Color Space Conversion Research Articles

Principal Component Analysis-Based Visual Saliency Detection

In this paper, a novel patch-wise saliency detection algorithm is proposed based on principal component analysis (PCA). As a powerful statistical procedure in data analysis, PCA is fully exploited to convert color space and produce compact patch representation. Specifically, images are first converted to linearly uncorrelated channels and divided into non-overlapped patches. Then the patches are represented by the coefficients of principal components using PCA analysis. Based on the compact representation of patches, two types of distinctiveness are introduced: 1) center-surround contrast and 2) global rarity. Experimental results demonstrate that the PCA-based color space conversion and patch representation can improve the accuracy of human fixations prediction. And the proposed algorithm outperforms the mainstream algorithms on predicting human fixations. Additional experiments on salient object detection and image retargeting show that the proposed model can achieve better performance than traditional models.

Fuzzy and Neural Network based Tomato Plant Disease Classification using Natural Outdoor Images

Objectives: The aim of the study is to automate the plant disease recognition and classification process by using image processing and soft computing techniques. Methods/Analysis: The proposed method examined the five types of tomato plant diseases using natural outdoor images in the study. The tomato plant images categorized into six categories including five disease infected that are bacterial leaf spot, fungal septoria leaf spot, bacterial canker, fungal lateblight, tomato leaf curl and one non-infected (healthy). The total 180 images of the dataset used for training and testing purpose. The total thirteen features computed by using CIE XYZ color space conversions that included color moments, histogram, and color coherence vector features. For classification, computed features are fed into three classifiers, i.e., “Fuzzy Inference System based on subtractive clustering”, “Adaptive neuro-fuzzy inference system using hybrid learning algorithm and multi-layer feed forward back propagation neural network” for classification of six injured and healthy tomato plant disease. Finding: The classification accuracy is best yielded with multi-layer feed forward back propagation classifier of 87.2%. Novelty/Improvement: Usually, in the studies the only one type of plant disease considered for the recognition and classification purpose. The current study considered five different types of tomato plant diseases including fungal, bacterial and viral. It indicates that the proposed algorithm could reliably classify the different types of plant diseases in digital images.

An adaptive cartoon-like stylization for color video in real time

The cartoon-like stylization of color video images is one of the major types of non-photorealistic rendering. It has broad applications in the entertainment industry due to its lively style, flexible form, and autonomous creation. Our video cartoonization framework consists of color space conversion, bilateral filtering, color quantization and edge detection. We use an adaptive difference of Gaussians filter to detect the edges– variance value of Gaussian filter is determined based on the gradient of each pixels, so that we can not only detect elaborate edges but also decrease the influence of noise. We also alter the target sharpness range in the color quantization to achieve a softer look. We implement two versions of our algorithm: serial on a CPU, and parallel on a GPU having the Computer Unified Device Architecture (CUDA). Only the CUDA GPU code is able to process video in real time, running 45 to 180 times faster than the CPU code.

Hardware image assessment for wireless endoscopy capsules.

Wireless capsule endoscopy is a new technology in the realm of telemedicine that has many advantages over the traditional endoscopy systems. Transmitted images should help diagnosis of diseases of the gastrointestinal tract. Two important technical challenges for the manufacturers of these capsules are power consumption and size of the circuitry. Also, the system must be fast enough for real-time processing of image or video data. To solve this problem, many hardware designs have been proposed for implementation of the image processing unit. In this paper we propose an architecture that could be used for the assessment of endoscopy images. The assessment allows avoidance of transmission of medically useless images. Hence, volume of data is reduced for more efficient transmission of images by the endoscopy capsule. This is done by color space conversion and moment calculation of images captured by the capsule. The inputs of the proposed architecture are RGB image frames and the outputs are images with converted colors and calculated image moments. Experimental results indicate that the proposed architecture has low complexity and is appropriate for a real-time application.

A Gamut-Mapping Framework for Color-Accurate Reproduction of HDR Images.

Few tone mapping operators (TMOs) take color management into consideration, limiting compression to luminance values only. This could lead to changes in image chroma and hues, which are typically managed with a post-processing step. However, current post-processing techniques for tone reproduction do not explicitly consider the target display gamut. Gamut mapping, on the other hand, deals with mapping images from one color gamut to another, usually smaller, gamut but has traditionally focused on smaller scale, chromatic changes. The authors present a combined gamut- and tone-management framework for color-accurate reproduction of high dynamic range images that can prevent hue and luminance shifts while taking gamut boundaries into consideration. Their approach is conceptually and computationally simple, parameter-free, and compatible with existing TMOs.

Robust Approach for Disparity Map Estimation Based on Multilevel Decomposition

A novel approach for dense disparity map (DM) estimation is designed. The proposed frameworks include together processing of stereo pairs using the following blocks: CIEL*a*b* color space conversion, stereo matching via multilevel scheme, employing Normalized Cross-Correlation or Structural Similarity Index Measure, color segmentation by k-means on a*b* color plane, and adaptive post-filtering. The Bad Matching Pixels and Structural Similarity Index Measure criteria are applied in order to compare the performance of the proposed approach against state-of-the-art techniques. Two designed frameworks appear outperform existing state-of-the-art techniques in terms of objective criteria as well as in subjective visual perception.

Color computer-generated hologram generation using the random phase-free method and color space conversion.

We propose two calculation methods of generating color computer-generated holograms (CGHs) with the random phase-free method and color space conversion in order to improve the image quality and accelerate the calculation. The random phase-free method improves the image quality in monochrome CGH, but it is not performed in color CGH. We first aimed to improve the image quality of color CGH using the random phase-free method and then to accelerate the color CGH generation with a combination of the random phase-free method and color space conversion method, which accelerates the color CGH calculation due to down-sampling of the color components converted by color space conversion. To overcome the problem of image quality degradation that occurs due to the down-sampling of random phases, the combination of the random phase-free method and color space conversion method improves the quality of reconstructed images and accelerates the color CGH calculation. We demonstrated the effectiveness of the proposed method in simulation, and in this paper discuss its application to lensless zoomable holographic projection.

Color transfer method preserving perceived lightness

Color transfer originally proposed by Reinhard et al. is a method to change the color appearance of an input image by using the color information of a reference image. The purpose of this study is to modify color transfer so that it works well even when the scenes of the input and reference images are not similar. Concretely, a color transfer method with lightness correction and color gamut adjustment is proposed. The lightness correction is applied to preserve the perceived lightness which is explained by the Helmholtz–Kohlrausch (H–K) effect. This effect is the phenomenon that vivid colors are perceived as brighter than dull colors with the same lightness. Hence, when the chroma is changed by image processing, the perceived lightness is also changed even if the physical lightness is preserved after the image processing. In the proposed method, by considering the H–K effect, color transfer that preserves the perceived lightness after processing is realized. Furthermore, color gamut adjustment is introduced to address the color gamut problem, which is caused by color space conversion. The effectiveness of the proposed method is verified by performing some experiments.

Agricultural products recognition system using taxonomist's knowledge as semantic attributes

Support Vector Machine (SVM) was used to classify type of produce commonly sold in supermarkets. We applied a sequence of image processing algorithms such as conversion of color space, thresholding and morphological operation to obtain the region of interest from the images. Global and local features were extracted from the images and used as input for the classifiers. The color and texture features extracted in this system were L*a*b* values and texton approach respectively. Since attribute learning has emerged as a promising paradigm for assisting in object recognition, we proposed to integrate it into our system. This could tackle problem occurred when less training data are available, i.e. less than 20 samples per class. The performances of the proposed classifier and conventional SVM were also compared. The experiments showed that the classification accuracy of the proposed classifier is higher than conventional SVM by 7% when only 4 samples per class were trained.

Real-time implementation of various colour space models

The colour space translation plays a significant task in pre-processing stage of digital image processing. Colour conversion can improve the quality of images. The objective is to convert one colour space to another and the inverse of same. Various colour space conversions are used such as RGB ← → HSV, RGB ← → HSL, RGB ← → HSI, RGB ← → YUV and RGB ← → YCbCr. The conversion process can be done using colour space conversion algorithm. The colour space conversion is used in various applications such as commercial, multimedia, computer vision, visual tracking systems etc. The hardware realisation of colour space conversion models can be implemented by using Xilinx system generator on field programmable gate array spartan-6. Finally, the above colour space conversion models are implemented in real-time then tabulated in terms of percentage resources utilisation and power required. The recommended RGB ← → HSV colour space conversion utilises 21% of DSP48A1s chips and required 0.354 watts of power. By means of colour conversion, the efficiency and speed are increased.

一种低面积低功耗RGB到YCbCr色彩空间转换电路实现方法

本文提出了一种低面积低功耗RGB与YCbCr色彩空间转换的电路实现方法。首先提出一种结合简化加法器图(Reduced Adder Graph, RAG)的公共子表达式消除(Common Subexpression Elimination, CSE)的电路实现，然后提出一个提高精度的补偿方法。最后采用TSMC 0.18um工艺对所提出的算法进行综合和布局布线。仿真和综合结果表明相比于传统的正则有符号数字(Canonic Signed Digit, CSD)编码系统，采用本文提出的结合CSE和RAG的RGB到YCbCr空间转换电路实现方法面积和功耗减小了20%，补偿算法提高了系统精度。 This paper presents a low-area and low-power circuit implementation of high-precision color space conversion from RGB to YCbCr. Firstly, an efficient circuit implementation combining com-mon-subexpression-elimination (CSE) with reduced-adder-graph (RAG) is presented. Secondly, a compensation method is proposed to enhance the precision. Finally, the synthesized results of a TSMC 0.18 um standard cell library are given. By using the proposed circuit implementation of color space conversion from RGB to YCbCr combining CSE and RAG without compensation, the results show that the area and power are reduced by about 20% than the traditional Canonic Signed Digital (CSD) method. With the compensation algorithm, the precision is much higher.

Methods of Hematoxylin and Erosin Image Information Acquisition and Optimization in Confocal Microscopy

ObjectivesWe produced hematoxylin and eosin (H&E) staining-like color images by using confocal laser scanning microscopy (CLSM), which can obtain the same or more information in comparison to conventional tissue staining.MethodsWe improved images by using several image converting techniques, including morphological methods, color space conversion methods, and segmentation methods.ResultsAn image obtained after image processing showed coloring very similar to that in images produced by H&E staining, and it is advantageous to conduct analysis through fluorescent dye imaging and microscopy rather than analysis based on single microscopic imaging.ConclusionsThe colors used in CLSM are different from those seen in H&E staining, which is the method most widely used for pathologic diagnosis and is familiar to pathologists. Computer technology can facilitate the conversion of images by CLSM to be very similar to H&E staining images. We believe that the technique used in this study has great potential for application in clinical tissue analysis.

Clustering Detection Algorithm of Plant Leaf Relative Lesion Area Based on Improved GA

AbstractIn order to overcome the defects of traditional methods on measuring plant leaf diseases and achieve accurate detection of blade relative lesion area, clustering algorithm and the improved clustering algorithm are used to calculate the leaf relative lesion area with the knowledge of computer graphics technology. First, preprocess the image selectively by the image correction, color space conversion technology and so on, use the clustering algorithm to divide the target area. Finally calculate relative lesion area according to the partition determined by objective function. This paper proposed an improved genetic algorithm to improve the limitation problem of selecting the clustering algorithm initial value and enhance the searching capability and the robustness of the original algorithm by improving genetic operator of genetic algorithm. Considering the accuracy of image processing as the quota, the results show that the algorithm in this paper makes the lesion area calculated by the clustering ce...

A MEC-BP-Adaboost neural network-based color correction algorithm for color image acquisition equipments

Color correction algorithm based on color space conversion is an essential part in color management system. Subject to the variation in conditions such as the limitations on imaging-forming principle, device performances and machining controls, the captured images usually contain certain color distortion compared to the actual images. Therefore, the paper proposes a mind evolutionary computation (MEC)-back propagation (BP)-adaboost algorithm (Adaboost) neural network-based color correction algorithm for color image collecting equipment. MEC-BP-Adaboost is utilized in training process to establish the color mapping model, with the captured samples of the color-targets under the color image acquisition equipments as input data and the standard color data as output data. MEC-BP-Adaboost neural network-based color correction algorithm not only can further the correction accuracy, but also can solve the problem that the color correction models obtained by using the neural network methods are not unique, and the difference among that color correction models is very big. Experimental results demonstrate that the proposed method achieves much better correction performance than the polynomial regression model, the conventional BP neural network, and the genetic algorithm (GA)-BP neural network.

An Efficient Sparse Code Fusion Method for Image Enhancement

Image enhancement can improve the perception of information for human viewers, which is also a basic and pretty significant role in image processing. However, there also exist some limitations in most image enhancement algorithms. In this paper discuss the limitations of existing techniques of image enhancement. In order to solve the limitations well, a novel sparse code fusion (SCF) method is proposed, in which combine piecewise dictionaries strategy. The proposed method firstly is that color space conversion from RGB to Ycbcr color space, secondly enhanced Y component using piecewise sparse code fusion strategy, finally color image reconstruction. Experimental results show that our method can obtain more appealing perceptual quality than the state-of-the-art usual algorithms.

색 공간 내 중복 정보 감소를 위한 HEVC 스크린 콘텐츠 부호화 기법 성능 분석

최근 동영상 압축에 관한 국제 표준화 기구인 JCT-VC (Joint Collaborative Team on Video Coding) 에서는 High Efficiency Video Coding (HEVC)의 확장 표준으로 HEVC/Range Extension (HEVC/RExt)의 개발을 완료하고 스크린 콘텐츠 동영상의 부호화기술을 위한 표준인 HEVC/Screen Content Coding (HEVC/SCC)을 제정 중이다. 기존 동영상 압축 과정에서는 이미지 센서로부터 취득한 RGB 영상을 변환하여 부호화를 수행하는 반면에 애니매이션, 그래픽스 등 컴퓨터로 합성한 영상을 일컫는 스크린 콘텐츠의 경우는 색 공간의 변환이 주관적 화질을 심각하게 열화 시킬 수 있으므로 기존 RGB 색 공간을 유지하며 효율적으로 색 공간 내 정보의 중복성을 줄이기 위한 부호화 기법이 필요하다. 본 논문에서는 HEVC/RExt.와 HEVC/SCC에서 개발한 스크린 콘텐츠 동영상 압축을 위한 색 요소 예측 기법과 루프 내 색 공간 변환 기술의 성능을 분석한다. 실험 결과에 의하면 색 요소 예측 기법은 평균 약 11.7% BD-rate 감소, 색 공간 예측 기법은 평균 약 16.4% BD-rate 감소를 보인다. 그러나 두 기법이 동시에 적용되는 경우 약 18.2%의 BD-rate 감소를 보여 두 기법의 부호화 효율이 약 9.9% 중첩된다. 본 결과를 응용하여 두 기법이 배타적으로 선택이 되게끔 부호기 고속화를 수행하는 경우 약 0.3%의 부호화 손실로 93%의 부호화 측정 시간을 제공한다. JCT-VC (Joint Collaborative Team on Video Coding) continues developing HEVC/Screen Content Coding (HEVC/SCC) as an extension for efficiently coding screen content videos, including computer animations, graphics, and electrical documents, based on HEVC/Range extension (HEVC/RExt.). Color space conversion from RGB space being captured from CCD sensors is popular in natural video coding. However, the conversion is often undesired for screen contents because of a significant loss in perceptual quality. Therefore, several coding tools including cross-component prediction (CCP) and in-loop adaptive color space transform (ACST) have been developed for an efficient screen content video coding in order to reduce the redundancies between color spaces while maintaining the original color space. In this paper, we review the two coding tools, i.e., CCP and ACST exploiting the correlation in the RGB color space and conduct the performance analysis of the coding tools. In our simulation results, CCP and ACST provide 11.7% BD-rate saving and 16.4% BD-rate saving, respectively, while the two coding tools provide 18.2% BD-rate saving in total. Following this idea, if the two coding tools are exclusively selected, we provide 93% encoding measurement time with a 0.3% coding loss.

Segmentation of White Blood Cells through Nucleus Mark Watershed Operations and Mean Shift Clustering.

This paper presents a novel method for segmentation of white blood cells (WBCs) in peripheral blood and bone marrow images under different lights through mean shift clustering, color space conversion and nucleus mark watershed operation (NMWO). The proposed method focuses on obtaining seed points. First, color space transformation and image enhancement techniques are used to obtain nucleus groups as inside seeds. Second, mean shift clustering, selection of the C channel component in the CMYK model, and illumination intensity adjustment are employed to acquire WBCs as outside seeds. Third, the seeds and NMWO are employed to precisely determine WBCs and solve the cell adhesion problem. Morphological operations are further used to improve segmentation accuracy. Experimental results demonstrate that the algorithm exhibits higher segmentation accuracy and robustness compared with traditional methods.

Automatic segmentation of blood vessels from retinal fundus images through image processing and data mining techniques

Machine Learning techniques have been useful in almost every field of concern. Data Mining, a branch of Machine Learning is one of the most extensively used techniques. The ever-increasing demands in the field of medicine are being addressed by computational approaches in which Big Data analysis, image processing and data mining are on top priority. These techniques have been exploited in the domain of ophthalmology for better retinal fundus image analysis. Blood vessels, one of the most significant retinal anatomical structures are analysed for diagnosis of many diseases like retinopathy, occlusion and many other vision threatening diseases. Vessel segmentation can also be a pre-processing step for segmentation of other retinal structures like optic disc, fovea, microneurysms, etc. In this paper, blood vessel segmentation is attempted through image processing and data mining techniques. The retinal blood vessels were segmented through color space conversion and color channel extraction, image pre-processing, Gabor filtering, image post-processing, feature construction through application of principal component analysis, k-means clustering and first level classification using Naïve–Bayes classification algorithm and second level classification using C4.5 enhanced with bagging techniques. Association of every pixel against the feature vector necessitates Big Data analysis. The proposed methodology was evaluated on a publicly available database, STARE. The results reported 95.05% accuracy on entire dataset; however the accuracy was 95.20% on normal images and 94.89% on pathological images. A comparison of these results with the existing methodologies is also reported. This methodology can help ophthalmologists in better and faster analysis and hence early treatment to the patients.

Designing FIRA Medium-Sized Soccer Robot Vision System Using Particle Swarm Optimization

Enabling FIRA medium-sized soccer robots to recognize target objects according to color information requires that competing teams manually set the range of colors according to ambient lighting conditions prior to games. This color information is used to differentiate features of target objects, such as the ball, the goals, and the field. Constructing a color-feature model such as this is extremely time-consuming and the resulting model is unable to adapt dynamically to changes in lighting conditions. This study applied a look-up table method to execute RGB-HSV color space conversion to accelerate video processing. A particle swarm optimization (PSO) scheme was developed to detect the color-feature parameters of the target objects in the HSV color space. This enables the automatic completion of color-feature modeling and the construction of the knowledge model required by the robot for object recognition. Experiment results demonstrate that the proposed method is capable of enhancing the robustness of the robot vision system in determining changes in lighting conditions. In addition, the manpower and time required to set robot parameters prior to games were reduced significantly.

Robust image hashing with embedding vector variance of LLE

Locally linear embedding (LLE) has been widely used in data processing, such as data clustering, video identification and face recognition, but its application in image hashing is still limited. In this work, we investigate the use of LLE in image hashing and find that embedding vector variances of LLE are approximately linearly changed by content-preserving operations. Based on this observation, we propose a novel LLE-based image hashing. Specifically, an input image is firstly mapped to a normalized matrix by bilinear interpolation, color space conversion, block mean extraction, and Gaussian low-pass filtering. The normalized matrix is then exploited to construct a secondary image. Finally, LLE is applied to the secondary image and the embedding vector variances of LLE are used to form image hash. Hash similarity is determined by correlation coefficient. Many experiments are conducted to validate our efficiency and the results illustrate that our hashing is robust to content-preserving operations and reaches a good discrimination. Comparisons of receiver operating characteristics (ROC) curve indicate that our hashing outperforms some notable hashing algorithms in classification between robustness and discrimination.