Edge Detection

An assignment on development of Cellular mobile communication Generations, Namely, From 0 G to 5 G. Including a briefing on GSM, EDGE, AMPS, GPRS, And all others categories related to this field. This is totally a briefing that was just created in 15 min. ;)

Automatic license plate recognition (LPR) plays an important role in numerous applications and a number of techniques have been proposed. However, most of them worked under restricted conditions, such as fixed illumination, limited vehicle speed, designated routes, and stationary backgrounds. In this study, as few constraints as possible on the working environment are considered. The proposed LPR technique consists of two main modules: a license plate locating module and a license number identification module. The former characterized by fuzzy disciplines attempts to extract license plates from an input image, while the latter conceptualized in terms of neural subjects aims to identify the number present in a license plate. Experiments have been conducted for the respective modules. In the experiment on locating license plates, 1088 images taken from various scenes and under different conditions were employed. Of which, 23 images have been failed to locate the license plates present in the images; the license plate location rate of success is 97.9%. In the experiment on identifying license number, 1065 images, from which license plates have been successfully located, were used. Of which, 47 images have been failed to identify the numbers of the license plates located in the images; the identification rate of success is 95.6%. Combining the above two rates, the overall rate of success for our LPR algorithm is 93.7%.

Since edge detection is in the forefront of image processing for object detection, it is crucial to have a good understanding of edge detection algorithms. This paper introduces a new classification of most important and commonly used edge detection algorithms, namely ISEF, Canny, Marr-Hildreth, Sobel, Kirsch, Lapla1 and Lapla2. Five categories are included in our classification, and then advantages and disadvantages of some available algorithms within this category are discussed. A representative group containing the above seven algorithms are the implemented in C++ and compared subjectively, using 30 images out of 100 images. Two sets of images resulting from the application of those algorithms are then presented. It is shown that under noisy conditions, ISEF, Canny, Marr-Hildreth, Kirsch, Sobel, Lapla2, Lapla1 exhibit better performance, respectively.

Automatic Number Plate Recognition (ANPR) has many applications as (highway electronic toll collection, Police applications, Average Speed Enforcement, Bus Lane Enforcement, Parking Management Systems, Journey Time Systems, detection of stolen vehicles, etc.).It is worth mentioning that there is a scarcity in researches that introduce an automatic number plate recognition which depends on Arabic language.

In computer vision and image processing, edge detection concerns the localization of significant variations of the grey level image and the identification of the physical phenomena that originated them. This information is very useful for applications in 3D reconstruction, motion, recognition, image enhancement and restoration, image registration, image compression, and so on. Usually, edge detection requires smoothing and differentiation of

The study of the spread of Buddhism using Geographic Information Science (GIS) mapping allows new methods for analyzing the cultural and commercial aspects that moved along routes and between seaports.  In particular, Edge Graph  approaches permit a granulated view of the complexity of such data.

The purpose of this project was to create several methods for achieving non-photorealistic appearance of the objects or, in other words, the goal was to create several different implementations of the cartoonish shader, which can sometimes be referred to as a cel-shader or just toon-shader.

We propose a system that reads the text encountered in natural scenes with the aim to provide assistance to the visually impaired persons. This paper describes the system design and evaluates several character extraction methods. Automatic text recognition from natural images receives a growing attention because of potential applications in image retrieval, robotics and intelligent transport system. Camera-based document analysis becomes a real possibility with the increasing resolution and availability of digital cameras. However, in the case of a blind person, finding the text region is the first important problem that must be addressed, because it cannot be assumed that the acquired image contains only characters. At first, our system tries to find in the image areas with small characters. Then it zooms into the found areas to retake higher resolution images necessary for character recognition. In the present paper, we propose four character-extraction methods based on connected components. We tested the effectiveness of our methods on the ICDAR 2003 Robust Reading Competition data. The performance of the different methods depends on character size. In the data, bigger characters are more prevalent and the most effective extraction method proves to be the sequence: Sobel edge detection, Otsu binarization, connected component extraction and rule-based connected component filtering.

The detection of tracks in spectrograms is an important step in remote sensing applications such as the analysis of marine mammal calls and remote sensing data in underwater environments. Recent advances in technology and the abundance of data requires the development of more sensitive detection methods. This problem has attracted researchers’ interest from a variety of backgrounds ranging between image processing, signal processing, simulated annealing and Bayesian filtering. Most of the literature is concentrated in three areas: image processing, neural networks, and statistical models such as the Hidden Markov model. There has not been a review paper which describes and critically analyses the application of these key algorithms. This paper presents an extensive survey and an algorithm taxonomy, additionally each algorithm is reviewed according to a set of criteria relating to their success in application. These criteria are defined to be their ability to cope with noise variation over time, track association, high variability in track shape, closely separated tracks, multiple tracks, the birth/death of tracks, low signal-to-noise ratios, that they have no a priori assumption of track shape and that they are computationally cheap. Our analysis concludes that none of these algorithms fully meets these criteria.

Automation of plant recognition is an important process for the fields working with plants. This presents an approach for plant recognition using Vegetable images. In this study, the proponents demonstrated the development of the system that gives users the ability to identify vegetables based on photographs of the leaves taken with a high definition camera. The output parameters are used to compute well documented metrics for the statistical and shape. Base on the study, the following conclusion are drawn: The system can extract the physical parameters from the Vegetable image that will be used in identifying Vegetables. The aim is to build an accurate, fast and reliable vegetable detection system. From the extracted Vegetable parameters, the system provides the statistical analysis and general information of the identified Vegetable. At the heart of this system is a modernize process of identification, so as to automate the way of identifying the vegetable plants through Vegetable image and digital image processing. The system used the Gabor Filter, Edge Detection, RGB Color and Gray scale Image to acquire the physical parameter of the leaves.

Edge Detection is an important step in any image processing algorithm, and the quality of edges detected determines the performance of the successive steps performed. The objective of this rep ort is to analyze and design algorithms that when used in conjunction to the Canny Edge Detector, gives better edge detection performance and minimizes influence of external noise which leads to detection of false edges. All the algorithms have been designed using OpenCV libraries. We analyze two areas in Edge detection 1. Applying Canny at a smaller scale and 2. Post processing the results from the Canny algorithm and filtering unwanted edges. The results improve the output of Canny, though unwanted edges are still detected and shown in the final results. Hence the algorithms hold potential but are far from giving any significant improvement in their current state and future work will be done to explore further improvements.

We present a simple and fast algorithm for image noise estimation. The input image is assumed to be corrupted by additive zero mean Gaussian noise. To exclude structures or details from contributing to the noise variance estimation, a simple edge detection algorithm using first-order gradients is applied first. Then a Laplacian operator followed by an averaging over the whole image will provide very accurate noise variance estimation. There is only one parameter which is self-determined and adaptive to the image contents. Simulation results show that the proposed algorithm performs well for different types of images over a large range of noise variances. Performance comparisons against other approaches are also provided.

Visual tracking of unknown objects in unconstrained video-sequences is extremely
challenging due to a number of unsolved issues. This thesis explores several of these
and examines possible approaches to tackle them.

The unconstrained nature of real-world input sequences creates huge variation in
the appearance of the target object due to changes in pose and lighting. Additionally,
the object can be occluded by either parts of itself, other elements of the scene, or
the frame boundaries. Observations may also be corrupted due to low resolution,
motion blur, large frame-to-frame displacement, or incorrect exposure or focus of the
camera. Finally, some objects are inherently difficult to track due to their (low) texture,
specular/transparent nature, non-rigid deformations, etc.

Conventional trackers depend heavily on the texture of the target. This causes issues
with transparent or untextured objects. Edge points can be used in cases where
standard feature points are scarce; these however suffer from the aperture problem. To
address this, the first contribution of this thesis explores the idea of virtual corners,
using pairs of non-adjacent line correspondences, tangent to edges in the image. Furthermore,
the chapter investigates the possibility of long-term tracking, introducing a
re-detection scheme to handle occlusions while limiting drift of the object model. The
outcome of this research is an edge-based tracker, able to track in scenarios including
untextured objects, full occlusions and significant length. The tracker, besides reporting
excellent results in standard benchmarks, is demonstrated to successfully track the
longest sequence published to date.

Some of the issues in visual tracking are caused by suboptimal utilisation of the
image information. The object of interest can easily occupy as few as ten or even one
percent of the video frame area. This causes difficulties in challenging scenarios such
as sudden camera shakes or full occlusions. To improve tracking in such cases, the next
major contribution of this thesis explores relationships within the context of visual
tracking, with a focus on causality. These include causal links between the tracked
object and other elements of the scene such as the camera motion or other objects.
Properties of such relationships are identified in a framework based on information
theory. The resulting technique can be employed as a causality-based motion model to
improve the results of virtually any tracker.

Significant effort has previously been devoted to rapid learning of object properties
on the fly. However, state-of-the-art approaches still often fail in cases such as
rapid out-of-plane rotations, when the appearance changes suddenly. One of the major
contributions of this thesis is a radical rethinking of the traditional wisdom of modelling
3D motion as appearance change. Instead, 3D motion is modelled as 3D motion.
This intuitive but previously unexplored approach provides new possibilities in visual
tracking research.

Firstly, 3D tracking is more general, as large out-of-plane motion is often fatal for 2D
trackers, but helps 3D trackers to build better models. Secondly, the tracker's internal
model of the object can be used in many different applications and it could even become
the main motivation, with tracking supporting reconstruction rather than vice versa.
This effectively bridges the gap between visual tracking and Structure from Motion.
The proposed method is capable of successfully tracking sequences with extreme out-of-plane
rotation, which poses a considerable challenge to 2D trackers. This is done by creating
realistic 3D models of the targets, which then aid in tracking.

In the majority of the thesis, the assumption is made that the target's 3D shape is
rigid. This is, however, a relatively strong limitation. In the final chapter, tracking and
dense modelling of non-rigid targets is explored, demonstrating results in even more
generic (and therefore challenging) scenarios. This final advancement truly generalises
the tracking problem with support for long-term tracking of low texture and non-rigid
objects in sequences with camera shake, shot cuts and significant rotation.

Taken together, these contributions address some of the major sources of failure
in visual tracking. The presented research advances the field of visual tracking, facilitating
tracking in scenarios which were previously infeasible. Excellent results are
demonstrated in these challenging scenarios. Finally, this thesis demonstrates that 3D
reconstruction and visual tracking can be used together to tackle difficult tasks.

This paper presents the current status of the Springrobot autonomous vehicle project, whose main objective is to develop a safety-warning and driver-assistance system and an automatic pilot for rural and urban traffic environments. This system uses a high precise digital map and a combination of various sensors. The architecture and strategy for the system are briefly described and the details of lane-marking detection algorithms are presented. The R and G channels of the color image are used to form graylevel images. The size of the resulting gray image is reduced and the Sobel operator with a very low threshold is used to get a grayscale edge image. In the adaptive randomized Hough transform, pixels of the gray-edge image are sampled randomly according to their weights corresponding to their gradient magnitudes.

Grading the Quality of the mango is
usuallyhandled physically which might not
beaccurate due to the judgement of a person.
Inthis study, image processing using
MATLABis proposed using MandamiFuzzyInterference System. The Mango is placed
onchamber to help the camera in collecting
theRed-Green-Blue (RGB) data and the spotdata
of the program. This woodenrectangular
chamber includes three LEDflashlights and the
camera. The resultsshowed that Red mean value
less than orequal to 155 are acceptable. The
blemishesand maturity of the mango is then
analysedbased in the white spots from the image
andred means of the image. The paper
alsoincludes size detection using
boundarytracing and spot detection using the
regionprops function. The results show that
theprogram is accurate enough to grade
themango. The system is strict enough to
rejectthe sample mango if it is too large, is
toosmall, is yellow or is blemished.

Using Image Processing Based on Edge Detection and Hough Transform has been developed to aid a driver in the lane departure decision-making, to reduce a loss of concentration and to prevent an accident while driving. In this paper, we propose a method for detecting the lane markers in real time by using a webcam camera to record the road as a video stream file (.avi). The Edge detection is a technique which used to identify points into a set of curved line segments called edge. Hough Transform method is used to detect the lanes in an image for increasing the accurate lane detection and the safety driving system. The results show the performance of the proposed lane detection and tracking algorithm in various lane road conditions on video clip that used for testing. According to the results, the driver can use this information to increase their safety driving, especially when making the decision of lane changing.

This paper presents an efficient architecture for various image filtering algorithms and tumor characterization using Xilinx System Generator (XSG). This architecture offers an alternative through a graphical user interface that combines MATLAB, Simulink and XSG and explores important aspects concerned to hardware implementation. Performance of this architecture implemented in SPARTAN-3E Starter kit (XC3S500E-FG320) exceeds those of similar or greater resources architectures. The proposed architecture reduces the resources available on target device by 50%.

Extraction of discriminative features from salient facial patches plays a vital role in effective facial expression recognition. The accurate detection of facial landmarks improves the localization of the salient patches on face images. This paper proposes a novel framework for expression recognition by using appearance features of selected facial patches. A few prominent facial patches, depending on the position of facial landmarks, are extracted which are active during emotion elicitation. These active patches are further processed to obtain the salient patches which contain discriminative features for classification of each pair of expressions, thereby selecting different facial patches as salient for different pair of expression classes. One-against-one classification method is adopted using these features. In addition, an automated learning-free facial landmark detection technique has been proposed, which achieves similar performances as that of other state-of-art landmark detection methods, yet requires significantly less execution time. The proposed method is found to perform well consistently in different resolutions, hence, providing a solution for expression recognition in low resolution images. Experiments on CK+ and JAFFE facial expression databases show the effectiveness of the proposed system.

Brain tumor diagnosis is done by doctors. For detecting brain tumor grading always gives different conclusion between one doctor to another. For helping doctors diagnose brain tumor grading, this research made a software with edge detections method , so it could give edge pattern of brain and brain tumor itself. Edge detection of brain tumor in this research is the first step for brain tumor grading research. This research found the best edge detection method for brain tumor detecting between Robert, Prewitt, and Sobel method. From these three methods, Sobel method is suitable with case of brain tumors detecting. Sobel method had smaller deviation standard value than two others edge detection method.

Quick and accurate measurements of size distribution are essential to managing fragmented rock and other materials. WipFrag is an automated image based granulometry system that uses digital image analysis of rock photographs and video tape images to determine grain size distributions.

Fractal dimension is an interesting parameter to characterize roughness in an image. It can be used in texture segmentation, estimation of three-dimensional (3D) shape and other information. A new method is proposed to estimate fractal dimension in a two-dimensional (2D) image which can readily be extended to a 3D image as well. The method has been compared with other existing methods to show that our method is both efficient and accurate.

The capability of satellite QuickBird imagery for the identification of archaeological crop marks is herein presented and discussed for two test sites located in the South of Italy. The selected sites, dating back to Middle Ages, were buried under surfaces covered by herbaceous plants characterized by a different phenological status (dry/green) when the satellite data were acquired.

Cracks are typical line structures that are of interest in many computer-vision applications. In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which brings great challenges to image-based crack detection by using low-level features. In this paper, we propose DeepCrack-an end-to-end trainable deep convolutional neural network for automatic crack detection by learning high-level features for crack representation. In this method, multi-scale deep con-volutional features learned at hierarchical convolutional stages are fused together to capture the line structures. More detailed representations are made in larger-scale feature maps and more holistic representations are made in smaller-scale feature maps. We build DeepCrack net on the encoder-decoder architecture of SegNet, and pairwisely fuse the convolutional features generated in the encoder network and in the decoder network at the same scale. We train DeepCrack net on one crack dataset and evaluate it on three others. The experimental results demonstrate that DeepCrack achieves F-Measure over 0.87 on the three challenging datasets in average and outperforms the current state-of-the-art methods.

Find article (software manual) at:  http://www.iaees.org/publications/journals/np/articles/2020-5(1-2)/1-Zhang-Abstract.asp                                                                                                                                               

Download software at:                       
http://www.iaees.org/publications/software/                                       

In present study, I developed a powerful Matlab-based software package, imageProcAnal (Version 1.0), for image processing and analysis. Several modules were available for uses. Functions to resize, crop, rotate, dilate, pixelate and watermark images are included in Basic module. Adjustment of image edge, contrast and gamma factor is available in Adjustment module. In Denoising module, four elementary denoising methods and their joint uses are provided for image filtering and denoising. In Edge and Contour Detection module, five methods for detection of image edge and contour are provided. Also three methods for image sharpening are available in Sharpening module. Segmentation module includes three methods for image segmentation. Connected components recognition can be made in Object Recognition module. In Analysis module, Pearson correlation measure was provided to align images. Pearson correlations and p values among images can be obtained. Mutiple methods across different modules can be sequentially and jointly used to achieve ideal image. Finally, some examples for image processing can be found in Demo module. In addition to conventional methods, I proposed two new methods for image segmentation, i.e., TDOS (Two-Dimensional Ordered Segmentation) and MWAS (Moving Windows Averaging Segmentation). In TDOS, which is based on two-dimensional ordered cluster analysis, the pixels belonging to the same segment (class) are adjoint and are not separated by any of remaining segments. MWAS is based on moving windows averaging method for transect boundary detection. Algorithms of TDOS and MWAS were given, and full Matlab codes of MWAS were given.

T he rising popularity of photosharing applications on the Web has led to the generation of huge amounts of personal image collections. Browsing through image collections of such magnitude is currently supported by the use of tags. However, tags suffer from several limitations-such as polysemy, lack of uniformity, and spam-thus not presenting an adequate solution to the problem of content organization. Therefore, automated contentorganization methods are of particular importance to improve the content-consumption experience. Because it's common for users to associate their photo-captured experiences with some landmarks-for example, a tourist site or an event, such as a music concert or a gathering with friends-we can view landmarks and events as natural units of organization for large image collections. It's for this reason that automating the process of detecting such concepts in large image sets can enhance the experience of accessing massive amounts of pictorial content.

A method for detecting buildings from satellite/aerial images is proposed in this paper. The aim is to extract rectilinear buildings by using hypothesis. Hypothesis generation is accomplished by using edge detection and line generation methods. Hypothesis verification is carried out by using information obtained both from the color segmentation of HSV representation of the image. Satellite images is firstly filtered to sharpen the edges. The edges are extracted using Canny edge detection algorithm. These edges are the input for the Hough Transform stage which will produce line segments according to these extracted edges. Then, extracted line segments are used to generate building hypothesis. Verification of these hypotheses makes use of the outputs of the HSV color segmentation. In this study, color segmentation is processed on the HSV representation of the satellite/aerial images which are less sensitive to the illumination. Finally, Buildings are extracted from the urban areas.

We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds. where he worked on VLSI design for very low bit-rate video communication. From served on the editorial board of IEEE TRANSACTIONS ON COMPUTERS. He is a Chair of the steering committee of the Symposium on Research Issues on Data Engineering and was one of its founders; he serves on the steering committee of IEEE ICDE and has served on its program chair and general chair. He has served on various program and organization committees. He is a member of the ACM.

Edge detection is one of image enhancement techniques that are used to extract important features from the edges of an image (e.g., corners, lines, curves). The aim of image enhancement is to improve the interpretability of information in images for human viewers, or to provide "better" input for other automated image processing techniques. The proposed work presents Programmable Gate Array (FPGA) based architecture for Edge Detection using Robinson edge detection operator in respect of both time and space complexity. The algorithm are implemented using MATLAB 2010 language code as well as the VHDL language to deal with use of FPGA device, which was of a kind (Xilinx XC3S500E Spartan-3E), and it implemented on 8 bit grayscale image data, Robinson edge detection algorithm is produced using the pixel windows (3×3 windows) to calculate its output, make a comparison between the resultant image in MATLAB and VHDL by calculate the Peak Signal-to-Noise Ratio (PNSR), Root Mean Square error (RMSE) and the correlation between resultant images from MATLAB and VHDL.

https://sites.google.com/site/ijcsis/

The Hammam Faroun has a particular importance due to its geothermal activity which constitutes the main geothermal resource of Egypt. The area is located on the Sinai Peninsula, a subplate bounded by two seismically active structural zones along the Gulf of Suez and Gulf of Aqaba. High-resolution ground-based gravity and magnetic data are available for the entire Hammam Faroun area, acquired as part of a national project to explore for mineral, geothermal, and hydrocarbon resources. Gravity and magnetic data were analyzed using Source Edge Detection and Source Parameter Imaging (SPI) techniques to image subsurface structures. These analyses show that the area is characterized by a set of northwest-striking faults lying parallel to the Gulf of Suez. Orthogonal patterns are also present, possibly related to rifting of the Gulf of Suez. Depth analysis using the SPI method indicates that surface faults extend to 5-km depth. Analysis of potential-field data elucidates the structurally complex subsurface structure of the Hammam Faroun area.

In this paper, a hardware system for Sobel Edge Detection Algorithm is designed and simulated for a 128 pixel, 8-bit monochrome line-scan camera. The system is designed to detect objects as they move along a conveyor belt in a manufacturing environment, the camera will observe dark objects on a light conveyor belt. The edge detector is required to detect horizontal and vertical edges using Sobel edge detection method. The Sobel operator requires 3 lines and takes 3 pixels per line, thus using a 3×3 input block to process each pixel. The centre pixel of the 3×3 pixel block can be classified as an edge point or otherwise by thresholding the value from the operator. The FPGA based Sobel edge detector is designed and simulated using Altera Quartus II 8.1 web edition by targeting Cyclone II development boards.

Segmentation of the vessels in retina images is an essential step in earlier diagnosis of diabetic and hypertension. The application of image analysis using segmentation could assist the ophthalmologists, to detect the signs of diabetic retinopathy in the early stages. In this paper, a bank of 180 Gabor filters is used to capture high frequency information among which the maximum response for each pixel is selected. The vessels in the filtered retina images are segmented using a threshold value that passes the informative pixels and rejects the insignificant pixels. Determination of an effective threshold is of utmost importance for reliable segmentation which leads reliable vessel detection. The paper proposes a systematic way of determining the threshold value for reliable performance. The proposed approach is applied to retinal images from DRIVE retina database. The performance of the proposed vessel segmentation approach reaches to 0.95 based on the area under the receiver operating characteristic curve.

Lineament extraction from satellite remotely sensed data has been one of the widely used applications of remote sensing in geology. In fact, recent advances in digital image processing allow such lineament extraction to be accomplished in semi-automatic to fully automatic approaches. However, satellite remotely sensed data acquired in heavily vegetated regions such as tropical rainforest, are vulnerable to higher inherent noise levels attributed to the resultant effects of scattering by clouds and adjacency effects of highly inhomogeneous vegetation cover within the pixel dimension. In this study, we examined the effects of noise levels to lineament extraction using a fully automatic approach, consisting of a combination of edge-line detection algorithms. Ancillary information from a digitized topographic map and image classification was used to discriminate between cultural and natural lineaments from the extracted lineaments. Adapting the combination of edge detection and a line-linking algorithm, we have found the optimal parameters for automatic lineament extraction of such complex areas using Enhanced Thematic Mapper (ETM+) data. A noise level of 30% is the maximum threshold before artifacts are generated. It is therefore concluded that the combination of edge-based and line-linking digital image processing operations with the priori local optimal parameters is crucial in lineament feature extraction in heavily vegetated regions.

The bone of contention for Advanced Driver Assistance Systems (ADAS) is Lane Detection. It is not effectively executed and is challenged because of susceptible computer vision techniques which are vulnerable for many factors like peculiar road pattern, unusual lighting and weather conditions, repercussion of obstacles like shadows and other cars, and many more. To try and overcome these vulnerabilities, The Sliding Windows method is used in this paper to detect lanes in real-time using the OpenCV python package. It includes undistorting, preprocessing, detecting lanes on the perspective transformed frame, and displaying detected lane as output. Radius of curvature of lane and offset of the car from the center of the lane is calculated. During preprocessing, different edge detection methods like Laplacian, Sobel and Canny edge detection methods are examined. After comparing and contemplating, it is deduced that Canny edge detection is better than the remaining ones. The test videos for lane detection are taken from Udacity GitHub repository.

Combining both spatial and intensity information in image, we present an MRI brain image segmentation approach based on multiresolution edge detection, region selection, and intensity threshold methods. The detection of white matter structure in brain is emphasized in this paper. First, a multi-resolution brain image representation and segmentation procedure based on a multi-scale image filtering method is presented. Given the nature of the structural connectivity and intensity homogeneity of brain tissues, region-based methods such as region growing and subtraction to segment the brain tissue structure from the multi-resolution images are utilized. From the segmented structure, the region-of-interest (ROI) image in the structure region is derived, and then a modified segmentation of the ROI based on an automatic threshold method using our threshold selection criterion is presented. Examples on both T1 and T2 weighted MRI brain image segmentation is presented, showing finer brain tissue structures. ᭧

Text detection and localization in natural scene images is important for content-based image analysis. This problem is challenging due to the complex background, the non-uniform illumination, the variations of text font, size and line orientation. In this paper, we present a hybrid approach to robustly detect and localize texts in natural scene images. A text region detector is designed to estimate the text existing confidence and scale information in image pyramid, which help segment candidate text components by local binarization. To efficiently filter out the non-text components, a conditional random field (CRF) model considering unary component properties and binary contextual component relationships with supervised parameter learning is proposed. Finally, text components are grouped into text lines/words with a learning-based energy minimization method. Since all the three stages are learning-based, there are very few parameters requiring manual tuning. Experimental results evaluated on the ICDAR 2005 competition dataset show that our approach yields higher precision and recall performance compared with state-of-the-art methods. We also evaluated our approach on a multilingual image dataset with promising results.

This paper presents a fast algorithm for corner detection based on the observation that the total curvature of the grey-level image is proportional to the second order directional derivative in the direction tangential to edge normal, and inversely proportional to the edge strength (norm of the edge normal). This algorithm simply takes the difference of the second tangential derivative with the edge strength, where the first term is the comemess measurement and the second is called a false comer suppression. A subpixel addressing mechanism (called linear interpolation) is utilized for intermediate pixel addressing in the differentiation step, which results in improved accuracy of comer localization and reduced computational complexity. The analysis of comer dislocation leads to a subpixel implementation. The comer tinder is implemented on a hybrid parallel processor PARADOX with a performance of 14 frames/s for the vision algorithm Droid.

Art historians have long observed the highly characteristic brushstroke styles of Vincent van Gogh and have relied on discerning these styles for authenticating and dating his works. In our work, we compared van Gogh with his contemporaries by statistically analyzing a massive set of automatically extracted brushstrokes. A novel extraction method is developed by exploiting an integration of edge detection and clustering-based segmentation. Evidence substantiates that van Gogh's brushstrokes are strongly rhythmic. That is, regularly shaped brushstrokes are tightly arranged, creating a repetitive and patterned impression. We also found that the traits that distinguish van Gogh's paintings in different time periods of his development are all different from those distinguishing van Gogh from his peers. This study confirms that the combined brushwork features identified as special to van Gogh are consistently held throughout his French periods of production (1886-1890).