Sobel Edge Detection Research Articles

A Novel Classification of MRI Brain Images using ANFIS and 3D Reconstruction

The brain tumor (BT) has turn into a chief hazard to life in many humans. With the advances in medicine and technology, early tumor detection may pay a way for treating it in an early phase and thereby reducing the death rates. MRI imaging has a significant role in imaging the BT. Neurologist base the treatment of BT on the type, location, and also size of the tumor and hence proper segmentation of the tumor region has become essential. Here, an efficient segmentation algorithm is proposed, is centered on using the Sobel edge detection mechanism and the classification of the tumor region centered on the features extorted as of the segmented images are performed. The brain MRI images from a database which contain normal and also abnormal cases. These images are stripped from the skull by utilizing the morphological operations like morphological opening along with closing. Following this, segmentation is executed and finally, features are extorted as well presented to the classifier where the classification is executed. The segmentations algorithm is estimated and also the outcome are contrasted to the other prevailing algorithms say Kmeans and SVM (Support Vectors Machine) and the classification algorithm is weighted against that of the existent classification algorithm like PNN (probabilistic neural network) and ANN (Artificial Neural Network). Thus the proposed algorithms are confirmed to be superior to the other algorithms used in BT segmentations and classification.

Optimization of Pattern Recognition of Hijaiyah Letters using Normalized Cross Correlation Tchniques

The development of analysis in digital image increasingly developed with various methods, one of which is in recognition of letter patterns. Each letter written using handwriting must have different writing patterns, such as the thickness and shape of the letter pattern. This research will be doing on the pattern recognition of hijaiyah letters of handwriting by applying the Normalized Cross Correlation (NCC) technique. NCC is a technique used to match two images. Before the NCC process, it should be done with the preprocessing using convolution and without convolution using the binary image. The convolution technique used was the Sobel and Prewitt edge detection with the aimed to get the edge of an object and compared the number of matching letters between using edge detection and without edge detection. The tests were done by using the different sized image of 32x32 pixels, 64x64 pixels and then match it against a similar sample data, a different sample data, a different objects font sample data and a different sample data of original image size. The results show that the matching of the letter pattern depends on the size of the image that is more matches to the image of 32x32 pixels. The binary image had better matching numbers than the convolution techniques. While in convolution techniques, Prewitt edge detection had the higher accuracy and matching results compared to the image using Sobel edge detection.

Identification of Chrysanthemum Flower Based on Color and Flower Form using Sobel Edge and Artificial Neural Network

Chrysanthemum is a popular ornamental plant in Indonesia because it has a variety of shapes and colors that attract a lot of attention. In addition to the trimmer, this flower can be used as a mosquito repellent and also absorbs dirty air pollution. Chrysanthemum flowers can be distinguished by color and shape with two types of ways to grow Chrysanthemum flowers that grow in clusters are called spray and also flowers that grow with no cluster or a flower per stalk. In addition, Chrysanthemum flowers have various color variations including pink, purple, yellow, white, orange, and red. The purpose of this study is to identify the type of Chrysanthemum flowers using extraction of Red, Green, Blue (RGB) color features and characteristic extraction using a Sobel edge detection, for his identification method using Artificial Neural Networks. Chrysanthemum data are white puma, Vania, Iranian, purple aster, and pink standard used in this research consisted of 100 training data and 50 tests data. The test was done with four tests that is identification with form extraction (Sobel) yielded accuracy value equal to 59.52%, identification with color and shape extraction yield accuracy value equal to 65.36%, identification with color extraction on flower and base flower plate yield value accuracy of 69.44%, and identification with color extraction yields an accuracy value of 75.35%.

Camera Captured Handwritten Kannada Character Recognition

Optical Character Recognition (OCR) is an automatic reading of text components that are optically sensed to translate human-readable characters into machine-readable codes. In handwritten the style of writing vary from person to person, so it is very challenging task to segment and recognize the characters. In this paper we are proposing segmentation and feature extraction techniques to recognise camera captured, handwritten Kannada documents. The segmentation is done by using projection profile technique & Connected Component Analysis (CCA). The pre-processing technique to detect the edges of Kannada character, we have proposed our own technique by combining of Sobel and Canny edge detection. The feature selection and extraction is done in two level, global and local features. Global features are extracted from entire image. In local feature extraction we divided an input character image in to four quadrate based on centroid of character and we will extract local features from all quadrates rather than whole image. We have used Support vector machine (SVM) to classify the handwritten Kannada characters. To evaluate the efficiency of proposed system we have used KHDD dataset, our own document and character dataset. The experimental results shows that our proposed features selection and extraction achieved 96.31% of accuracy, results are encouraging.

Relationship Identification & Prediction of Diseases Association using Micro-RNA of Genomic Data

The current process of finding the relationship between the father and the son and also predicting the diseases that is yet to occur is quite inaccurate because it includes only the gene-id of the respected person. In order to handle or to make this system more accurate, we propose this system by using the chromosome structure of the person. This system takes the input of the chromosome structure of the son that has been partitioned from the father’s chromosome structure. It initially preprocesses the image of the son using the collaborative filtering for making it look different from the input image to show the similarity between the father and the son. It then detects the edge of the structure after preprocessing it using the SOBEL edge detection algorithm. The SOBEL edge detection algorithm is that the gradient of the image is calculated for each pixel position in the image. After detecting the edges of those input images, matching process starts between the input image and the list of father chromosome images. Then the matched output appears. In order to predict the diseases which is yet to come in future for the son is represented graphically by dividing it into three colors, firstly green represents there is less possibility of the son getting the disease, secondly yellow represents there may be any chance of son getting the disease and finally red represents there is high possibility of son getting the disease.

A Fuzzy Approach to Recognize Face Using Contourlet Transform

Face recognition addresses identification, verification, and authentication in biometric-based security systems. This work enhances the contrast and edges in face images and recognizes the face using contourlet transform and fuzzy rules. Contourlet transformed image provides multiscale and directional information. The transformed image is divided into low-pass image (low-frequency image) and band-pass image (high-frequency image). The low-pass image is enhanced using fuzzy-based histogram specification since it deals with contrast. Band-pass image contains detailed information about the edges of the image and are enhanced using fuzzy rules and morphological gradient operators. The proposed system achieves the accuracy rate of 99.81% and 99.35% on Yale-B and JAFEE dataset, respectively, which is better than the existing curvelet and wavelet transform-based recognition. The incorporation of fuzzy rules enhances the mean intensity value of the edges to 34.19, which is better than Canny, Sobel, Prewitt, Robert and Laplacian edge detection techniques. Finally Discriminant Correlation Analysis (DCA) feature level fusion is applied to fuse enhanced edge intensities and histogram features for Support Vector Machine (SVM) classification.

Optimized Hardware Design using Sobel and Median Filters for Lane Detection

In this paper, the image is received from the camera and the lane is sensed. There are various ways to detect lanes. Generally, the method of detecting edges uses a lot of the Sobel edge detection and the Canny edge detection. The minimum use of multiplication and division is used when designing for the hardware configuration. The images are tested using a black box image mounted on the vehicle. Because the top of the image of the used the black box is mostly background, the calculation process is excluded. Also, to speed up, YCbCr is calculated from the image and only the data for the desired color, white and yellow lane, is obtained to detect the lane. The median filter is used to remove noise from images. Intermediate filters excel at noise rejection, but they generally take a long time to compare all values. In this paper, by using addition, the time can be shortened by obtaining and using the result value of the median filter. In case of the Sobel edge detection, the speed is faster and noise sensitive compared to the Canny edge detection. These shortcomings are constructed using complementary algorithms. It also organizes and processes data into parallel processing pipelines. To reduce the size of memory, the system does not use memory to store all data at each step, but stores it using four line buffers. Three line buffers perform mask operations, and one line buffer stores new data at the same time as the operation. Through this work, memory can use six times faster the processing speed and about 33% greater quantity than other methods presented in this paper. The target operating frequency is designed so that the system operates at 50MHz. It is possible to use 2157fps for the images of 640by360 size based on the target operating frequency, 540fps for the HD images and 240fps for the Full HD images, which can be used for most images with 30fps as well as 60fps for the images with 60fps. The maximum operating frequency can be used for larger amounts of the frame processing.

Distance-Based Method used to Localize the Eyeball Effectively for Cerebral Palsy Rehabilitation.

Iris plays a vital role in human life for object identification. Many models and techniques were proposed and suggested for detecting the Iris, but the accuracy was not achieved up to the level and its frequently used for biometric application. The Proposed Work divided into two steps, at first, we detect the entire eye region outer layer by using mathematics first order derivatives by applying combinations of canny edge detection and circular hough transform. The next, we detect the inner portion of eye region that is Iris region is detected by combination of sobel edge detector and circular hough transform, As the results thereby reducing the error rate, marking the edges closest to the actual edges for maximizing the localization, indicating edges and also detect the inner and outer layer of the eye portions accurately. Finally this process is applied for cerebral palsy Children to detect the misalignment of eye and obtain the deviation position and results are compared with normal children eyes. In this context, image processing techniques are being recommended as a performance evaluation tool in cerebral palsy kids.

Using Neural Natural Network for Image Recognition in Bioinformatics

Automatic image recognition is very useful in bioinformatics. This article presents a novel technique to recognize the characters in the number plate automatically by using connected component analysis (CCA), artificial neural network (ANN) and neural natural network (Triple N). The preprocessing steps, Sobel edge detection technique and CCA are applied to the captured image of the vehicle to obtain character images. ANN technique can be used over these images to recognize the characters of the image in bioinformatics. The preprocessing steps are used to remove the noise and to enhance the image for recognizing the characters effectively. After performing the preprocessing steps, the edge detection technique and CCA are carried out to separate the character images from the whole image which can be recognized using ANN. These text characters can be compared with database to find authentication of vehicle, identifying the owner of the vehicle, penalty bill generation, etc.

UAV AND LIDAR IMAGE REGISTRATION: A SURF-BASED APPROACH FOR GROUND CONTROL POINTS SELECTION

Abstract. Multisource remote sensing image data provides synthesized information to support many applications including land cover mapping, urban planning, water resource management, and GIS modelling. Effectively utilizing such images however requires proper image registration, which in turn highly relies on accurate ground control points (GCP) selection. This study evaluates the performance of the interest point descriptor SURF (Speeded-Up Robust Features) for GCPs selection from UAV and LiDAR images. The main motivation for using SURF is due to it being invariant to scaling, blur and illumination, and partially invariant to rotation and view point changes. We also consider features generated by the Sobel and Canny edge detectors as complements to potentially increase the accuracy of feature matching between the UAV and LiDAR images. From our experiments, the red channel (Band-3) produces the most accurate and practical results in terms of registration, while adding the edge features seems to produce lacklustre results.

Segmentasi Region Of Interest (ROI) Garis Telapak Tangan Menggunakan Deteksi Tepi Sobel

The palm is one of the biometric characteristics that has been relatively recently investigated for identification and verification systems. The reason for using the palm geometry feature is, because the palm geometry is considered more resistant to external factors, such as weather, dry or wet palm conditions compared to using the characteristics of the palm lines that have difficult details and are susceptible to external factors. The problem that often arises in the self-recognition system is that it is easy to commit a crime against a person's identity if only by using something that is owned or something that is known to a system, using biometrics techniques is expected to minimize these frequent problems. Therefore, this study was made to implement the region of interest (ROI) segmentation method for palm line imagery using sobel edge detection, so that it can help for the initial process of identification and verification. the highest accuracy value on the right palm line image reached 87.01% and the lowest reached 86.46%, the highest accuracy value on the left palm line image reached 85.35% and the lowest reached 82.68%.

Comparative Performance Analysis of various Digital Image Edge Detection Techniques against Salt and Pepper Noise

The edge detection is a digital image processing technique to find the boundaries or edges of an image or object through the brightness discontinuity. There are many operators to get boundaries or edges but we need more effective and accurate methods. This paper will provide a comparison of Conventional Sobel, Prewitt, Roberts, Canny and Log Operators Edge Detector Techniques against Salt and Pepper noise With regard to Mean Square Error (MSE), Root Mean Square Error (RMSE), signal to noise ratio (SNR) , peak signal to noise ratio (PSNR) , mean-absolute error (MAE) and Bit error, etc.

Research on Coal-Rock Fracture Image Edge Detection Based on Tikhonov Regularization and Fractional Order Differential Operator

Aiming at the conventional image edge detection algorithm, the first-order differential edge detection method is easy to lose the image details and the second-order differential edge detection method is more sensitive to noise. To deal with the problem, the Tikhonov regularization method is adopted to reconstruct the input coal-rock infrared images, so as to reduce the noise interference, and then, the reconstructed image is transformed by gray level. Finally, we consider the frequency characteristics and long memory properties of fractional differential, the classical first-order Sobel and second-order Laplacian edge detection algorithms are extended to fractional order pattern, and a new pattern of fractional order differential image edge detection is constructed to realize the coal-rock fracture edge features identification. The results show that, compared with integer order differential, the error rate and omission rate of fractional order differential algorithm are smaller, the quality factor is larger, and the execution time and memory footprint are smaller. From the point of view of location criteria and location accuracy, the fractional order differential algorithm is better than the integer order. In addition, the proposed method is compared with Canny algorithm, B-spline wavelet transform, and multidirection fuzzy morphological edge detection method, can detect more coal-rock fracture infrared image edge details, and is more robust to noise.

Multi-stream CNN for facial expression recognition in limited training data

Limited data is a challenging problem to train Convolutional Neural Networks. On the other hand, acquiring a database in a demanded scale is not a straightforward task. In this paper, handcrafted features along with a multi-stream structure are proposed as a solution to improve performance of limited data via CNN. Three handcrafted features using local binary pattern code extractor and Sobel edge detection operator in horizontal and vertical directions of images have been extracted to apply to the multi-stream CNN model. Our model is based on two distinct structures including three-stream and single-stream structures. The three-stream structure can be employed to improve the recognition rate in facial expression classifiers when the training data is limited. In three-stream structure, each of information channels will be added to distinct streams separately. Furthermore, the transfer learning technique employed and behaviour of VGG16 architecture trained with limited data have been studied to be compared with the proposed method. In addition, input data is expanded by means of rotation, cropping, and flipping. Next, three-stream and single-stream structures are examined while using limited and also expanded training data. We have evaluated the mentioned system in order to compare it with state of the arts for CK+ and MUG databases in both limited-data and expanded-data. The results indicate that by using limited-data, recognition accuracy will be improved through the mentioned strategy. (92.19 to 88.95 in CK+ database and 85.4 to 82.5 in MUG database). Additionally, the performance was improved in comparison with benchmark methods.

Remote Sensing Image Enhancement Via Edge-Preserving Multiscale Retinex

Recently, an image enhancement receives a considerable research attention due to its wide application. In this paper, we propose a novel algorithm to enhance the contrast of remote sensing image while avoiding color distortion and detail loss. First, based on the Sobel operator strength, the local adaptive weighting parameter is obtained to penalize the fixed regularization parameter of original guided filtering. Then, the grayscale difference between flat patch and edge patch, which is caused by the fixed regularization parameter is amplified meanwhile without sacrificing the denoising performance. Finally, the Gaussian filtering of original multiscale retinex with color restoration is replaced with the guided filtering based on the Sobel edge detection operator to estimate the incident component of an image. Comparing with the previous algorithms, the proposed one can obtain more edge details and better color fidelity but with lower computational complexity and higher efficiency.

Realization of Internet of vehicles technology integrated into an augmented reality system

The goal of this study is to develop an internet of vehicles system with augmented reality technology. The system deals mainly with three subjects, namely, lane departure warning, forward collision detection and warning, and internet of vehicles. First, to deal with the subject of lane departure warning, the Hough transform is used in this study to extract the possible positions of lane lines from the region of interest of an image. The Kalman filter is further employed to remove noises and estimate the actual positions of car lane lines. The lane departure decision is then used to determine whether a lane departure situation occurs. Second, the Sobel edge detector and taillight detection method are used to locate the hypothetical region of the vehicle. The characteristic parameters within the hypothetical region can also be obtained through the Harris corner detection method. To verify the hypothetical region and identify the vehicle, the support vector machine algorithm is used. The collision decision is then applied to determine whether the distance between two vehicles is short, thus fulfilling the goal of forward collision detection and warning. In addition, a secure and easy-to-use internet of vehicles is achieved with the use of the Rivest–Shamir–Adleman encryption algorithm, which uses public and secret keys to encrypt and decrypt messages to achieve the task of user identification. Upon obtaining control of the vehicle, the driver has full access to the most up-to-date information provided by the driver assistance system. Finally, internet of vehicles applications incorporating the previously mentioned methods, smart glasses, and augmented reality are implemented in this study. Smart glasses provide the drivers easy access to information about the vehicle and warnings, which helps enhance driver convenience and safety considerably.

Identification of Virus in Microscopic Image Using Genetic Algorithm

In this paper describes a several techniques of effective edge detection by using image segmentation. The image segmentation provides various techniques to detect the edges on image. The paper mainly focused on edge detection using matlab parameters and solved the many problems. Edge detection techniques have a several type of techniques. We have taken microscopic image, which affects the human body by making diseases through viruses and bacteria’s. Now analyze only about the major techniques: a.) Roberts edge detection, b) sobel edge detection, c) prewitt edge detection, d) log (laplacian of gaussian) edge detection, e) genetic edge detection and f) canny edge detection. We have applied above five techniques which are used in edge detection and got a result on microscopic images. Hence, we scope this paper defines and compares the variety of techniques and demand assures the genetic algorithm provides a better performance on edge detection using microscopic image.

A Study on Parallel and Pipelining Simulation Techniques for Edge Detection and Their Performance Analysis

Real processing components along with component simulators are combined together to construct a new virtual prototyping system. The increase in component simulators result in degraded performance of the simulation in distributed systems. The speed of simulation can be increased by doing parallel simulation techniques. Prime number test and Image edge detection are chosen to implement the parallel simulation techniques and achieved the expected results while implementing in real time applications. The prime number test calculates the number of processors in a system and the image edge detection can be done in two stages by Canny Edge detection and Sobel Edge detection. The Canny Edge detection is used to detect the edges in the images by using a multi-stage algorithm. The smaller, separable and integer valued filter in images are combined in horizontal and vertical directions by using the Sobel edge detection resulting in reduction of implementation cost. The tool named OpenMP is used for implementing the parallel simulation techniques by combining both the canny edge and Sobel edge detection. An add-on named MPI is used along with the OpenMP to reduce the implementation time in parallel processing.

Integer-Value Encoding for Approximate On-Chip Communication

Approximate computing has been broadly investigated in the computing domain to maintain the benefits of technology scaling. Recently, it has been extended to the communication domain. The idea is to trade transmission quality for energy or/and performance efficiency. Exploiting the integer-value representation of the transmitted signals in parallel buses, we propose two memoryless encoding approaches for approximate communications in order to reduce the integer value deviation. First, restricted to area-constrained applications, we propose a Combined Integer-Value (CIV) coding technique based on the swap and inversion of the input signals. Second, a Crosstalk-Avoidance-based Integer-Value (CAIV) coding technique for applications with a more relaxed area constraint is presented. The optimal mapping of the data words and codewords combined with the selective inversion of the input signals minimize the error magnitude in this coding technique. A comprehensive experimental result using a 65 nm commercial technology evaluates the proposed coding approaches. For example, our proposed CIV coding scheme improves the quality of the received images and the sampled radio communication signals with different modulation up to factor of 2 8 and 2 7 , respectively, as it compares with conventional transmission of signals with no coding. CAIV coder can improve the data transmission accuracy by about 2 18 as it compares with the conventional transmission. Furthermore, to assess the applicability of the proposed encoders, we carried out two case studies employing the scale-invariant feature transform algorithm and SOBEL edge detector.

Plant disorder precognition by image based pattern recognition

Abstract Proliferating population in the world has ushered a lot of burden on resources in agriculture. In order to sustain the population and the economy, it is very important to obtain maximum yield from crops. Diseases in plants are the chief cause of damage in plants which leads to production loss in agriculture. Earlier disease detection is manual, where farmers refer guide books or use their experiences to recognize the diseases. This process is time-consuming and requires some knowledge for selection of pesticides. Capturing images of leaves and processing them with the help of an automated system to identify the disease infected leaves could be a better solution for farmers. This paper discuss about how image processing and machine learning is effectively used in detection of diseases in plants. Analysis is done with various classification techniques and the comparison is made between Active contour and Sobel edge detection techniques. Experimental results indicate that Multiclass Support Vector Machines combined with Active contour edge detection gives better results compared to other methods for disease classification.