Sobel operator

About: Sobel operator is a research topic. Over the lifetime, 3535 publications have been published within this topic receiving 58627 citations.

A Computational Approach to Edge Detection

Abstract: This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.

Color Image Processing and Applications

Abstract: This book claims to fill a niche in the provision of textbooks devoted to image processing by being devoted to colour aspects. It is aimed at researchers and practitioners working in the area of colour image processing, particularly graduates in Computer Science and Electrical and Computer Engineering. The book is structured in such a way that, after reading an introductory chapter on colour, readers can work their way through the following four chapters on image processing, or omit them and move directly to the final three chapters that deal with colour image analysis and coding. It is not immediately apparent from reading the preface that companion image processing software is available online from the publisher's website, and this is not made use of as an integral part of the book. Regrettably, the book shows much evidence of a lack of rigorous proof reading and editing. A number of errors can be found, particularly in the first chapter; this provides the fundamentals in colour science on which the book is based. For example, on the first page the visible spectrum is incorrectly reproduced with the wrong wavelength scale and photoreceptors are referred to as `roads'. A few pages on there is a complete mismatch between the explanatory text and diagrams concerning the CIE, XYZ and RGB colour matching functions. One diagram appears to have been reproduced twice, is incorrectly titled and not annotated. Also, the CIE chromaticity diagram lacks a wavelength scale and the colours of the diagram are incorrectly reproduced. Unfortunately, these fundamental errors appear in the first ten pages and have the unfortunate effect of detracting from the authoritative nature of the book as a whole. A further example of poor proof reading/editing can be found towards the end of the chapter in which photographic film is defined as follows: `The film which is used by conventional cameras contains three emulsion layers which are sensitive to red and blue light, which enters through the camera lens.' The chapters do improve, however, as one goes through the book, although in chapter 2 the description of the origins of photographic noise is incorrect and incomplete (`the noise is mainly due to the silver grains that precipitate during film exposure'). Also, the origins of noise in photoelectronic sensors are incompletely described. Each chapter is accompanied by a substantial number of references to the primary sources of information, many of which are to recent literature in the field, in very useful summary or conclusion sections. It is puzzling that in view of the significance of the Fourier transform in image processing, it is not included, other than a brief mention of the Discrete Fourier Transform in the chapter on image compression. Adaptive image filters are described at length in chapter 3, which is followed by chapters dedicated to colour edge detection, enhancement and restoration, image segmentation, image compression and emerging applications. The latter makes interesting reading but is based almost exclusively on the detection and automatic location of the human face. The index is not very exhaustive and as a consequence it is difficult to find many items that are discussed in the text but are not indexed. A few examples include: Wiener filter, Sobel, Prewitt and Robert's edge detection, all of which appear in the text and in the indices of most books on image processing but not in the index to this book. Also, most of the existing texts on image processing include many aspects of colour, which detracts somewhat from this book's claimed uniqueness, although it does contain more state-of-the-art aspects. Ralph Jacobson

Design of an image edge detection filter using the Sobel operator

Abstract: The architecture of the edge detector presented is highly pipeline to perform the computations of gradient magnitude and direction for the output image samples The chip design is based on a 2- mu m, double-metal, CMOS technology and was implemented using a silicon compiler system in less than 2 man-months It is designed to operate with a 10-MHz two-phase clock, and it performs approximately 200*10/sup 6/ additions/s to provide the required magnitude and direction outputs every clock cycle The function of the chip has been demonstrated with a prototype system that is performing image edge detection in real time >

A Descriptive Algorithm for Sobel Image Edge Detection

Abstract: Image edge detection is a process of locating the e dge of an image which is important in finding the approximate absolute gradient magnitude at each point I of an input grayscale image. The problem of getting an appropriate absolute gradient magnitude for edges lies in the method used. The Sobel operator performs a 2-D spatial gradient measurement on images. Transferring a 2-D pixel array into statistically uncorrelated data se t enhances the removal of redundant data, as a result, reduction of the amount of data is required to represent a digital image. The Sobel edge detector uses a pair of 3 x 3 convolution masks, one estimating gradient in the x-direction and the other estimating gradient in y‐direction. The Sobel detector is incredibly sensit ive to noise in pictures, it effectively highlight them as edges. Henc e, Sobel operator is recommended in massive data communication found in data transfer.

A robust arbitrary text detection system for natural scene images

Abstract: Text detection in the real world images captured in unconstrained environment is an important yet challenging computer vision problem due to a great variety of appearances, cluttered background, and character orientations. In this paper, we present a robust system based on the concepts of Mutual Direction Symmetry (MDS), Mutual Magnitude Symmetry (MMS) and Gradient Vector Symmetry (GVS) properties to identify text pixel candidates regardless of any orientations including curves (e.g. circles, arc shaped) from natural scene images. The method works based on the fact that the text patterns in both Sobel and Canny edge maps of the input images exhibit a similar behavior. For each text pixel candidate, the method proposes to explore SIFT features to refine the text pixel candidates, which results in text representatives. Next an ellipse growing process is introduced based on a nearest neighbor criterion to extract the text components. The text is verified and restored based on text direction and spatial study of pixel distribution of components to filter out non-text components. The proposed method is evaluated on three benchmark datasets, namely, ICDAR2005 and ICDAR2011 for horizontal text evaluation, MSRA-TD500 for non-horizontal straight text evaluation and on our own dataset (CUTE80) that consists of 80 images for curved text evaluation to show its effectiveness and superiority over existing methods.