Hue And Saturation Research Articles

Automated uniform recognition to enhance video surveillance at correctional services in South Africa

Injuries from inmate altercations are common in correctional service facilities. Monitoring incidents manually from video surveillance can be challenging. Computer vision has the potential to assist security personnel in securing facilities. This work compares two methods for recognising occupational uniforms with the aim of improving situational awareness and safety in prisons. The first method uses histograms of hue and saturation (HS) colour-space features and a shallow learning classifier. The second method uses convolutional neural network (CNN) models trained with either hand-engineered or automatically learned features. A training dataset with civilians, South African correctional service and police uniforms was created. The experimental results demonstrate comparable performance from shallow learning algorithms and CNN models. Machine learning algorithms evaluated on the proposed colour features achieved an average balanced performance (F1-score) of 0.85 and inference times range from 0.01 to 4.9 milliseconds.

Object Detection In Cluttered Background using Color Clusters

Object detection in presence of complex background and illumination variation is important image analysis problem with many applications. Most of the object detection algorithms use local image descriptors which are computed from interest points based on luminance information and neglect precious color information of an object. If appearances of the object to be detected contain multiple colors in non-homogeneous distributions then it makes it difficult to detect these objects using shape features. In this context, we propose a robust algorithm designed to detect a class of objects using a descriptor which is computed from color information of an object. Clusters are formed in Hue and Saturation (HS) color space of an object using k-means clustering and cluster analysis based on number of pixels belong to each cluster, object detection is performed. Use of clustering algorithm in color space of an object to form descriptor reduces the large dimensionality of the histogram bins in the computation. The performance of the algorithm is demonstrated by experimentation carried out on standard dataset GroZi-120. Experimental results shows that the proposed algorithm is insensitive to scaling, object rotation, illumination variations and capable of handling cluttered background effectively. Finally results shows that proposed algorithm outperforms closely related algorithm by a decisive margin.

Full-colour nanoprint-hologram synchronous metasurface with arbitrary hue-saturation-brightness control

The colour gamut, a two-dimensional (2D) colour space primarily comprising hue and saturation (HS), lays the most important foundation for the colour display and printing industries. Recently, the metasurface has been considered a promising paradigm for nanoprinting and holographic imaging, demonstrating a subwavelength image resolution, a flat profile, high durability, and multi-functionalities. Much effort has been devoted to broaden the 2D HS plane, also known as the CIE map. However, the brightness (B), as the carrier of chiaroscuro information, has long been neglected in metasurface-based nanoprinting or holograms due to the challenge in realising arbitrary and simultaneous control of full-colour HSB tuning in a passive device. Here, we report a dielectric metasurface made of crystal silicon nanoblocks, which achieves not only tailorable coverage of the primary colours red, green and blue (RGB) but also intensity control of the individual colours. The colour gamut is hence extruded from the 2D CIE to a complete 3D HSB space. Moreover, thanks to the independent control of the RGB intensity and phase, we further show that a single-layer silicon metasurface could simultaneously exhibit arbitrary HSB colour nanoprinting and a full-colour hologram image. Our findings open up possibilities for high-resolution and high-fidelity optical security devices as well as advanced cryptographic approaches.

Object Detection Using Color Entropies and a Fuzzy Classifier

This paper proposes a novel approach to specific object detection in complex scenes using color-based entropy features and a fuzzy classifier (FC). Appearances of the detected objects are assumed to contain multiple colors in non-homogeneous distributions that make it difficult to detect these objects using shape features. The proposed detection approach consists of two filtering phases with two different novel color-based entropy features. The first phase filters a test pattern with the entropy of color component (ECC). A self-splitting clustering (SSC) algorithm is proposed to automatically generate clusters in the hue and saturation (HS) color space according to the composing pixels of an object. The ECC value is computed from histograms of pixels in the found clusters and is used to generate object candidates. The second filtering phase uses the entropies of geometric color distributions (EGCD) to filter the object candidates obtained from the first phase. An EGCD is computed for each of the clustered composing colors of a candidate object. The EGCD values are fed to an FC to enable advanced filtering. A new FC using the SSC algorithm and support vector machine (FC-SSCSVM) for antecedent and consequent parameter learning, respectively, is proposed to improve detection performance. Experimental results on the detection of different objects and comparisons with various detection approaches and classifiers verify the advantage of the proposed detection approach using the FC-SSCSVM.

A novel color detection method based on HSL color space for robotic soccer competition

In a robotic soccer competition, the locations of the ball and the robot are recognized through the vision system in a strong dynamic environment; therefore, the robot and the computer need to identify the object in real-time and accurately through the vision system. Due to the influence of the game ball under different brightnesses, the color clusters of glossy materials will produce a nonlinear behavior and will cause difficulty of recognition. Thus, we propose a novel color detection method based on hue, saturation, and lightness (HSL) color space in this paper. Firstly, by utilizing the hue histogram, the hue and saturation (HS) plane and the hue and lightness (HL) plane can be obtained respectively. In addition, based on the obtained information from two planes, the databases can be built for decreasing the running-time and increasing the recognition success rate of identifying object. Moreover, a novel algorithm is presented for the game ball in the robotic soccer competition. Finally, some examples under different brightnesses are illustrated to demonstrate the preciseness and the accuracy of the proposed method are better than the traditional method.

Object detection by color histogram-based fuzzy classifier with support vector learning

A new method for specific object detection in two-dimensional color images is proposed in this paper. The proposed method uses color histograms of an object on the hue and saturation (HS) color space as detection features. To represent color information by histograms as accurately as possible, a non-uniform partition of HS space is proposed. The whole detection process consists of three stages. In the first stage, the input image is repeatedly sub-sampled by a factor, resulting in a pyramid of images. Scanning on all of the scaled images with a pre-defined window size is performed, where histograms of each window are fed as inputs to a fuzzy classifier. The fuzzy classifier used is a self-organizing Takagi–Sugeno (TS)-type fuzzy network with support vector learning (SOTFN-SV). SOTFN-SV is a fuzzy system constituted by TS-type fuzzy if–then rules. It is constructed by the hybridization of fuzzy clustering and support vector machine. Many candidate objects are detected in this stage. In the second stage, a splitting K-means clustering method is proposed and applied to the detections from Stage 1 so that detections with nearby positions are grouped into the same cluster. The number of clusters is generated automatically by the clustering method according to cluster variances. Final object position is determined from the clusters. In the final stage, size of a detected object is determined. To verify performance of the proposed method, experiments on five specific object detections are conducted and comparisons with different types of detectors are made.

Using self-organizing fuzzy network with support vector learning for face detection in color images

This paper proposes a three-stage face detection method using self-organizing Takagi–Sugeno (T–S)-type fuzzy network with support vector (SOTFN-SV) learning. SOTFN-SV is a T–S-type fuzzy system constructed by hybridizing fuzzy clustering and support vector machine. The proposed face detection method consists of three stages. In the first stage, SOTFN-SV is applied to skin color segmentation. Color information from the hue and saturation (HS) color space is used. In the second stage, face size and shape filters are employed to exclude some face candidates to reduce the number of false alarms. Shape analysis is based on the fact that an oval face shape can be approximated by an elliptical shape, and a best fitting ellipse to each connected skin region is found for analysis. In the final stage, colors of the eyes, mouth, and face skin regions of the remaining face candidates are used as detection features. An SOTFN-SV color filter uses these features as inputs to make a final detection decision. The proposed method has a fast detection speed and detects not only the face, but also its size and orientation. Experimental results verify the efficiency and effectiveness of the proposed face detection method.

A Self-Organizing TS-Type Fuzzy Network With Support Vector Learning and its Application to Classification Problems

A self-organizing Takagi-Sugeno (TS)-type fuzzy network with support vector learning (SOTFN-SV) is proposed in this paper. The proposed SOTFN-SV is inspired by analysis of TS-type fuzzy systems and composite-kernel support vector machine (SVM). SOTFN-SV is a fuzzy system constructed by the hybridization of fuzzy clustering and SVM. The antecedent part of SOTFN-SV is generated via fuzzy clustering of the input data, and then SVM is used to tune the consequent part parameters to give the network better generalization performance. For demonstration, SOTFN-SV is applied to several classification problems, especially the skin color classification problem. In the skin color classification application, each color pixel is represented by hue and saturation (HS) color space. To represent color information by histogram as accurately as possible, a nonuniform partition of HS space is proposed. For comparison, SVMs and other fuzzy systems trained by SVM or neural networks are applied to the same classification problems. The advantages of SOTFN-SV are verified by comparisons with the results of these methods.

Pizza sauce spread classification using colour vision and support vector machines

An automated classification system of pizza sauce spread using colour vision and support vector machine (SVM) was developed. To characterise pizza sauce spread with low dimensional colour features, a sequence of image processing algorithms was developed. After image segmentation from the background, the segmented image was transformed from red, green, and blue (RGB) colour space to hue, saturation, and value (HSV) colour space. Then a vector quantifier was designed to quantify the HS (hue and saturation) space to 256-dimension, and the quantified colour features of pizza sauce spread were represented by colour histogram. Finally, principal component analysis (PCA) was applied to reduce the 256-dimensional vectors to 30-dimensional vectors. With the 30-dimensional vectors as the input, SVM classifiers were used for classification of pizza sauce spread. It was found that the polynomial SVM classifiers resulted in the best classification accuracy with 96.67% on the test experiments.