Color Space Conversion Research Articles

Real-time License plate number detection based on image contour

The license plate number detection technology is an application of computer video image recognition technology in vehicle license plate recognition. In this paper, an image processing technology is used to extract and detect a license plate in motion from a complex background to a license plate recognition system. The method in this paper is mainly divided into four steps. First, the original image is preprocessed, the color image is converted into a grayscale image, and the gradient edge features are extracted by Sobel operator. Secondly, after the image is binarized, the image generated through the morphological operation of the image to highlight the image outline. Then detect the contour of the entire image and label the contour. Finally, the RGB space is converted into the HSV color space through color space conversion, and the color of the license plate is used to find the area where the license plate is located in the image.

An Acquisition Method for Visible and Near Infrared Images from Single CMYG Color Filter Array-Based Sensor.

Near-infrared (NIR) images are very useful in many image processing applications, including banknote recognition, vein detection, and surveillance, to name a few. To acquire the NIR image together with visible range signals, an imaging device should be able to simultaneously capture NIR and visible range images. An implementation of such a system having separate sensors for NIR and visible light has practical shortcomings due to its size and hardware cost. To overcome this, a single sensor-based acquisition method is investigated in this paper. The proposed imaging system is equipped with a conventional color filter array of cyan, magenta, yellow, and green, and achieves signal separation by applying a proposed separation matrix which is derived by mathematical modeling of the signal acquisition structure. The elements of the separation matrix are calculated through color space conversion and experimental data. Subsequently, an additional denoising process is implemented to enhance the quality of the separated images. Experimental results show that the proposed method successfully separates the acquired mixed image of visible and near-infrared signals into individual red, green, and blue (RGB) and NIR images. The separation performance of the proposed method is compared to that of related work in terms of the average peak-signal-to-noise-ratio (PSNR) and color distance. The proposed method attains average PSNR value of 37.04 and 33.29 dB, respectively for the separated RGB and NIR images, which is respectively 6.72 and 2.55 dB higher than the work used for comparison.

Study on visual positioning and evaluation of automatic evisceration system of chicken

Automatic evisceration is a very important production technology in the chicken industry. In this study, an automatic chicken eviscerating robot system was developed and evaluated based on machine vision for locating the chicken carcasses and anal incision. This system consisted of chicken carcass conveying device, robotic manipulator, end-effector, control system and machine vision system. Based on machine vision, this system employed color space conversion, threshold segmentation, morphological operation method and active contour algorithm to obtain the chicken carcass images of the removed wings and legs. Subsequently, anal incision contour was extracted and its position was detected by the maximum inscribed circle algorithm. All the algorithms were implemented in the system for recognizing the individual carcass and automatically locating the targets of different sizes, which guided the manipulator to complete the evisceration. Present results indicated that the maximum location deviation of contour centroid of chicken carcass and anal incision was 5 and 4 pixels, respectively, while the average time of image processing was 954 ms. Then the eviscerating manipulator could accurately grasp the viscera, the residual rate and the breakage rate of viscera were 6.2% and 15%, respectively. The high accuracy obtained from the evaluation results shows that the machine vision system can be applied successfully to robotic evisceration in the processing of chicken. Hence, the development of the method for the eviscerating robot is necessary and significant, in particular for providing great foundation for robotic evisceration in poultry industry.

OBJECTS DETECTION FROM AN IMAGE USING MATLAB

Objects detection from a cluttered scene is one of the main tasks in computer vision. A lot of research has focused on the optimization of this process by using machine learning, where creating algorithms with specific instructions for solving a problem is not applicable. Most of embedded systems for detection object are based on algorithms using monochrome (intensity) images. Therefore, in the article are created models for color space conversion from images and the main stages of the object detection algorithm are discussed, as well as the functions through which this is done in MATLAB.

A Canny operator road edge detection method based on color features

The road edge detection method, proposed by us, highlights the morphological and color features of the road in the image. The method performs color space conversion and color feature screening on color images containing road information, and Canny operator is used for edge detection. Then the edge detection results are detected by straight lines, and the road edges are detected and marked based on the principle of Hough transform. The experiment of edge detection on road pictures with complex background proves that the detection method can better detect the road edge. The novelty of this method is to combine several principles such as color feature screening, Canny operator and Hough transform. Therefore, a new method of road edge detection is formed.

Detection and enumeration of wheat grains based on a deep learning method under various scenarios and scales

Grain number is crucial for analysis of yield components and assessment of effects of cultivation measures. The grain number per spike and thousand-grain weight can be measured by counting grains manually, but it is time-consuming, tedious and error-prone. Previous image processing algorithms cannot work well with different backgrounds and different sizes. This study used deep learning methods to resolve the limitations of traditional image processing algorithms. Wheat grain image datasets were collected in the scenarios of three varieties, six background and two image acquisition devices with different heights, angles and grain numbers, 1 748 images in total. All images were processed through color space conversion, image flipping and rotation. The grain was manually annotated, and the datasets were divided into training set, validation set and test set. We used the TensorFlow framework to construct the Faster Region-based Convolutional Neural Network Model. Using the transfer learning method, we optimized the wheat grain detection and enumeration model. The total loss of the model was less than 0.5 and the mean average precision was 0.91. Compared with previous grain counting algorithms, the grain counting error rate of this model was less than 3% and the running time was less than 2 s. The model can be effectively applied under a variety of backgrounds, image sizes, grain sizes, shooting angles, and shooting heights, as well as different levels of grain crowding. It constitutes an effective detection and enumeration tool for wheat grain. This study provides a reference for further grain testing and enumeration applications.

Segmentation of thermal infrared images of cucumber leaves using K-means clustering for estimating leaf wetness duration

Leaf wetness duration (LWD) is a critical parameter used to predict plant disease, but its determination under actual field conditions is a major challenge. In this study, a method for determining LWD using thermal infrared imaging was developed and applied to cucumber plants grown in a solar greenhouse. Thermal images of the plant leaves were captured using an infrared scanning camera, and a leaf wetness area segmentation method consisting of two procedures was applied. First, a color space conversion was performed automatically by an image-processing algorithm. Then, the K-means clustering algorithm was applied to enable the segmentation of the wetness area on the thermal image. Subsequently, to enable overall thermal image analysis, an initial leaf wetness threshold (LWT) of 5% was defined (where wetness values higher than 5% indicated that the leaf was in a wet state). The results of comparative experiments conducted using thermal images of plant leaves captured using an infrared scanning camera and human visual observation indicated that the estimated LWD values were generally higher than the observed LWD values, because slight leaf wetness condensations were overlooked by the human eye but detected by the infrared scanning camera. While these differences were not found to be statistically significant in this study, the proposed method for determining LWD using thermal infrared imaging may provide a new LWD detection method for cucumber and other plants grown in solar greenhouses. Keywords: thermal imaging, K-means clustering algorithm, leaf wetness duration, cucumber DOI: 10.25165/j.ijabe.20201303.4301 Citation: Wen D M, Ren A X, Ji T, Flores-Parra I M, Yang X T, Li M. Segmentation of thermal infrared images of cucumber leaves using K-means clustering for estimating leaf wetness duration. Int J Agric & Biol Eng, 2020; 13(3): 161–167.

Recognition of garlic clove orientation based on machine vision

To address the problem of low garlic clove-head-turning rates in mechanized sowing of garlic, this study proposes an algorithm for identifying garlic clove orientation using machine vision. First, the algorithm performs preprocessing operations such as image enhancement and color space conversion; then, it identifies and labels the garlic clove regions by determining the connected regions. Each garlic clove region is derived for independent analysis, and three garlic clove features of each clove are calculated. Then, based on the distinctiveness of each feature parameter with clove recognition, comprehensive feature parameters are obtained by fusing the information of the three feature parameters. Finally, garlic clove head is identified on the basis of these comprehensive feature parameters. Furthermore, two garlic varieties, ‘Cangshan’ and ‘Jinxiang’ garlic, are tested by capturing images of both single and multiple garlic cloves. The experimental results indicate that the average recognition rate of the algorithm is 97.44%, and the average running time is 0.61 s. The correct recognition rate of ‘Jinxiang’ garlic is 94.51%, while that of ‘Cangshan’ garlic is 100%. In summary, the algorithm has strong adaptability and high accuracy, and it can provide a useful reference for an intelligent garlic clove-head-turning mechanism for garlic planters.

Selective Image Encryption Based on DCT, Hybrid Shift Coding and Randomly Generated Secret Key

Most of today’s techniques encrypt all of the image data, which consumes a tremendous amount of time and computational payload. This work introduces a selective image encryption technique that encrypts predetermined bulks of the original image data in order to reduce the encryption/decryption time and thecomputational complexity of processing the huge image data. This technique is applying a compression algorithm based on Discrete Cosine Transform (DCT). Two approaches are implemented based on color space conversion as a preprocessing for the compression phases YCbCr and RGB, where the resultant compressed sequence is selectively encrypted using randomly generated combined secret key.The results showed a significant reduction in image quality degradation when applying the system based on YCbCr over RGB, where the compression ratio was raised in some of the tested images to 50% for the same Peak Signal to Noise Ratio (PSNR). The usage of 1-D DCT reduced the transform time by 47:1 times comparedto the same transform using 2-D DCT. The values of the adaptive scalar quantization parameters were reduced to the half for the luminance (Y band) to preserve the visual quality, while the chrominance (Cb and Cr bands) were quantized by the predetermined quantization parameters. In the hybrid encoder horizontal zigzag,block scanning was applied to scan the image. The Detailed Coefficient (DC) coefficients are highly correlated in this arrangement- where DC are losslessly compressed by Differential Pulse Coding Modulation (DPCM) and theAccumulative Coefficients (AC) are compressed using Run Length Encoding (RLE). As a consequence, for the compression algorithm, the compression gain obtained was up to 95%. Three arrays are resulted from each band (DC coefficients, AC values, and AC runs), where the cipher is applied to some or all of those bulksselectively. This reduces the encryption decryption time significantly, where encrypting the DC coefficients provided the second best randomness and the least encryption/decryption time recorded (3 10-3 sec.) for the entire image. Although the compression algorithm consumes time but it is more efficient than the savedencryption time.

Correlation between clinical risk factors and tracheal intubation difficulty in infants with Pierre-Robin syndrome: a retrospective study

BackgroundDifficult tracheal intubation is a common problem encountered by anesthesiologists in the clinic. This study was conducted to assess the difficulty of tracheal intubation in infants with Pierre Robin syndrome (PRS) by incorporating computed tomography (CT) to guide airway management for anesthesia.MethodsIn this retrospective study, we analyzed case-level clinical data and CT images of 96 infants with PRS. First, a clinically experienced physician labeled CT images, after which the color space conversion, binarization, contour acquisition, and area calculation processing were performed on the annotated files. Finally, the correlation coefficient between the seven clinical factors and tracheal intubation difficulty, as well as the differences in each risk factor under tracheal intubation difficulty were calculated.ResultsThe absolute value of the correlation coefficient between the throat area and tracheal intubation difficulty was 0.54; the observed difference was statistically significant. Body surface area, weight, and gender also showed significant difference under tracheal intubation difficulty.ConclusionsThere is a significant correlation between throat area and tracheal intubation difficulty in infants with PRS. Body surface area, weight and gender may have an impact on tracheal intubation difficulty in infants with PRS.

An Analysis of Imperceptibility and Robustness Performance in CRT Image Watermarking based on Color Space Theory

Color images have more information and more storage space than gray images. The process of computing color images is also more complex compared to gray images. Nevertheless, human vision is more sensitive to color images compared to gray images, so color image processing is so important. Image watermarking is a method of copyright protection by embedding copyrights in the image. The embedding process can cause changes in the pixel value of the image, so it needs to be analyzed and measured the quality of watermarked images both visually or imperceptibility and watermark durability. In general, color images use the RGB color space model and color space conversion is not done when embedding watermarking. But several studies have suggested converting RGB color space to YCbCr color space for a specific purpose. This research proposes to analyze the robustness and imperceptibility performance in the R, G, B and Y color spaces in the CRT method. CRT is one of the methods of image watermarking in the spatial domain, where this method was previously also used as a cryptographic algorithm. So that the CRT method excels in durability and security watermarks. Based on the results of testing with the CRT method, the color space R has an advantage in the aspect of imperceptibility compared to other color spaces, the difference is very thin with the G and B color spaces, but when compared with the Y color space the difference reaches 3dB based on the PSNR calculation. But for testing the robustness of the color space Y is far superior compared to other color spaces even though extraction without attack, not all watermarks can be extracted perfectly.

Framework for Color and Texture Feature Fusion in Content Based Image Retrieval using Block Truncation Coding with Color Spaces

With tremendous growth in social media and digital technologies, generation, storing and transfer of huge amount of information over the internet is on the rise. Images or visual mode of communication have been prevailing and widely accepted as a mode of communication since ages. And with the growth of internet, the rate at which images are generated is growing exponentially. But the methods used to retrieve images are still very slow and inefficient, compared to the rate of increase in image databases. To cope up with this explosive increase in images, this information age has seen huge research advancement in Content Based Image Retrieval (CBIR). CBIR systems provide a way of utilizing the 3 major ways in which content is portrayed in images, those are shape, texture and color. In CBIR system, features are extracted from query image and similarity is found with features stored in database for retrieval. This provides an objective way of image retrieval, which is more efficient compared to subjective human annotation. Application specific CBIR systems have been developed and perform really well, but Generic CBIR systems are still under developed. Block Truncation Coding (BTC) has been chosen as a feature extractor. BTC applied directly on input image provides color content-based features of image and BTC applied after applying LBP on the image provide texture content-based features of image. Previous work consists of either color, shape or texture, but usage of more than one descriptor is still in research and might give better performance. The paper presents framework for color and texture feature fusion in content-based image retrieval using block truncation coding with color spaces. Experimentation is carried out on Wang Dataset of 1000 images consisting of 10 classes. Each class has 100 images in it. Obtained results have shown performance improvement using fusion of BTC extracted color features and texture features extracted with BTC applied on Local Binary Patterns (LBP). Conversion of color space from RGB to LUV is done using Kekre's LUV.

Optical asymmetric cryptosystem for multi-image in cyan-magenta-yellow-black color space.

In this paper, we propose an optical single-channel asymmetric cryptosystem for multi-image in cyan-magenta-yellow-black (CMYK) color space. To the best of our knowledge, this is the first time that multiple images in CMYK color space have been directly encrypted. The proposed optical asymmetric cryptosystem is based on the quick response (QR) encoding process and the designed Fresnel-linear canonical-fractional Fourier transform (FLFT) encryption process. Each FLFT encryption process consists of phase-truncated FLFT and random amplitude phase masks. The proposed cryptosystem without color space conversion can improve the quality of the decrypted images and avoid the loss of information. In addition, by utilizing the QR codes, the cross talk and quality-loss problems can be reduced efficiently. Numerical simulation results demonstrate that the proposed cryptosystem possesses high robustness against various types of attacks, high security for encrypting multiple color images, and fast encryption efficiency. Furthermore, the proposed cryptosystem outperforms the other relevant cryptosystems and can be extended to encrypt multiple color images in a straightforward way.

MMFO: modified moth flame optimization algorithm for region based RGB color image segmentation

<span lang="EN-US">Region-based color image segmentation is elementary steps in image processing and computer vision. Color image segmentation is a region growing approach in which RGB color image is divided into the different cluster based on their pixel properties. The region-based color image segmentation has faced the problem of multidimensionality. The color image is considered in five-dimensional problems, in which three dimensions in color (RGB) and two dimensions in geometry (luminosity layer and chromaticity layer). In this paper, L*a*b color space conversion has been used to reduce the one dimension and geometrically it converts in the array hence the further one dimension has been reduced. This paper introduced an improved algorithm MMFO (Modified Moth Flame Optimization) Algorithm for RGB color image Segmentation which is based on bio-inspired techniques for color image segmentation. The simulation results of MMFO for region based color image segmentation are performed better as compared to PSO and GA, in terms of computation times for all the images. The experiment results of this method gives clear segments based on the different color and the different no. of clusters is used during the segmentation process.</span>

Comparative Study of Parallelism and Pipelining of RGB to HSL Colour Space Conversion Architecture on FPGA

RGB colour model is a basic colour model and complements together to produce full colour range but it is unable to produce sufficient information for digital image analysis. However, HSL is capable to provide other useful information such as colour in degree, saturation of the colour and brightness of colour. In this work, RGB to HSL mathematical conversion algorithm is implemented on FPGA chip. Parallelism and pipelining capabilities of FPGA helps to speed up conversion performance. The RGB to HSL equation is implemented by using two architectures which are parallel and 7-stages pipeline architectures. The designed parallel and pipeline converters have one clock and seven clock cycle of data latency respectively. The parallel and pipeline architectures for RGB to HSL converter have been achieved rate of accuracy by hardware verification up to 99% and 98% and possessed maximum operating frequency merit of 50 MHz and 120 MHz respectively.

An Automatic Nucleus Segmentation and CNN Model based Classification Method of White Blood Cell

White blood cells (WBCs) play a remarkable role in the human immune system. To diagnose blood-related diseases, pathologists need to consider the characteristics of WBC. The characteristics of WBC can be defined based on the morphological properties of WBC nucleus. Therefore, nucleus segmentation plays a vital role to classify the WBC image and it is an important part of the medical diagnosis system. In this study, color space conversion and k-means algorithm based new WBC nucleus segmentation method is proposed. Then we localize the WBC based on the location of segmented nucleus to separate them from the entire blood smear image. To classify the localized WBC image, we propose a new convolutional neural network (CNN) model by combining the concept of fusing the features of first and last convolutional layers, and propagating the input image to the convolutional layer. We also use a dropout layer for preventing the model from overfitting problem. We show the effectiveness of our proposed nucleus segmentation method by evaluating with seven quality metrics and comparing with other methods on four public databases. We achieve average accuracy of 98.61% and more than 97% on each public database. We also evaluate our proposed CNN model by using nine classification metrics and achieve an overall accuracy of 96% on BCCD test database. To validate the generalization capability of our proposed CNN model, we show the training and testing accuracy and loss curves for random test set of BCCD database. Further, we compare the performance of our proposed CNN model with four state-of-the-art CNN models (biomedical image classifier) by measuring the value of evaluation metrics.

An FPGA-Based Simple RGB-HSI Space Conversion Algorithm for Hardware Image Processing

In this paper, a new, low-complexity, easy-to-implement hardware method for color space conversion between the red-green-blue (RGB) and the hue-saturation-intensity (HSI) color spaces called the simple RGB-HSI space conversion (S-SC) algorithm is proposed, which aims to provide more rapid computing due to the need for fewer operations. In the S-SC algorithm, we reconstruct the model of space conversion between the RGB color space and the HSI color space (RGB-HSI) by inverting the conversion from the HSI color space to the RGB color space of the traditional geometric derivation algorithm. As a result, the nonlinear model-realized RGB-HSI color space conversion by the geometric derivation algorithm is transformed into a linear conversion model, which can avoid complicated calculations such as trigonometric and inverse trigonometric functions in the color space conversion process. The model can effectively reduce the computational complexity of the algorithm and facilitate hardware implementation at the same time. To evaluate the performance of the S-SC algorithm, we first compare the S-SC algorithm with the geometric derivation algorithm from the computational complexity perspective. On this basis, we compare the S-SC algorithm with five other RGB-HSI color space conversion algorithms from the perspectives of error and conversion effect. Finally, we use the field programmable gate array (FPGA) hardware platform to analyze and verify the timing sequence and logical resource consumption and verify the effectiveness of the proposed algorithm with experimental results. We show that the S-SC algorithm achieves good performance in terms of conversion accuracy, logical unit resource occupancy, and output timing.

Application of fuzzy intelligent reasoning method in art color measurement

Under the influence of the COVID-19 epidemic situation, many countries have taken many measures to control the flow of people. The inability of people to gather makes art color measurement a problem. Color matching and coordination and color space conversion have always been the research focus of art color measurement. This paper studies a method of fuzzy intelligent reasoning in art color measurement. Based on case-based reasoning and rule-based reasoning, this method is an important self-learning and self-maintenance method in the field of artificial intelligence and expert system. On the basis of expounding the basic characteristics of color and color space, this paper designs the process principle of case-based reasoning and the process of rule-based reasoning. In this paper, case and rule knowledge representation method, case retrieval technology and rule conflict resolution strategy are established. Based on the above strategy, the color case base is established. In addition, the rule table is established by combining color-brewer with rule reasoning and referring to color-brewer. The rule table has a certain reference value for the application of intelligent reasoning method in the field of art color measurement under the influence of COVID-19 epidemic.

Estimation of a point along overlapping cervical cell nuclei in Pap smear image using colour space conversion

The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system especially when abnormal cells are hidden behind overlapped cells. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. Hence, there is need for algorithm which segments cells from the cluster of overlapped cells. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps in segmenting overlapped cells. This paper discusses image processing-based method which segment disjoint nuclei and identifies the point of intersection called as concavity point in the cluster of cells where only nuclei are overlapped.

Estimation of a point along overlapping cervical cell nuclei in Pap smear image using colour space conversion

The identification of normal and abnormal cells is considered as one of the most challenging task for computer assisted Pap smear analysis system especially when abnormal cells are hidden behind overlapped cells. The complexity of the problem depends on whether only cytoplasm of two cells are overlapped, or only nuclei are overlapped with disjoint cytoplasm, and in some case both cytoplasm and nuclei are overlapped. Sometimes, Pap smear sample contains mixture of cells with disjoint/overlapped cytoplasm and nuclei. Hence, there is need for algorithm which segments cells from the cluster of overlapped cells. In case of overlapped nuclei, identifying the point of overlapping accurately is one of the significant steps in segmenting overlapped cells. This paper discusses image processing-based method which segment disjoint nuclei and identifies the point of intersection called as concavity point in the cluster of cells where only nuclei are overlapped.