Image colour edge detection using hypercomplex convolution

The conventional color edge detection methods generate color edge maps by calculating the vector gradient at each pixel. These methods may cause false edge detection for color stripe images and other special color images and they are sensitivity to noise. A new vector template matching method based on pyramid structure is presented. It can generate more precise edge points. The pyramid image structure has been used to reduce the computational cost in the multiresolution analysis. The effect of Gaussian noise can be reduced by selecting a suitable weighting function in the color pyramid generation. The edge interpolation, adjustment and smoothing are carried out to obtain edge map of a lower pyramid level from the edge map immediately above by the top-down strategy. The vector average median filtering is applied in this procedure to reduce the effect of impulsive noise. The method is applied to color palm images and another special images with both Gaussian and impulsive noise. Good edge maps are obtained from ex- periments. © 1997 Society of Photo-Optical Instrumentation Engineers. (S0091-3286(97)02105-3)

Most of the edge detection methods available in literature are gradient based, which further apply thresholding, to find the final edge map in an image. In this paper, we propose a novel method that is based on fuzzy logic for edge detection in gray images without using the gradient and thresholding. Fuzzy logic is a mathematical logic that attempts to solve problems by assigning values to an imprecise spectrum of data in order to arrive at the most accurate conclusion possible. Here, the fuzzy logic is used to conclude whether a pixel is an edge pixel or not. The proposed technique begins by fuzzifying the gray values of a pixel into two fuzzy variables, namely the black and the white. Fuzzy rules are defined to find the edge pixels in the fuzzified image. The resultant edge map may contain some extraneous edges, which are further removed from the edge map by separately examining the intermediate intensity range pixels. Finally, the edge map is improved by finding some left out edge pixels by defining a new membership function for the pixels that have their entire 8-neighbourhood pixels classified as white. We have compared our proposed method with some of the existing standard edge detector operators that are available in the literature on image processing. The quantitative analysis of the proposed method is given in terms of entropy value.

Fusion of color and edge information for improved segmentation and edge linking

Defects in fabrics usually appear as inhomogeneities of fabric texture patterns. Accurate and efficient detection of these inhomogeneities is crucial for fabric manufacturers. Many sophisticated visual inspection methods have been introduced based on texture analysis algorithms. Unfortunately, only few of these are suitable for real-time fabric inspections due to the high computational cost. An efficient and robust fabric defect detection method is proposed in this paper. It is based on the fact that the presence of defects breaks the texture's homogeneity and thereby changes the distribution of microedges in the edge map after the original texture image undergoes edge detection. In the proposed approach, a set of edge operators are introduced to reveal microedges in multiple directions. Local measures of microedge pixel densities are proposed to characterize the underlying fabric texture. A weighted distance derived from normal distribution is exploited to classify the inhomogeneous areas from normal fabrics. The proposed method is implemented on a smart camera using its on-board processing ability to achieve fast inspection. Experimental results on real fabrics demonstrate the effectiveness and robustness of the proposed method.

The inherent memory effect of the Grunwald–Letnikov fractional derivatives is combined with the effectiveness of information sets for detecting edges in digital images. Fractional derivatives are utilized in the computation of fractional gradients, which are further processed using information sets for the proposed edge detector to extract more edges than possible with the traditional edge detectors. In the proposed approach, first the gradient operators of the Sobel mask are converted into the fractional form and convolved with the given gray image. In the next step, the histogram of the fractional gradients is fuzzified using the Gaussian membership function and the sigmoidal membership function. The optimal parameters for these membership functions are selected through a grid search method based on the information set-based edge strength factor ESf. In the final step, defuzzification is performed to obtain the final edge maps. By plotting the edge maps, analyzing the boundary information, and Pratt’s figure of merit scores for images in the Berkeley segmentation dataset, it is observed that the resulting edge maps of the proposed edge detector contain more quantitative and qualitative information than that of traditional edge detectors even in the presence of noise.

This paper proposes a new method to locate the text regions from images with complex background based on the Discrete Shearlet Transform. Text localization is an important step of text extraction to obtain the useful information from images. It is now widely acknowledged that traditional wavelets are not very effective in dealing with multi-dimensional signals containing distributed discontinuities. Shearlets not only possess the main features of wavelets such as multi-scale, multi-direction and time-frequency localization, but also offers a high degree of directionality and anisotropy. Meanwhile, compared with Nonsubsampled Contourlet Transform (NSCT), Shearlets has obvious superiority in flexibility on directional selectivity and lower computing complexity. The proposed method applies the Discrete Shearlet Transform on an image to decompose it into set of directional subbands with texture details captured in different orientations and scales. Then, the binarization with dynamic thresholding is applied to these subbands so as to filter out the background and recognize the edges in multiple directions. Morphological operations are carried out on these binary images and connect the edges together in these images. At each scale, text regions are obtained with the help of the logical AND operator on all binary subband images; and the final text regions are achieved through voting-decision among different scales. This method of text localization is applied on different samples of images and the experiment results have a good performance.

At present times the topic of Chaos gain a lot of attention for the encryption/decryption methodology, yet we didn’t settled to get a good difference between conventional counterparts. Several chaotic maps can be considered sensitivity dependence to seed values. Taking into consideration for this property, In this paper, the author have presented an image encryption technique employing a 2-dimensional chaotic Henon map, initially it implemented the confusion scheme using chaotic sequence obtained by several iterations using chaotic map approach. In the subsequent stage Edge Maps, generated by edge detection filters and binary bit plane decomposition is applied to perform further confusion using a bit-xor operation to get a cipher image. It is more secure and robust, experimental analysis and simulation is performed to get required results which better revealed that the encrypted images are secured and tolerant to different attacks.

The classical color histogram for image indexing does not take into account the shape information of an image. A color histogram method with edge information is studied. Color distributions are found for the pixels of three types of edges (two directional edges and one non-directional edge) and three distance measures are computed on the basis of the color distribution of each edge type. The proposed similarity measure obtained by combining these three distance measures could reduce the false match rate in comparison with using only single (non-directional) edge types. Simulation results show an improvement in indexing quality as compared to that of the traditional color histogram and edge histogram.

An increasing number of tasks have been developed for autonomous driving and advanced driver assistance systems. However, this gives rise to the problem of incorporating plural functionalities to be ported into a power-constrained computing device. Therefore, the objective of this work is to alleviate the complex learning procedure of the pixel-wise approach for driving scene understanding. In this paper, we go beyond the pixel-wise detection of the semantic segmentation task as a point detection task and implement it to detect free space and lane. Instead of pixel-wise learning, we trained a single deep convolution neural network for point of interest detection in a grid-based level and followed with a computer vision (CV) based post-processing of end branches corresponding to the characteristic of target classes. To achieve the corresponding final result of pixel-wise detection of semantic segmentation and parametric description of lanes, we propose a CV-based post-processing to decode points of output from the neural network. The final results showed that the network could learn the spatial relationship for point of interest, including the representative points on the contour of the free space segmented region and the representative points along the center of the road lane. We verify our method on two publicly available datasets, which achieved 98.2% mIoU on the KITTI dataset for the evaluation of free space and 97.8% accuracy on the TuSimple dataset (with the field of view below the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$y=320$ </tex-math></inline-formula> axis) for the evaluation of the lane.

Edge detection in range images provides rich information about the scene being observed. Many researchers have been taking advantage of this information to improve image segmentation by integrating edge detection with other segmentation techniques. This paper presents a methodology to perform edge detection in range images in order to provide a reliable and meaningful edge map, which helps to guide and improve range image segmentation by clustering techniques. The obtained edge map leads to three important improvements: (1) the definition of the ideal number of clusters to initialise the clustering algorithm; (2) the selection of suitable initial cluster centres; and (3) the successful identification of distinct regions with similar features. Experimental results that substantiate the effectiveness of this work are presented.

The edge descriptor proposed by MPEG-7 standard is a representative approach for the contents-based image retrieval using the edge information. In the edge descriptor, the edge information is the edge histogram derived from a gray-level value image. This paper proposes a new method which extracts color edge information from color images and a new approach for the contents-based image retrieval based on the color edge histogram. The poposed method and technique are applied to image retrieval of the e-catalogue. For the evaluation, the results of image retrieval using the proposed approach are compared with those of image retrieval using the edge descriptor by MPEG-7 and the statistics shows the efficiency of the proposed method. The proposed color edge model is made by combining the R,G,B channel components vectorially and by characterizing the vector norm of the edge map. The color edge histogram using the direction of the color edge model is subsequently used for the contents-based image retrieval.

The H operator represents the deterministic performance of any imaging system. For a linear, digital imaging system, this system operator can be written in terms of a matrix, H, that describes the deterministic response of the system to a set of point objects. A singular value decomposition of this matrix results in a set of orthogonal functions (singular vectors) that form the system basis. A linear combination of these vectors completely describes the transfer of objects through the linear system, where the respective singular values associated with each singular vector describe the magnitude with which that contribution to the object is transferred through the system. This paper is focused on the measurement, analysis, and interpretation of the H matrix for digital x-ray detectors. A key ingredient in the measurement of the H matrix is the detector response to a single x ray (or infinitestimal x-ray beam). The authors have developed a method to estimate the 2D detector shift-variant, asymmetric ray response function (RRF) from multiple measured line response functions (LRFs) using a modified edge technique. The RRF measurements cover a range of x-ray incident angles from 0 degree (equivalent location at the detector center) to 30 degrees (equivalent location at the detector edge) for a standard radiographic or cone-beam CT geometric setup. To demonstrate the method, three beam qualities were tested using the inherent, Lu/Er, and Yb beam filtration. The authors show that measures using the LRF, derived from an edge measurement, underestimate the system's performance when compared with the H matrix derived using the RRF. Furthermore, the authors show that edge measurements must be performed at multiple directions in order to capture rotational asymmetries of the RRF. The authors interpret the results of the H matrix SVD and provide correlations with the familiar MTF methodology. Discussion is made about the benefits of the H matrix technique with regards to signal detection theory, and the characterization of shift-variant imaging systems.

A system named Fire Danger Rating System is a tool using for early warning system of forest fires. Since 1999 Indonesia has this system, adapted from Canadian Forest Service (CFS), and developed by BPPT cooperation with BMG (now is BMKG), and Departemen Kehutanan (KLHK). The main scientific based of this FDRS is meteorology, where it used total precipitation in a day, and noon condition of temperature, relative humidity, and wind speed. The final result is the Fire Weather Index where we may see the four classes of fire danger rating in two-dimension map. The improvement on this weather component is the use of satellite data to replace some parameter of weather from Automatic Weather Station data. In recent condition, not only weather condition as the primary parameter, but also the human-caused factor, and fuels condition analysis were putting as the same level of weather. Human activities are the main factor of the occurrence of forest fires, that is why the forest, plantation, and horticulture-agriculture land are the main land use that we pay attention more, and it's related to the people who live on small cities or districts in that areas. The condition of peatland we analyzed is the thickness of the peat and the land cover on the surface. The position of water body also we calculated to see the distance of the source of water for wetting the land. Using Spatial Multi-Criteria Evaluation is the right way to get some scenarios to have the final composite risk map. Grouping and standardizing the spatial factors based on human-caused and fuels we may know the effect of that component to the final composite map of the Advanced-FDRS. Ina-FDRS is the biggest scenario that includes Natural Resources Accounting as one of the main components, instead of climate, human-caused, and fuels. So, this Advanced-FDRS is the main part of Ina-FDRS (Indonesia Fire Danger Rating System) that ongoing develop by BPPT and the stakeholders for early warning land and forest fire in peatland in Indonesia.

This paper presents a robust filter called the quaternion Hardy filter (QHF) for color image edge detection. The QHF can be capable of color edge feature enhancement and noise resistance. QHF can be used flexibly by selecting suitable parameters to handle different levels of noise. In particular, the quaternion analytic signal, which is an effective tool in color image processing, can also be produced by quaternion Hardy filtering with specific parameters. Based on the QHF and the improved Di Zenzo gradient operator, a novel color edge detection algorithm is proposed; importantly, it can be efficiently implemented by using the fast discrete quaternion Fourier transform technique. From the experimental results, we conclude that the minimum PSNR improvement rate is 2.3% and the minimum SSIM improvement rate is 30.2% on the CSEE database. The experiments demonstrate that the proposed algorithm outperforms several widely used algorithms.

This study aims at the simultaneous solution of several quaternion linear systems with the same Hermitian and positive definite coefficient matrix by employing the conjugate gradient method. We consider the setting when the quaternion Hermitian positive definite coefficient matrix at hand is very large so that direct methods are not applicable. In the study, we first transform linear quaternion systems into real linear systems. The transformed real linear systems have special structure due to the fact that they are real representations of quaternion systems. Benefitting from the special structure, we further reduce the size of these linear systems. Then a block conjugate gradient method is applied to the resulting reduced real linear systems. The solution obtained after applying the conjugate gradient method is a real representation of the solution of the original quaternion problem. Thus, a conversion of this real solution to the quaternion setting is performed in the end.