YCbCr Color Space Research Articles

A Face Detection Method Based on Skin Color Features and AdaBoost Algorithm

The face detection based on skin color features is greatly affected by illumination and the face detection based on AdaBoost algorithm is greatly affected by multi-pose of face, and this means that the large face deflection will make the detection less accurate. So we investigated a face detection method that combines the skin color model and the improved AdaBoost algorithm in this paper. This method first judges whether the collected face image needs illumination compensation. The image is converted from RGB color space to YCbCr color space with higher pixel clustering characteristics and distribution rules by whether it is needed or not. Meanwhile, the candidate regions containing face images are carried out through morphological process and shape select after establishing the Gaussian model. Finally, the face detection results are obtained through detecting the candidate regions with face images by improved AdaBoost algorithm. A large number of experimental results show that this new method can effectively reduce the false detection rate and improve the efficiency of face detection.

Fusion of Handcrafted and Deep Features for Forgery Detection in Digital Images

Content authentication of digital images has captured the attention of forensic experts and security researchers due to a multi-fold increase in the dissemination of multimedia data through the open and vulnerable Internet. Shrewd attackers successfully devise novel ways to challenge state-of-art forensic tools used for forgery detection in digital images. Feature engineering approaches have yielded up to 97% accuracy on benchmarked datasets. Deep learning approaches have shown promising results in various image classification problems but cannot find hidden patterns in digital images, which can reliably detect image forgeries. State-of-art accuracy of deep learning approaches for forgery detection is up to 98% on benchmarked datasets. The objective of the proposed approach is to further escalate the detection accuracy, pushing it near 100%. In this paper, a synergy of handcrafted features based on color characteristics and deep features using the image’s luminance channel is employed to mine patterns responsible for accurate forgery detection. In the first Stream, 648-D Markov-based features are computed from the quaternion discrete cosine transform of the image. In the second Stream, the luminance channel of YCbCr colorspace is used to extract the Local Binary Pattern of the image. Further, local binary feature maps are fed to the pre-trained ResNet-18 model to obtain a 512-D feature vector called ’ResFeats’ from the last layer of the model’s convolutional base portion. The handcrafted features from Stream I and ResFeats from Stream II are combined to form an 1160-D feature vector. Further, classification is performed using a shallow neural network, and the method is tested on CASIA v1 and CASIA v2 datasets. The accuracy of the proposed fusion-based approach is 99.3% on benchmark datasets.

Auto Colorization of Gray-Scale Image Using YCbCr Color Space

The process of converting gray images or videos to color ones by adding colors to them and transforming them from one-dimension to three-dimension is called colorization. This process is often used to make the image appear more visually appealing. The main problem with the colorization process is the lack of knowledge of the true colors of the objects in the picture when it is captured. For that, there is no a unique solution. In the current work, the colorization of gray images is proposed based on the utilization of the YCbCr color space. Reference image (color image) is selected for transferring the color to a gray image. Both color and gray images are transferred to YCbCr color space. Then, the Y value of the gray image is combined with the Cb and Cr values of the reference image, based on the Euclidian distance between them. The quality of the resulted image was measured based on several quality measures, which indicated very good results. The proposed algorithm is simple, efficient, and fast.

Race Classification from Face Images Using Fast Fourier Transform and Discrete Cosine Transform

Ethnicity identification and recognition is a key biometric technology with a wide range of applications related to homeland security, safety, access control, and automatic annotation. Ethnicity identification from face images is a process of gathering facial features of an individual face image compared to existing face images in the dataset to interpretation his/her ethnic class. In this paper, a propose method in multi-level fusion schema for ethnicity identification by using two global features; fast Fourier transform (FFT) and discrete cosine transform (DCT) on the pre-processed face image of size 128 * 128 in YCbCr color space. A dataset is consisting of 750 face image of three different ethnicities (Kurd 300, Oriental 300 and African 150). The query image feature is compared with a dataset image features using k – nearest neighbor classifier using City block distance for evaluating similarity measurement. The experimental result shows good accuracy and demonstrate the effectiveness of the combined features reached an accuracy rate 96.22% of classification.

Severity Estimation of Plant Leaf Diseases Using Segmentation Method

Plants have assumed a significant role in the history of humankind, for the most part as a source of nourishment for human and animals. However, plants typically powerless to different sort of diseases such as leaf blight, gray spot and rust. It will cause a great loss to farmers and ranchers. Therefore, an appropriate method to estimate the severity of diseases in plant leaf is needed to overcome the problem. This paper presents the fusions of the Fuzzy C-Means segmentation method with four different colour spaces namely RGB, HSV, L*a*b and YCbCr to estimate plant leaf disease severity. The percentage of performance of proposed algorithms are recorded and compared with the previous method which are K-Means and Otsu’s thresholding. The best severity estimation algorithm and colour space used to estimate the diseases severity of plant leaf is the combination of Fuzzy C-Means and YCbCr color space. The average performance of Fuzzy C-Means is 91.08% while the average performance of YCbCr is 83.74%. Combination of Fuzzy C-Means and YCbCr produce 96.81% accuracy. This algorithm is more effective than other algorithms in terms of not only better segmentation performance but also low time complexity that is 34.75s in average with 0.2697s standard deviation.

WBCs detection depending based on a binary conversion of the color component in a Ycbcr color space

Detection of white blood cells (WBCs) automatically is an important issue that has many applications in the field of medical imaging, in this research, we tend to detect white blood cells depending on the Ycbcr color space. The proposed method has been used for the binary conversion of color compounds cbcr depending on the certain threshold limits. In the experimental results from microscopy images of blood samples, the proposed algorithm was compared with several other algorithms for detection by using a quality scale that compares manual cell count with automatic detection of algorithms where the proposed algorithm obtained a high distinction accuracy reached to 100% compared to other methods.

Lettuce Canopy Area Measurement Using Static Supervised Neural Networks Based on Numerical Image Textural Feature Analysis of Haralick and Gray Level Co-Occurrence Matrixs

Leaf canopy area is a fundamental crop growth characteristic that encompasses the spatial area covered by plants. However, non-destructive and automatic computation of lettuce canopy area is still open research. This study presents a vision-based system with color space thresholding and machine learning models in measuring the photosynthetic productivity of aquaponic lettuce based on canopy area derived from the numerical image textural features of Haralick and gray level co-occurrence matrix (GLCM). Lettuce images on different growth stages with varying photosynthetic pigment intensities and geometrical structures are extracted with contrast, correlation, energy, homogeneity, entropy, variance, and information measure of correlations 1 and 2 features. For multi-band color space thresholding, CIELab bested RGB, HSV, and YCbCr colour spaces in segmenting the lettuce plant with sensitivity and specificity measures of 94.77% and 97.16% respectively. For measuring the lettuce canopy area, RMSE was recorded as 50.23% for fitness function neural network (FFNN), 20.46% for radial basis function neural network (RBFNN), 15.11% for exact radial basic function neural network (RBEFNN) and 13.54% for generalized regression neural network (GRNN). Comparative analysis revealed that the two-hidden layer GRNN model with 0.09 spread value and 240 hidden neurons bested other machine learning models in terms of RMSE without overfitting.

Low-Illumination Image Enhancement for Night-Time UAV Pedestrian Detection

To accomplish reliable pedestrian detection using unmanned aerial vehicles (UAVs) under night-time conditions, an image enhancement method is developed in this article to improve the low-illumination image quality. First, the image brightness is mapped to a desirable level by a hyperbolic tangent curve. Second, the block-matching and 3-D filtering methods are developed for an unsharp filter in YCbCr color space for image denoising and sharpening. Finally, pedestrian detection is performed using a convolutional neural network model to complete the surveillance task. Experimental results show that the Minkowski distance measurement index of enhanced images is increased to 0.975, and the detection accuracies, in F-measure and confidence coefficient, reach 0.907 and 0.840, respectively, which are the highest as compared with other image enhancement methods. This developed method has potential values for night-time UAV visual monitoring in smart city applications.

Digital Image Steganography Scheme for Speech Signals in the Discrete Wavelet Transform Domain

In recent years, the evolution and expansion of the multimedia world has allowed digital images to be widely used as a carrier medium for facilitating the sending and receiving of confidential digital content such as text, audio and images. However, there are few steganographic schemes that hide digital speech signals into digital images; also, the state-of-the-art methods have some disadvantages such as low embedding capacity, low quality in the modified image, and/or low audible quality in the recovered speech signal. In this paper, a new steganographic scheme that hides a digital speech signal into a color image is presented, where the embedding process is performed in the HL and LH channels of the first decomposition level of the discrete wavelet transform (DWT) over the YCbCr color space; additionally, a chaotic map method is implemented to encrypt the speech signal and to spread it throughout the whole image. Experimental results have demonstrated that the proposed scheme results in better performance against other state-of-the-art methods, due to their ability to embed and recover speech signals with duration up to 16.384 seconds using color images of 512×512 pixels, obtaining 32 dB and 0.92 in PSNR and SSIM, respectively for the stego-image, and 41 dB in SNR for the recovered speech signal.

Steganography-assisted secure localization of smart devices in internet of multimedia things (IoMT)

Steganography is a secure way of communicating secret visual data/information from one place to another via multimedia carriers. Digital steganography, spatial and frequency domain has taken several methods over the past two decades. In this work, we present steganography-assisted secure localization of smart devices for Visual Sensor Network (VSN). The proposed system is based on achromatic-component (Y-Plane) of the YCbCr color space and maximum likelihood estimation algorithm (MLEA) in the spatial domain. Data/information security via multimedia carriers is the main concern in this technological era, if secret information is captured by a Visual Sensor network, (VSN) then the capture information in the case to send from one place to another needs fundamental security to keep the information confidential. In the proposed steganography-assisted Visual Sensor Network (VSN) the camera nodes are intelligent to process the image data and to extract the important information and the rich-description are provided to the system’s user for further action. In the proposed technique first, the input image is rotated on 90 degrees and transformed into YCbCr color space. Furthermore, the secret data is separated into different blocks of the same size based on key giving sub-blocks in Y-Plane, secret information is then encrypted using an MLE algorithm (MLEA) and the corresponding blocks of secret data is embedded in the sub-image of Y-Plane. The experimental results authenticate that the proposed technique does not only boost the visual quality of stegno-images but also delivers good imperceptibility, robustness, and security as compared to state-of-the-art approaches.

Image Steganography Based on Wavelet Transform and Color Space Approach

This paper presents a color image steganography scheme based on discrete wavelet transform (DWT) and YCbCr color space. The cover image is initially transformed from RGB color space into YCbCr and the Cb component is utilized for hiding a secret grayscale image. Two-level DWT is applied to the selected component to obtain the horizontal sub-band HL2 which is used for the embedding process based on the singular value decomposition (SVD) of the secret image and the obtained sub-band HL2 of the cover image. Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) are measured for evaluating the performance of the proposed scheme. Simulation results show that the proposed steganography method is reliable against several attacks without degrading the visual quality of the cover image. Further, comparative results for the proposed method in YCbCr and RGB color spaces show that the YCbCr space is more efficient in secret image retrieval

Extracted features based multi-class classification of orthodontic images

The purpose of this study is to investigate computer vision and machine learning methods for classification of orthodontic images in order to provide orthodontists with a solution for multi-class classification of patients’ images to evaluate the evolution of their treatment. Of which, we proposed three algorithms based on extracted features, such as facial features and skin colour using YCbCrcolour space, assigned to nodes of a decision tree to classify orthodontic images: an algorithm for intra-oral images, an algorithm for mould images and an algorithm for extra-oral images. Then, we compared our method by implementing the Local Binary Pattern (LBP) algorithm to extract textural features from images. After that, we applied the principal component analysis (PCA) algorithm to optimize the redundant parameters in order to classify LBP features with six classifiers; Quadratic Support Vector Machine (SVM), Cubic SVM, Radial Basis Function SVM, Cosine K-Nearest Neighbours (KNN), Euclidian KNN, and Linear Discriminant Analysis (LDA). The presented algorithms have been evaluated on a dataset of images of 98 different patients, and experimental results demonstrate the good performances of our proposed method with a high accuracy compared with machine learning algorithms. Where LDA classifier achieves an accuracy of 84.5%.

Classifying white blood cells from a peripheral blood smear image using a histogram of oriented gradient feature of nuclei shapes

Researchers developed various methods and algorithms to classify white blood cells (WBCs) from blood smear images to assist hematologists and to develop an automatic system. Furthermore, the pathological and hematological conditions of WBCs are related to diseases that can be analyzed accurately in a short time. In this work, we proposed a simple technique for WBC classification from a peripheral blood smear image based on the types of cell nuclei. The developed algorithms utilized a histogram of oriented gradient (HOG) feature typically known for application in human disease detection. The segmentation of WBC nuclei utilizes a YCbCr color space and K-means clustering techniques. The HOG feature contains information about the cell nuclei shapes, which then is classified using a support vector machine (SVM) and backpropagation artificial neural network (ANN). The results show that the proposed HOG feature is useful for WBC classification based on the shapes of nuclei. We are able to categorize the type of a WBC based on its nucleus shape with more than 95% accuracy.

Aerial Forest Fire Detection and Monitoring Using a Small UAV

In recent years, large patches of forest have been destroyed by fires, bringing tragic consequences for the environment and small settlements established around these regions. In this context, it is essential that fire fighting teams possess an increased situational awareness about the fire propagation, in order to promptly act in the extinguishing process. Recent advances in UAV technology allied with remote sensing and computer vision techniques show very promising UAVs applicability in forest fires detection and monitoring. Besides presenting lower operational costs, these vehicles are able to reach regions that are inaccessible or considered too dangerous for fire fighting crews operations. This paper describes the application of a real-time forest fire detection algorithm using aerial images captured by a video camera onboard an Unmanned Aerial Vehicle (UAV). The forest fire detection algorithm consists of a rule-based colour model that uses both RGB and YCbCr colour spaces to identify fire pixels. An intuitive targeting system was also developed, allowing the detection of multiple fires at the same time. Additionally, a fire geolocation algorithm was developed in order to estimate the fire location in terms of latitude (φ), longitude (λ) and altitude (h). The geolocation algorithm consists of applying two coordinates systems transformations between the body-fixed frame, North-East-Down frame (NED) and Earth-Centered, Earth Fixed (ECEF) frame. Flight tests were performed during a controlled burn in order to assess the fire detection algorithm performance. The algorithm was able to detect the fire with few false positive detections.
 Keywords: Aerial fire detection algorithm, Aerial fire monitoring, Forest fire, UAV, Remote sensing

Cross-Component Prediction in HEVC

Video coding in the YCbCr color space has been widely used, since it is efficient for compression, but it can result in color distortion due to conversion error. Meanwhile, coding in the RGB color space maintains high color fidelity, having the drawback of a substantial bitrate increase with respect to YCbCr coding. Cross-component prediction (CCP) efficiently compresses video content by decorrelating color components while keeping high color fidelity. In this scheme, the chroma residual signal is predicted from the luma residual signal inside the coding loop. This paper gives a description of the CCP scheme from several points of view, from theoretical background to practical implementation. The proposed CCP scheme has been evaluated in standardization communities and adopted into H.265/High Efficiency Video Coding (HEVC) Range Extensions. The experimental results show significant coding performance improvements for both natural and screen content video, while the quality of all color components is maintained. The average coding gains for natural video are 17% and 5% bitrate reduction in the case of intra coding and 11% and 4% in the case of inter coding for RGB and YCbCr coding, respectively, while the average increment of encoding and decoding times in the HEVC reference software implementation are 10% and 4%, respectively.

Nondestructive determination of soluble solids content and pH in red bayberry (Myrica rubra) based on color space.

Color has strong relationship with food quality. In this paper, partial least square regression (PLSR) and least square-support vector machine (LS-SVM) models combined with six different color spaces (NRGB, CIELAB, CMY, HSI, I1I2I3, and YCbCr) were developed and compared to predict pH value and soluble solids content (SSC) in red bayberry. The results showed that PLSR and LS-SVM models coupled with color space could predict pH value in red bayberry (r = 0.93-0.96, RMSE = 0.09-0.12, MAE = 0.07-0.09, and MRE = 0.04-0.06). In addition, the minimum errors (RMSE = 0.09, MAE = 0.07, and MRE = 0.04) and maximum correlation coefficient value (r = 0.96) were found with the PLSR based on CMY, I1I2I3, and YCbCr color spaces. For predicting SSC, PLSR models based on CIELAB color space (r = 0.90, RMSE = 0.91, MAE = 0.69 and MRE = 0.12) and HSI color space (r = 0.89, RMSE = 0.95, MAE = 0.73 and MRE = 0.13) were recommended. The results indicated that color space combined with chemometric is suitable to non-destructively detect pH value and SSC of red bayberry.

Human Emotion Recognition Based on Face and Facial Expression Detection Using Deep Belief Network Under Complicated Backgrounds

The human emotion recognition based on facial expression has a significant meaning in the application of intelligent man–machine interaction. However, the human face images vary largely in real environments due to the complex backgrounds and luminance. To solve this problem, this paper proposes a robust face detection method based on skin color enhancement model and a facial expression recognition algorithm with block principal component analysis (PCA). First, the luminance range of human face image is broadened and the contrast ratio of skin color is strengthened by the homomorphic filter. Second, the skin color enhancement model is established using YCbCr color space components to locate the face area. Third, the feature based on differential horizontal integral projection is extracted from the face. Finally, the block PCA with deep neural network is used to accomplish the facial expression recognition. The experimental results indicate that in the case of weaker illumination and more complicated backgrounds, both the face detection and facial expression recognition can be achieved effectively by the proposed algorithm, meanwhile the mean recognition rate obtained by the facial expression recognition method is improved by 2.7% comparing with the traditional Local Binary Patterns (LBPs) method.

An automatic visible-range video weed detection, segmentation and classification prototype in potato field

Weeds might be defined as destructive plants that grow and compete with agricultural crops in order to achieve water and nutrients. Uniform spray of herbicides is nowadays a common cause in crops poisoning, environment pollution and high cost of herbicide consumption. Site-specific spraying is a possible solution for the problems that occur with uniform spray in fields. For this reason, a machine vision prototype is proposed in this study based on video processing and meta-heuristic classifiers for online identification and classification of Marfona potato plant (Solanum tuberosum) and 4299 samples from five weed plant varieties: Malva neglecta (mallow), Portulaca oleracea (purslane), Chenopodium album L (lamb's quarters), Secale cereale L (rye) and Xanthium strumarium (coklebur). In order to properly train the machine vision system, various videos taken from two Marfona potato fields within a surface of six hectares are used. After extraction of texture features based on the gray level co-occurrence matrix (GLCM), color features, spectral descriptors of texture, moment invariants and shape features, six effective discriminant features were selected: the standard deviation of saturation (S) component in HSV color space, difference of first and seventh moment invariants, mean value of hue component (H) in HSI color space, area to length ratio, average blue-difference chrominance (Cb) component in YCbCr color space and standard deviation of in-phase (I) component in YIQ color space. Classification results show a high accuracy of 98% correct classification rate (CCR) over the test set, being able to properly identify potato plant from previously mentioned five different weed varieties. Finally, the machine vision prototype was tested in field under real conditions and was able to properly detect, segment and classify weed from potato plant at a speed of up to 0.15 m/s.

Color and white balancing in low-light image enhancement

Images acquired during night either appear too dark or either seem biased towards the color of lighting source. This paper proposes a low-light image enhancement technique that simultaneously preserves contrast and removes color saturation from an input image. Initially low and high frequencies are extracted from the low light image. Color balancing is performed on low frequencies using a sigmoid function. This is followed by chromatic balancing which is done using constrained linear least square minimization in YCbCr color space. The high frequencies are added back with respect to the ratio of enhanced and original low frequencies. The proposed method improves input contrast and object prominence while reducing artifacts as compared to state-of-art low light image enhancement methods.

Robust IHWT- CRT Image Watermarking using YCbCr Color Space

This research proposes a watermarking method that combines Integer Haar Wavelet Transform (IHWT) and Chinese Remainder Theorem (CRT) algorithms on RGB images that are converted to YCbCr color space. The goal is to get a watermarking method that is robust, imperceptible and secure. Robust because with IHWT done on component Y as a place to insert a watermark done on the frequency domain that is resistant to attack. Whereas CRT is an insertion method in a spatial domain that is relatively more imperceptible to human vision, CRT also more secure because CRT is a cryptographic algorithm. Based on the results of the test and bookkeeping of the imperceptibility quality, the average PSNR value is above 48dB and the average SSIM is above 0.99. Whereas the robustness test proves that by using the YCbCr color space the increase in resistance occurs in Gaussian noise, JPEG compression and JPEG 2000 compression with an average NC value above 0.8.