No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Flag Identification Using Support Vector Machine
... This adjustment makes the distribution of the intensity is better than the original image histogram. This allows low contrast area of image to become better contrasted area by spreading out the most frequently intensity value 12,13 . Histogram equalization steps are discussed in details in the following lines. ...
... 3: Calculate the Cumulative Distribution Function (CDF) for each bovine muzzle image using equation (2): a= 0,......N -1 , 0 ≤ ≤ 1 4: Calculate Histogram Equalization (HEQ) gray level value to gray level for each input bovine muzzle image using equation (3) 5: change gray level by calculating histogram equalization algorithm using equation (4). Mean in this equation show the distance between and +1 has a direct relation with PDF of input bovine image at gray level [13]. 6: return gray level value for each bovine muzzle image. ...
Bovines muzzle classification is considered as a biometric classifier to maintain the safety of bovines and guarantee the livestock products. This paper presents two different bovines classifications models using Artificial Neural Network (ANN) and K-Nearest Neighbor Classifier (KNN). The proposed ANN model consists of three phases; pre-processing, feature extraction and classifications. Pre-processing techniques; histogram equalization and mathematical morphology filtering has been used. The ANN model use Segmentation-based Fractal Texture Analysis (SFTA) for extract muzzle features. The proposed KNN model consists of two phases; Expectation Maximization image segmentation and classification. Expectation Maximization image segmentation (EM) depends on extracts bovine image color and texture feature extraction. The experimental result evaluation proves the advancement of KNN model than ANN as it achieves 100% classification accuracy in case of increase number of classification groups to twenty-five compared to 92.76% classification accuracy achieved from ANN classification model.
... A decision plane is one that separate set of object which has different class membership. MSVMs depending on finding the support vectors that calculate the separators giving the widest separation of classes (Rahman et al., 2013). This paper presents robust cattle classification system that uses MSVMs for calculating the similarity score between the input cattle muzzle print image and the template one. ...
... Equation (4) means that distance between S k and S k + 1 has direct relation with PDF of the input image at grey level r k (Rahman et al., 2013). ...
Cattle muzzle classification can be considered as a biometric identifier to maintain the livestock and guarantee the safety of cattle products. This paper presents a muzzle-based classification system using multiclass support vector machines (MSVMs). The proposed MSVMs system consists of three phases; namely preprocessing, feature extraction and classifications. Preprocessing techniques; histogram equalisation and mathematical morphology filtering have been used to increase image contrast and removing noise respectively. The proposed system uses box-counting algorithm for detecting feature of each muzzle image. For a strong classification system and achieving more accurate classification result, MSVMs has been used. The experimental evaluation prove the advancement of the presented system as it achieve 96% classification accuracy in case of increase number of classified group to ten groups compared to 90% classification accuracy achieved by traditional classification system.
... For the recognition of human gender, a dataset of labeled face image can be used to train a multi-class SVM and to predict the gender of a new face image. A technique is selected based on the dataset's size as well as the desired accuracy of the classifier [47]. Figure 8 presents an image of a dataset belonging to two classes that are selected by the SVM method as the best hyper surface for their separation. . ...
In the realm of robotics and interactive systems, gender recognition is a crucial problem. Considering the several uses it has in security, web search, human-computer interactions, etc., gender recognition from facial photos has garnered a lot of attention. The need to use and enhance gender recognition techniques is felt more strongly today due to a significant development in the design of facial recognition systems. Relatively speaking to other approaches, the progress gained in this area thus far is not exceptional. Thus, a novel method has been adopted in this study to improve accuracy in comparison to earlier research. To create the best rate of accuracy and efficiency in the suggested method of this research, we choose a minimal set of characteristics. Testing on the FERET and UTK-Face datasets reveals that our suggested algorithm has a lower degree of inaccuracy. In this article, the input image of the person's face is pre-processed to extract the right features from the face once the person's face has been recognized. Gender separation is achieved using Multi-class Support Vector Machine (SVM) Classifiers after features from normalized images have been extracted using Histogram Oriented Gradient (HOG), Gabor Filters, and Speeded Up Robust Features (SURF), as well as their combination to select the most appropriate feature from them as input for gender classification. As a feature reduction feature, the Principal Component Analysis (PCA) algorithm is also employed. Using the proposed approach, 98.75% gender recognition precision has been accomplished on the FERET database and a runtime performance of 0.4 Sec. on the UTK-Face database, 97.43% gender recognition accuracy has been accomplished and a runtime performance of 0.5 Sec.
... The adjustment of the intensities after applying histogram equalization on image makes the cattle muzzle image intensity better than the original one. This allow the low contrast area of image to become high contrast by spreading the most frequently intensity values [21,22]. HEQ algorithm is discussed in details in the following lines. ...
Animal agricultures pays a great attention for saving the cattle because of the rapid growth of the livestock. The critical point in this research is to classify large different groups of cattle's with high degree of accuracy. This paper presents cattle classification model depending on decision tree classifier. Such model consists of three parts; pre-processing part, texture feature extraction part and classification part. Pre-processing part consists of histogram equalization used to increase image contrast and mathematical morphology filtering to remove noise. The second part uses two different algorithms in order to extract image features; box-counting and segmentation based fractal texture analysis (SFTA). Then the decision tree is applied for the classification process. The used data base consists of fifty-two different cattle with sixty different images for each cattle. Experimental results prove the advancement of decision tree classifier than other classifiers techniques. The result of decision tree is compared with artificial neural networks (ANNs). For fifty-two different groups the accuracy rate in case of decision tree is 96.39% compared to 14% in case of using ANN classification system.
... Rahman, Z. et. al. [2] proposed a method to identify flags based on Support Vector Machine (SVM) where the machine is trained with percentage of different colors in the flag. After image acquisition and pre-processing they compute a database that consists of color percentage of 9 different colors in the flag and an additional information which is the label. ...
Free access : http://www.ijcaonline.org/archives/volume149/number11/lodh-2016-ijca-911587.pdf
... S. Lu shows the application of multilayer neural network in traffic sign recognition [15]. Maldonado-Bascn, Saturnino et al. in their article [16] presented an automatic road-sign detection and recognition system based on support vector machines (SVMs) as one of the main advantages of the SVM over other networks is that its training is performed through the solution of a linearly constrained convex quadratic programming problem [14,21]. Traffic sign identification system has actually two part [7,23]: detection and recognition. ...
Traffic sign recognition is a major part of an automated intelligent driving vehicle or driver assistance systems.Perfect recognition of traffic sign helps an intelligent driving system giving valuable information about road signs,warnings, prohibitions thus increasing driving speed, security and decreasing risk of accident. Many techniques have been used for recognising traffic signs such as backpropagation neural network,support vector machines ,convolutional neural network etc on different shaped signs. Fuzzy inference system has not been used in deep for this purpose. In this paper, we have tried to find out the capability of adap-tive neuro fuzzy inference system(ANFIS) for traffic sign recognition. We have used video and image processing for detecting circular shaped signs and used ANFIS for recognizing detected signs.
Because of the non-rigid characteristics of flags, they cannot be easily identified under conditions of deformation, obstruction and changes in light intensity. Therefore, we build a picture dataset containing flags of different scales, styles, occlusion, deformations, lighting conditions. We propose a flag recognition algorithm based on convolutional neural network (CNN). We use a 1x1 convolutional layer structure to replace the traditional full-connected layer in order to improve the network performance. By analyzing the distribution of flags in the test sample we propose a region proposal rule based on multi-scale matching strategy for flag detection.
In complex scene, the exact determination and division of color is the key to color flag recognition tasks. Aiming at the problem that the traditional recognition methods have low recognition accuracy and can not be identified in complex scene and multi-targets, this paper proposes a color threshold determination (CTD) method to identify color flag. Firstly, the color sample data set under different light conditions is constructed, and the filtering of the noise pixels is realized by the projection method in the HSV color space to obtain the final color decision threshold. Secondly, color decision is made for each pixel in the candidate region of interest detected by Gentle Adaboost cascade classifier based on HOG feature. Finally, the color feature is matched by the preset threshold, and the matching region is retained to obtain the final recognition results. Experiments show that the proposed approach has better performance in the color flag recognition task under complex scene. The recognition accuracy was 97.1%, the sensitivity was 90.70% and the specificity was 99.33%.
Cattle Feature Extraction is the critical point in this paper which is considered as a continual research for authors. The biometric identifier of cattle is its muzzle. Today, Veterinarians search for new technologies to save cattle's livestock. This paper presents Artificial Neural Networks (ANNs) as the identification model. The proposed model contains the following three parts: pre-processing, Feature Extraction and Cattle Identifications. Pre-processing techniques are histogram equalization and mathematical morphology filtering. The proposed model compares between the following two feature extraction algorithms: Box-Counting Algorithm and Segmentation-based Fractal Texture Analysis (SFTA). Box-Counting Algorithm gives a feature vector of eight features and SFTA gives eighteen features for each cattle image. For achieving more accurate results in the identification part, ANNs have been used. This paper also uses the supervised learning technique in which the main factor is external teacher. The experimental results showed that SFTA Algorithm has achieved the best accuracy among all other identification techniques and our approach is superior than the existed work as our work achieves 99.97% identification accuracy.
An abstract is not available.
We propose an interactive system for identifying flags in photos taken from natural scenes. The system is interactive in two respects. First, because segmentation can be a difficult problem, users are asked to crop the flag portion from a photo. Second, the user makes the final decision by selecting one of the top choices obtained from the machine classification system. The proposed system utilizes a color-based image retrieval technique. For experimental purposes a large number of flag images are synthetically generated from a small number of original ones in order to increase the reference image database. A nearest neighbor classifier produces a sorted list of candidate choices. Recognition accuracy of these choices varies from 82% to 93% depending on whether the correct flag is among the first 8 or 18 top choices, respectively, from a set of 186 flags.
In this paper, we extract our proposed RSC features from leaf images and use SVM classifier to implement an automated leaf recognition system for plant leaf identification and classification. Automatic plant species identification and classification is helpful in biology, forest and agriculture to study and discover new species in plant in botanical gardens and is also used to recognize the medicinal plants to prepare herbal medicines. Here, 300 leaf features are extracted from a single leaf of 624 leaf dataset to classify 23 different kinds of plant species with an average accuracy of 95%. Compared with other approaches, our proposed algorithm has less time complexity and is easy to implementation with higher accuracy.
Thesupport-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
The present thesis can take its place among the numerous doctoral theses and other publications that are currently revolutionizing the area of machine learning. The author's basic concern is with kernel-based methods and in particular Support Vector algorithms for regression estimation for the solution of inverse, often ill- posed problems. However, Alexander Smola's thesis stands out from many of the other publications in this field. This is due in part to the author's profound theoretical penetration of his subject-matter, but also and in particular to the wealth of detailed results he has included. Especially neat and of particular relevance are the algorithmic extensions of Support Vector Machines, which can be combined as building blocks, thus markedly improving the Support Vectors. Of substantial interest is also the very elegant unsupervised method for nonlinear feature extraction, which applies the kernel-based method to classical Principal Component Analysis (kernel PCA). And although only designed to illustrate the theoretical results, the practical applications the author gives us from the area of high-energy physics and time-series analysis are highly convincing. In many respects the thesis is groundbreaking, but it is likely to soon become a frequently cited work for numerous innovative applications from the field of statistical machine learning and for improving our theoretical understanding of Support Vector Machines.
The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data. High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Convergence of a generalized version of the modified SMO algorithms given by Keerthi et al. for SVM classifier design is proved. The convergence results are also extended to modified SMO algorithms for solving -SVM classifier problems.
This book is the first comprehensive introduction to Support Vector Machines (SVMs), a new generation learning system based on recent advances in statistical learning theory. The book also introduces Bayesian analysis of learning and relates SVMs to Gaussian Processes and other kernel based learning methods. SVMs deliver state-of-the-art performance in real-world applications such as text categorisation, hand-written character recognition, image classification, biosequences analysis, etc. Their first introduction in the early 1990s lead to a recent explosion of applications and deepening theoretical analysis, that has now established Support Vector Machines along with neural networks as one of the standard tools for machine learning and data mining. Students will find the book both stimulating and accessible, while practitioners will be guided smoothly through the material required for a good grasp of the theory and application of these techniques. The concepts are introduced gradually in accessible and self-contained stages, though in each stage the presentation is rigorous and thorough. Pointers to relevant literature and web sites containing software ensure that it forms an ideal starting point for further study. Equally the book will equip the practitioner to apply the techniques and an associated web site will provide pointers to updated literature, new applications, and on-line software.
Digital Image Processing
- C Rafael
- Gonzalez
Rafael C. Gonzalez, " Digital Image Processing ".
[12] " Flag " -(http://www.flags.net)-accessed on 28 April-2012.
Guide to Flags of the World
- Firefly
FireFly, "Guide to Flags of the World", Published by Firefly Books Ltd.
2003 ISBN 1-55297-813-3.