also compare thus produced dataset with the one presented in B16. The tests indicate very high accuracy, completeness and purity (>95%) of the classifier at the bright end, deteriorating for the faintest sources, but still retaining acceptable levels of 85%. No significant variation of classification quality with Galactic latitude is observed. Application of the classifier to all-sky WISExSuperCOSMOS data gives 15 million galaxies after masking problematic areas. The resulting sample is purer than the one in B16, at a price of lower completeness over the sky. The automatic classification gives a successful alternative approach to defining a reliable galaxy sample as compared to colour cuts.

Towards automatic classification of all WISE sources

The WISE satellite has detected hundreds of millions sources over the entire sky. Classifying them reliably is however a challenging task due to degeneracies in WISE multicolour space and low levels of detection in its two longest-wavelength bandpasses. Here we aim at obtaining comprehensive and reliable star, galaxy and quasar catalogues based on automatic source classification in full-sky WISE data. This means that the final classification will employ only parameters available from WISE itself, in particular those reliably measured for a majority of sources. For the automatic classification we applied the support vector machines (SVM) algorithm, which requires a training sample with relevant classes already identified, and we chose to use the SDSS spectroscopic dataset for that purpose. By calibrating the classifier on the test data drawn from SDSS, we first established that a polynomial kernel is preferred over a radial one for this particular dataset. Next, using three classification parameters (W1 magnitude, W1-W2 colour, and a differential aperture magnitude) we obtained very good classification efficiency in all the tests. At the bright end, the completeness for stars and galaxies reaches ~95%, deteriorating to ~80% at W1=16 mag, while for quasars it stays at a level of ~95% independently of magnitude. Similar numbers are obtained for purity. Application of the classifier to full-sky WISE data, flux-limited to 16 mag (Vega) in the 3.4 {\mu}m channel, and appropriate a posteriori cleaning allowed us to obtain reliably-looking catalogues of star and galaxy candidates. However, the sources flagged by the classifier as `quasars' are in fact dominated by dusty galaxies but also exhibit contamination from sources located mainly at low ecliptic latitudes, consistent with Solar System objects. [abridged]

WISE × SuperCOSMOS PHOTOMETRIC REDSHIFT CATALOG: 20 MILLION GALAXIES OVER 3π STERADIANS

ABSTRACT We cross-match the two currently largest all-sky photometric catalogs—mid-infrared Wide-field Infrared Survey Explorer and SuperCOSMOS scans of UKST/POSS-II photographic plates—to obtain a new galaxy sample that covers 3π steradians. In order to characterize and purify the extragalactic data set, we use external GAMA and Sloan Digital Sky Survey spectroscopic information to define quasar and star loci in multicolor space, aiding the removal of contamination from our extended source catalog. After appropriate data cleaning, we obtain a deep wide-angle galaxy sample that is approximately 95% pure and 90% complete at high Galactic latitudes. The catalog contains close to 20 million galaxies over almost 70% of the sky, outside the Zone of Avoidance and other confused regions, with a mean surface density of more than 650 sources per square degree. Using multiwavelength information from two optical and two mid-IR photometric bands, we derive photometric redshifts for all the galaxies in the catalog, using the ANNz framework trained on the final GAMA-II spectroscopic data. Our sample has a median redshift of , with a broad reaching up to z > 0.4. The photometric redshifts have a mean bias of , a normalized scatter of σ z = 0.033, and less than 3% outliers beyond 3σ z . Comparison with external data sets shows no significant variation of photo-z quality with sky position. Together with the overall statistics, we also provide a more detailed analysis of photometric redshift accuracy as a function of magnitudes and colors. The final catalog is appropriate for “all-sky” three-dimensional (3D) cosmology to unprecedented depths, in particular through cross-correlations with other large-area surveys. It should also be useful for source preselection and identification in forthcoming surveys, such as TAIPAN or WALLABY.

Sparse tree structured representation for re-identification

Finding substantial features for image representation is one of the keys to cope with the challenges of person re-identification given video streams. The important features for re-identification can be found by image saliency computation and subject appearance modeling. State-of-the-art models explore this direction by balancing between the global low-level features and the features from local patches. We proposed a novel nested patch tree for a tree structured feature representation, and the feature representation is used to match between a probe image and a gallery image to solve the re-identification problem. The feature representation is learned based on an unsupervised approach, which is different from the majority of the community when they work on finding similar subjects. Usually, the video streams for the same figure may have highly repetitive information, and the pseudo repetitiveness should be useful for a center-learning based method. We further improve the prediction accuracy by learning components by components for the same subject and working in the multi-color space. We evaluate the proposed method for person re-identification on the VIPeR and GRID datasets. The result shows that the proposed method is indeed superior to other state-of-the-art methods.

Multi-color space threshold segmentation and self-learning k-NN algorithm for surge test EUT status identification

The identification of targets varies in different surge tests. A multi-color space threshold segmentation and self-learning k-nearest neighbor algorithm (k-NN) for equipment under test status identification was proposed after using feature matching to identify equipment status had to train new patterns every time before testing. First, color space (L*a*b*, hue saturation lightness (HSL), hue saturation value (HSV)) to segment was selected according to the high luminance points ratio and white luminance points ratio of the image. Second, the unknown class sample Sr was classified by the k-NN algorithm with training set Tz according to the feature vector, which was formed from number of pixels, eccentricity ratio, compactness ratio, and Euler’s numbers. Last, while the classification confidence coefficient equaled k, made Sr as one sample of pre-training set Tz′. The training set Tz increased to Tz+1 by Tz′ if Tz′ was saturated. In nine series of illuminant, indicator light, screen, and disturbances samples (a total of 21600 frames), the algorithm had a 98.65%identification accuracy, also selected five groups of samples to enlarge the training set from T0 to T5 by itself.

Improved Dynamic Threshold Method for Skin Colour Detection Using Multi-Colour Space

This paper presents a skin colour detection based on animproved dynamic threshold method to reduce false skin detection. Current fixedthreshold skin detection fails in certain situations such as misclassificationbetween non skin-like with similar skin-like colour. Any true skin may falsely bedetected as non-skin. Research work introduces high-level skin detection strategybased on online sampling where offline training is not required. This strategyshows a promising performance in term of classifying images under skin-like andethnicity image variations. However, some of the methods produced high falsepositives that reduced the accuracy of skin detection performance. Therefore,in this study, instead of single colour space and fixed threshold method, animproved skin detection based on multi-colour spaces is proposed. Furthermore,a dynamic threshold method also has been improved by introducing elasticelliptical mask model for online skin sampling. The experimental result showsan improvement in employing multi-colour rather than single colour space byreducing the false positive and increasing the precision rate.

Unsupervised color-image segmentation by multicolor space iterative pixel classification

We propose a color-image segmentation algorithm by unsupervised classification of pixels. The originality of the proposed approach consists in iteratively identifying pixel classes by taking into account both the pixel color distributions in several color spaces and their spatial arrangement in the image. In order to overcome the difficult problem of the color space choice, the algorithm selects the color space that is well suited to construct the class at each iteration step. The selection criterion is based on connectedness and color homogeneity measures of pixel subsets. In order to tune the sensitivity of segmentation, we introduce a hierarchical criterion that allows us to segment images with different numbers of regions as human observers do. Experiments carried out on the well-known Berkeley segmentation dataset show that this multicolor space approach succeeds in constructing classes that effectively correspond to regions in the image.

PHOTOMETRIC REDSHIFT WITH BAYESIAN PRIORS ON PHYSICAL PROPERTIES OF GALAXIES

We present a proof-of-concept analysis of photometric redshifts with Bayesian priors on physical properties of galaxies. This concept is particularly suited for upcoming/on-going large imaging surveys, in which only several broad-band filters are available and it is hard to break some of the degeneracies in the multi-color space. We construct model templates of galaxies using a stellar population synthesis code and apply Bayesian priors on physical properties such as stellar mass and star formation rate. These priors are a function of redshift and they effectively evolve the templates with time in an observationally motivated way. We demonstrate that the priors help reduce the degeneracy and deliver significantly improved photometric redshifts. Furthermore, we show that a template error function, which corrects for systematic flux errors in the model templates as a function of rest-frame wavelength, delivers further improvements. One great advantage of our technique is that we simultaneously measure redshifts and physical properties of galaxies in a fully self-consistent manner, unlike the two-step measurements with different templates often performed in the literature. One may rightly worry that the physical priors bias the inferred galaxy properties, but we show that the bias is smaller than systematic uncertainties inherent in physical properties inferred from the SED fitting and hence is not a major issue. We will extensively test and tune the priors in the on-going Hyper Suprime-Cam survey and will make the code publicly available in the future.

Quantization Methodology of Autofluorescence Bronchoscopy Image in the YUV System

背景与目的通过对不同病理类型的自荧光气管镜（autofluorescence bronchoscope, AFB）图像目标区域的YUV定量分析，确定区分不同疾病类型的最佳判别指标，探讨AFB在中央型支气管肺癌诊断中的价值。方法对研究对象进行白光气管镜+AFB检查，二者在镜下存在异常者行活检。并对荧光图像显示病变部位通过MATLAB图像测量软件进行YUV定量分析。根据正常支气管粘膜、炎症、低级别上皮样瘤变、高级别上皮样瘤变、浸润性癌的病理结果分组。研究各组与YUV值间的关系，所得数据采用SPSS 11.5软件进行统计学处理。结果Y值在浸润性癌和LGD组间存在统计学差异（P=0.040），在浸润性癌和炎症组也存在明显统计学差异（P < 0.001）。其他的各组间无统计学差异。U值在浸润性癌和HGD、LGD、炎症、正常支气管粘膜组之间存在统计学差异（P < 0.050），能较好鉴别正常粘膜及恶性病变。V值在浸润性癌和LGD组（P=0.003）、炎症组（P < 0.001）、正常支气管粘膜组（P < 0.001）存在统计学差异，能有效鉴别浸润性癌及良性疾病。V值在正常支气管粘膜组与HGD组（P=0.001）、炎症组（P=0.004）间比较也具有统计学差异。结论利用YUV色彩空间系统针对支气管和肺良恶性疾病鉴别有一定临床应用价值，为临床气管镜诊断肺癌及癌前病变提供有效科学依据。

A Real-Time Apple Grading System Using Multicolor Space

This study was focused on the multicolor space which provides a better specification of the color and size of the apple in an image. In the study, a real-time machine vision system classifying apples into four categories with respect to color and size was designed. In the analysis, different color spaces were used. As a result, 97% identification success for the red fields of the apple was obtained depending on the values of the parameter “a” of CIE L*a*b*color space. Similarly, 94% identification success for the yellow fields was obtained depending on the values of the parameter y of CIE XYZ color space. With the designed system, three kinds of apples (Golden, Starking, and Jonagold) were investigated by classifying them into four groups with respect to two parameters, color and size. Finally, 99% success rate was achieved in the analyses conducted for 595 apples.

Supervised texture classification: color space or texture feature selection?

The color of pixels can be represented in different color spaces which take into account different properties. However, no color space is well-suited to the discrimination of all texture databases and the prior determination of such a space is not easy. In this paper, we compare the performances reached by two texture classification schemes that use color spaces: (a) the single color space selection approach, that defines a set of texture features and then selects the color space with which the texture features allow to reach the highest classification accuracy, (b) the multi-color space feature selection (MCSFS) approach, that selects texture features which have been processed from images coded into different color spaces. Experiments carried out with benchmark texture databases show that taking advantage simultaneously of the properties of several color spaces thanks to the MCSFS approach improves the rates of well-classified images with lower learning and decision processing times.