Search results for: image classification

Authors: A. Rakhmadi, M. S. M. Rahim, A. Bade, H. Haron, I. M. Amin

Abstract:

In this study, a Loop Back Algorithm for component connected labeling for detecting objects in a digital image is presented. The approach is using loop back connected component labeling algorithm that helps the system to distinguish the object detected according to their label. Deferent than whole window scanning technique, this technique reduces the searching time for locating the object by focusing on the suspected object based on certain features defined. In this study, the approach was also implemented for a face detection system. Face detection system is becoming interesting research since there are many devices or systems that require detecting the face for certain purposes. The input can be from still image or videos, therefore the sub process of this system has to be simple, efficient and accurate to give a good result.

Keywords: Image processing, connected components labeling, face detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2300

Authors: G. Schirripa Spagnolo, M. De Santis

Abstract:

The protection of the contents of digital products is referred to as content authentication. In some applications, to be able to authenticate a digital product could be extremely essential. For example, if a digital product is used as a piece of evidence in the court, its integrity could mean life or death of the accused. Generally, the problem of content authentication can be solved using semifragile digital watermarking techniques. Recently many authors have proposed Computer Generated Hologram Watermarking (CGHWatermarking) techniques. Starting from these studies, in this paper a semi-fragile Computer Generated Hologram coding technique is proposed, which is able to detect malicious tampering while tolerating some incidental distortions. The proposed technique uses as watermark an encrypted image, and it is well suitable for digital image authentication.

Keywords: Asymmetric cryptography, Semi-Fragile watermarking, Image authentication, Hologram watermark, Public- Key Cryptography, RSA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1609

Authors: A. Buzzanca, G. Castellano, A.M. Fanelli

Abstract:

In this paper we address the problem of musical style classification, which has a number of applications like indexing in musical databases or automatic composition systems. Starting from MIDI files of real-world improvisations, we extract the melody track and cut it into overlapping segments of equal length. From these fragments, some numerical features are extracted as descriptors of style samples. We show that a standard Bayesian classifier can be conveniently employed to build an effective musical style classifier, once this set of features has been extracted from musical data. Preliminary experimental results show the effectiveness of the developed classifier that represents the first component of a musical audio retrieval system

Keywords: Musical style, Bayesian classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1297

Authors: Mohammad A. Khasawneh

Abstract:

Asphalt concrete pavements gradually lose their skid resistance causing safety problems especially under wet conditions and high driving speeds. In order to enact the actual field polishing and wearing process of asphalt pavement surfaces in a laboratory setting, several laboratory-scale accelerated polishing devices were developed by different agencies. To mimic the actual process, friction and texture measuring devices are needed to quantify surface deterioration at different polishing intervals that reflect different stages of the pavement life. The test could still be considered lengthy and to some extent labor-intensive. Therefore, there is a need to come up with another method that can assist in investigating the bituminous pavement surface characteristics in a practical and time-efficient test procedure.

The purpose of this paper is to utilize a well-developed image analysis technique to characterize asphalt pavement surfaces without the need to use conventional friction and texture measuring devices in an attempt to shorten and simplify the polishing procedure in the lab.

Promising findings showed the possibility of using image analysis in lieu of the labor-sensitive-variable-in-nature friction and texture measurements. It was found that the exposed aggregate surface area of asphalt specimens made from limestone and gravel aggregates produced solid evidence of the validity of this method in describing asphalt pavement surfaces. Image analysis results correlated well with the British Pendulum Numbers (BPN), Polish Values (PV) and Mean Texture Depth (MTD) values.

Keywords: Friction, Image Analysis, Polishing, Statistical Analysis, Texture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2561

Authors: R. Rama Kishore, Sunesh

Abstract:

This paper presents an optimized, robust, and secured watermarking technique. The methodology used in this work is the combination of entropy and chaotic grid map. The proposed methodology incorporates Discrete Cosine Transform (DCT) on the host image. To improve the imperceptibility of the method, the host image DCT blocks, where the watermark is to be embedded, are further optimized by considering the entropy of the blocks. Chaotic grid is used as a key to reorder the DCT blocks so that it will further increase security while selecting the watermark embedding locations and its sequence. Without a key, one cannot reveal the exact watermark from the watermarked image. The proposed method is implemented on four different images. It is concluded that the proposed method is giving better results in terms of imperceptibility measured through PSNR and found to be above 50. In order to prove the effectiveness of the method, the performance analysis is done after implementing different attacks on the watermarked images. It is found that the methodology is very strong against JPEG compression attack even with the quality parameter up to 15. The experimental results are confirming that the combination of entropy and chaotic grid map method is strong and secured to different image processing attacks.

Keywords: Digital watermarking, discrete cosine transform, chaotic grid map, entropy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 719

Authors: Iman Elyasi, Sadegh Zarmehi

Abstract:

Due to some reasons, observed images are degraded which are mainly caused by noise. Recently image denoising using the wavelet transform has been attracting much attention. Waveletbased approach provides a particularly useful method for image denoising when the preservation of edges in the scene is of importance because the local adaptivity is based explicitly on the values of the wavelet detail coefficients. In this paper, we propose several methods of noise removal from degraded images with Gaussian noise by using adaptive wavelet threshold (Bayes Shrink, Modified Bayes Shrink and Normal Shrink). The proposed thresholds are simple and adaptive to each subband because the parameters required for estimating the threshold depend on subband data. Experimental results show that the proposed thresholds remove noise significantly and preserve the edges in the scene.

Keywords: Image denoising, Bayes Shrink, Modified Bayes Shrink, Normal Shrink.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2473

Authors: Mohamed Gouskir, Belaid Bouikhalene, Hicham Aissaoui, Benachir Elhadadi

Abstract:

In this paper, we present an application of Riemannian geometry for processing non-Euclidean image data. We consider the image as residing in a Riemannian manifold, for developing a new method to brain edge detection and brain extraction. Automating this process is a challenge due to the high diversity in appearance brain tissue, among different patients and sequences. The main contribution, in this paper, is the use of an edge-based anisotropic diffusion tensor for the segmentation task by integrating both image edge geometry and Riemannian manifold (geodesic, metric tensor) to regularize the convergence contour and extract complex anatomical structures. We check the accuracy of the segmentation results on simulated brain MRI scans of single T1-weighted, T2-weighted and Proton Density sequences. We validate our approach using two different databases: BrainWeb database, and MRI Multiple sclerosis Database (MRI MS DB). We have compared, qualitatively and quantitatively, our approach with the well-known brain extraction algorithms. We show that using a Riemannian manifolds to medical image analysis improves the efficient results to brain extraction, in real time, outperforming the results of the standard techniques.

Keywords: Riemannian manifolds, Riemannian Tensor, Brain Segmentation, Non-Euclidean data, Brain Extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1662

Authors: Atiqul Islam, Shamim Akhter, Tumnun E. Mursalin

Abstract:

Least Development Countries (LDC) like Bangladesh, whose 25% revenue earning is achieved from Textile export, requires producing less defective textile for minimizing production cost and time. Inspection processes done on these industries are mostly manual and time consuming. To reduce error on identifying fabric defects requires more automotive and accurate inspection process. Considering this lacking, this research implements a Textile Defect Recognizer which uses computer vision methodology with the combination of multi-layer neural networks to identify four classifications of textile defects. The recognizer, suitable for LDC countries, identifies the fabric defects within economical cost and produces less error prone inspection system in real time. In order to generate input set for the neural network, primarily the recognizer captures digital fabric images by image acquisition device and converts the RGB images into binary images by restoration process and local threshold techniques. Later, the output of the processed image, the area of the faulty portion, the number of objects of the image and the sharp factor of the image, are feed backed as an input layer to the neural network which uses back propagation algorithm to compute the weighted factors and generates the desired classifications of defects as an output.

Keywords: Computer vision, image acquisition device, machine vision, multi-layer neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3301

Authors: Bence Kővári, ZSolt Kertész

Abstract:

This paper proposes a stroke extraction method for use in off-line signature verification. After giving a brief overview of the current ongoing researches an algorithm is introduced for detecting and following strokes in static images of signatures. Problems like the handling of junctions and variations in line width and line intensity are discussed in detail. Results are validated by both using an existing on-line signature database and by employing image registration methods.

Keywords: Stroke extraction, spline fitting, off-line signatureverification, image registration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1977

Authors: Haoyu Ma, Bin Hu, Mike Jackson, Jingzhi Yan, Wen Zhao

Abstract:

In this paper we propose a new classification method for automatic sleep scoring using an artificial neural network based decision tree. It attempts to treat sleep scoring progress as a series of two-class problems and solves them with a decision tree made up of a group of neural network classifiers, each of which uses a special feature set and is aimed at only one specific sleep stage in order to maximize the classification effect. A single electroencephalogram (EEG) signal is used for our analysis rather than depending on multiple biological signals, which makes greatly simplifies the data acquisition process. Experimental results demonstrate that the average epoch by epoch agreement between the visual and the proposed method in separating 30s wakefulness+S1, REM, S2 and SWS epochs was 88.83%. This study shows that the proposed method performed well in all the four stages, and can effectively limit error propagation at the same time. It could, therefore, be an efficient method for automatic sleep scoring. Additionally, since it requires only a small volume of data it could be suited to pervasive applications.

Keywords: Sleep, Sleep stage, Automatic sleep scoring, Electroencephalography, Decision tree, Artificial neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2072

Authors: Zied Trifa, Maher Khemakhem

Abstract:

The survey and classification of the different security attacks in structured peer-to-peer (P2P) overlay networks can be useful to computer system designers, programmers, administrators, and users. In this paper, we attempt to provide a taxonomy of structured P2P overlay networks security attacks. We have specially focused on the way these attacks can arise at each level of the network. Moreover, we observed that most of the existing systems such as Content Addressable Network (CAN), Chord, Pastry, Tapestry, Kademlia, and Viceroy suffer from threats and vulnerability which lead to disrupt and corrupt their functioning. We hope that our survey constitutes a good help for who-s working on this area of research.

Keywords: P2P, Structured P2P Overlay Networks, DHT, Security, classification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1764

Authors: U. Bottigli, M.Carpinelli, P.L. Fiori, B. Golosio, A. Marras, G. L. Masala, P. Oliva

Abstract:

The counting process of cell colonies is always a long and laborious process that is dependent on the judgment and ability of the operator. The judgment of the operator in counting can vary in relation to fatigue. Moreover, since this activity is time consuming it can limit the usable number of dishes for each experiment. For these purposes, it is necessary that an automatic system of cell colony counting is used. This article introduces a new automatic system of counting based on the elaboration of the digital images of cellular colonies grown on petri dishes. This system is mainly based on the algorithms of region-growing for the recognition of the regions of interest (ROI) in the image and a Sanger neural net for the characterization of such regions. The better final classification is supplied from a Feed-Forward Neural Net (FF-NN) and confronted with the K-Nearest Neighbour (K-NN) and a Linear Discriminative Function (LDF). The preliminary results are shown.

Keywords: Automatic cell counting, neural network, region growing, Sanger net.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1461

Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Abstract:

Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies  the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.

Keywords: Retail stores, Faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 584

Authors: Hossein Mirzaee, Farhad Besharati

Abstract:

Solar sunspot rotation, latitudinal bands are studied based on intelligent computation methods. A combination of image fusion method with together tree decomposition is used to obtain quantitative values about the latitudes of trajectories on sun surface that sunspots rotate around them. Daily solar images taken with SOlar and Heliospheric (SOHO) satellite are fused for each month separately .The result of fused image is decomposed with Quad Tree decomposition method in order to achieve the precise information about latitudes of sunspot trajectories. Such analysis is useful for gathering information about the regions on sun surface and coordinates in space that is more expose to solar geomagnetic storms, tremendous flares and hot plasma gases permeate interplanetary space and help human to serve their technical systems. Here sunspot images in September, November and October in 2001 are used for studying the magnetic behavior of sun.

Keywords: Quad tree decomposition, sunspot image.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1251

Authors: K. A. D. N. K Wimalawarne

Abstract:

In this paper we introduce a novel kernel classifier based on a iterative shrinkage algorithm developed for compressive sensing. We have adopted Bregman iteration with soft and hard shrinkage functions and generalized hinge loss for solving l1 norm minimization problem for classification. Our experimental results with face recognition and digit classification using SVM as the benchmark have shown that our method has a close error rate compared to SVM but do not perform better than SVM. We have found that the soft shrinkage method give more accuracy and in some situations more sparseness than hard shrinkage methods.

Keywords: Compressive sensing, Bregman iteration, Generalisedhinge loss, sparse, kernels, shrinkage functions

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1378

Authors: Kaewkarn Phuangsombat, Arthit Phuangsombat, Anupun Terdwongworakul

Abstract:

Hard seeds will not grow and can cause mold in sprouting process. Thus, the hard seeds need to be separated from the normal seeds. Near infrared hyperspectral imaging in a range of 900 to 1700 nm was implemented to develop a model by partial least squares discriminant analysis to discriminate the hard seeds from the normal seeds. The orientation of the seeds was also studied to compare the performance of the models. The model based on hilum-up orientation achieved the best result giving the coefficient of determination of 0.98, and root mean square error of prediction of 0.07 with classification accuracy was equal to 100%.

Keywords: Mung bean, near infrared, germinatability, hard seed.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1162

Authors: Yi-Feng Su, Chia-Tseng Chen, Hsueh-Lung Liao

Abstract:

The objective of this research is to develop an advanced driver assistance system characterized with the functions of lane departure warning (LDW), forward collision warning (FCW) and adaptive front-lighting system (AFS). The system is mainly configured a CCD/CMOS camera to acquire the images of roadway ahead in association with the analysis made by an image-processing unit concerning the lane ahead and the preceding vehicles. The input image captured by a camera is used to recognize the lane and the preceding vehicle positions by image detection and DROI (Dynamic Range of Interesting) algorithms. Therefore, the system is able to issue real-time auditory and visual outputs of warning when a driver is departing the lane or driving too close to approach the preceding vehicle unwittingly so that the danger could be prevented from occurring. During the nighttime, in addition to the foregoing warning functions, the system is able to control the bending light of headlamp to provide an immediate light illumination when making a turn at a curved lane and adjust the level automatically to reduce the lighting interference against the oncoming vehicles driving in the opposite direction by the curvature of lane and the vanishing point estimations. The experimental results show that the integrated vehicle image system is robust to most environments such as the lane detection and preceding vehicle detection average accuracy performances are both above 90 %.

Keywords: Lane mark detection, lane departure warning (LDW), dynamic range of interesting (DROI), forward collision warning (FCW), adaptive front-lighting system (AFS).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2157

Authors: Ksheeraj Sai Vepuri, Nada Attar

Abstract:

We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.

Keywords: Facial expression recognition, image pre-processing, deep learning, CNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 544

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: Convolutional Neural Network, Deep Learning, Deep Learning Based FER, Facial Emotion Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1373

Authors: F. Smach, M. Atri, J. Mitéran, M. Abid

Abstract:

Face detection and recognition has many applications in a variety of fields such as security system, videoconferencing and identification. Face classification is currently implemented in software. A hardware implementation allows real-time processing, but has higher cost and time to-market. The objective of this work is to implement a classifier based on neural networks MLP (Multi-layer Perceptron) for face detection. The MLP is used to classify face and non-face patterns. The systm is described using C language on a P4 (2.4 Ghz) to extract weight values. Then a Hardware implementation is achieved using VHDL based Methodology. We target Xilinx FPGA as the implementation support.

Keywords: Classification, Face Detection, FPGA Hardware description, MLP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2281

Authors: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: Pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1283

Authors: Farshideh Einsele, Hassan Foroosh

Abstract:

In this paper, we present a robust algorithm to recognize extracted text from grocery product images captured by mobile phone cameras. Recognition of such text is challenging since text in grocery product images varies in its size, orientation, style, illumination, and can suffer from perspective distortion. Pre-processing is performed to make the characters scale and rotation invariant. Since text degradations can not be appropriately defined using well-known geometric transformations such as translation, rotation, affine transformation and shearing, we use the whole character black pixels as our feature vector. Classification is performed with minimum distance classifier using the maximum likelihood criterion, which delivers very promising Character Recognition Rate (CRR) of 89%. We achieve considerably higher Word Recognition Rate (WRR) of 99% when using lower level linguistic knowledge about product words during the recognition process.

Keywords: Camera-based OCR, Feature extraction, Document and image processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2470

Authors: Dragos Nicolae VIZIREANU

Abstract:

One of the main image representations in Mathematical Morphology is the 3D Shape Decomposition Representation, useful for Image Compression and Representation,and Pattern Recognition. The 3D Morphological Shape Decomposition representation can be generalized a number of times,to extend the scope of its algebraic characteristics as much as possible. With these generalizations, the Morphological Shape Decomposition 's role to serve as an efficient image decomposition tool is extended to grayscale images.This work follows the above line, and further develops it. Anew evolutionary branch is added to the 3D Morphological Shape Decomposition's development, by the introduction of a 3D Multi Structuring Element Morphological Shape Decomposition, which permits 3D Morphological Shape Decomposition of 3D binary images (grayscale images) into "multiparameter" families of elements. At the beginning, 3D Morphological Shape Decomposition representations are based only on "1 parameter" families of elements for image decomposition.This paper addresses the gray scale inter frame interpolation by means of mathematical morphology. The new interframe interpolation method is based on generalized morphological 3D Shape Decomposition. This article will present the theoretical background of the morphological interframe interpolation, deduce the new representation and show some application examples.Computer simulations could illustrate results.

Keywords: 3D shape decomposition representation, mathematical morphology, gray scale interframe interpolation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1745

Authors: Indradip Banerjee, Souvik Bhattacharyya, Gautam Sanyal

Abstract:

‘Steganalysis’ is one of the challenging and attractive interests for the researchers with the development of information hiding techniques. It is the procedure to detect the hidden information from the stego created by known steganographic algorithm. In this paper, a novel feature based image steganalysis technique is proposed. Various statistical moments have been used along with some similarity metric. The proposed steganalysis technique has been designed based on transformation in four wavelet domains, which include Haar, Daubechies, Symlets and Biorthogonal. Each domain is being subjected to various classifiers, namely K-nearest-neighbor, K* Classifier, Locally weighted learning, Naive Bayes classifier, Neural networks, Decision trees and Support vector machines. The experiments are performed on a large set of pictures which are available freely in image database. The system also predicts the different message length definitions.

Keywords: Steganalysis, Moments, Wavelet Domain, KNN, K*, LWL, Naive Bayes Classifier, Neural networks, Decision trees, SVM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2572

Authors: Tonislav Ivanov, Oleksii Nedashkivskyi, Denis Babeshko, Vadim Pinskiy, Matthew Putman

Abstract:

Training a machine learning model for object detection that generalizes well is known to benefit from a training dataset with diverse examples. However, training datasets usually contain many repeats of common examples of a class and lack rarely seen examples. This is due to the process commonly used during human annotation where a person would proceed sequentially through a list of images labeling a sufficiently high total number of examples. Instead, the method presented involves an active process where, after the initial labeling of several images is completed, the next subset of images for labeling is selected by an algorithm. This process of algorithmic image selection and manual labeling continues in an iterative fashion. The algorithm used for the image selection is a deep learning algorithm, based on the U-shaped architecture, which quantifies the presence of unseen data in each image in order to find images that contain the most novel examples. Moreover, the location of the unseen data in each image is highlighted, aiding the labeler in spotting these examples. Experiments performed using semiconductor wafer data show that labeling a subset of the data, curated by this algorithm, resulted in a model with a better performance than a model produced from sequentially labeling the same amount of data. Also, similar performance is achieved compared to a model trained on exhaustive labeling of the whole dataset. Overall, the proposed approach results in a dataset that has a diverse set of examples per class as well as more balanced classes, which proves beneficial when training a deep learning model.

Keywords: Computer vision, deep learning, object detection, semiconductor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 829

Authors: Abdulaziz Alsadhan, Naveed Khan

Abstract:

In recent years intrusions on computer network are the major security threat. Hence, it is important to impede such intrusions. The hindrance of such intrusions entirely relies on its detection, which is primary concern of any security tool like Intrusion detection system (IDS). Therefore, it is imperative to accurately detect network attack. Numerous intrusion detection techniques are available but the main issue is their performance. The performance of IDS can be improved by increasing the accurate detection rate and reducing false positive. The existing intrusion detection techniques have the limitation of usage of raw dataset for classification. The classifier may get jumble due to redundancy, which results incorrect classification. To minimize this problem, Principle component analysis (PCA), Linear Discriminant Analysis (LDA) and Local Binary Pattern (LBP) can be applied to transform raw features into principle features space and select the features based on their sensitivity. Eigen values can be used to determine the sensitivity. To further classify, the selected features greedy search, back elimination, and Particle Swarm Optimization (PSO) can be used to obtain a subset of features with optimal sensitivity and highest discriminatory power. This optimal feature subset is used to perform classification. For classification purpose, Support Vector Machine (SVM) and Multilayer Perceptron (MLP) are used due to its proven ability in classification. The Knowledge Discovery and Data mining (KDD’99) cup dataset was considered as a benchmark for evaluating security detection mechanisms. The proposed approach can provide an optimal intrusion detection mechanism that outperforms the existing approaches and has the capability to minimize the number of features and maximize the detection rates.

Keywords: Particle Swarm Optimization (PSO), Principle component analysis (PCA), Linear Discriminant Analysis (LDA), Local Binary Pattern (LBP), Support Vector Machine (SVM), Multilayer Perceptron (MLP).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2766

Authors: H. Özkan

Abstract:

In this paper, a novel and fast algorithm for segmental and subsegmental lung vessel segmentation is introduced using Computed Tomography Angiography images. This process is quite important especially at the detection of pulmonary embolism, lung nodule, and interstitial lung disease. The applied method has been realized at five steps. At the first step, lung segmentation is achieved. At the second one, images are threshold and differences between the images are detected. At the third one, left and right lungs are gathered with the differences which are attained in the second step and Exact Lung Image (ELI) is achieved. At the fourth one, image, which is threshold for vessel, is gathered with the ELI. Lastly, identifying and segmentation of segmental and subsegmental lung vessel have been carried out thanks to image which is obtained in the fourth step. The performance of the applied method is found quite well for radiologists and it gives enough results to the surgeries medically.

Keywords: Computed tomography angiography (CTA), Computer aided detection (CAD), Lung segmentation, Lung vessel segmentation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2179

Authors: N. H. Harun, A. S. Abdul Nasir, M. Y. Mashor, R. Hassan

Abstract:

Leukaemia is a blood cancer disease that contributes to the increment of mortality rate in Malaysia each year. There are two main categories for leukaemia, which are acute and chronic leukaemia. The production and development of acute leukaemia cells occurs rapidly and uncontrollable. Therefore, if the identification of acute leukaemia cells could be done fast and effectively, proper treatment and medicine could be delivered. Due to the requirement of prompt and accurate diagnosis of leukaemia, the current study has proposed unsupervised pixel segmentation based on clustering algorithm in order to obtain a fully segmented abnormal white blood cell (blast) in acute leukaemia image. In order to obtain the segmented blast, the current study proposed three clustering algorithms which are k-means, fuzzy c-means and moving k-means algorithms have been applied on the saturation component image. Then, median filter and seeded region growing area extraction algorithms have been applied, to smooth the region of segmented blast and to remove the large unwanted regions from the image, respectively. Comparisons among the three clustering algorithms are made in order to measure the performance of each clustering algorithm on segmenting the blast area. Based on the good sensitivity value that has been obtained, the results indicate that moving kmeans clustering algorithm has successfully produced the fully segmented blast region in acute leukaemia image. Hence, indicating that the resultant images could be helpful to haematologists for further analysis of acute leukaemia.

Keywords: Acute Leukaemia Images, Clustering Algorithms, Image Segmentation, Moving k-Means.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2789

Authors: V. Veeraprathap, G. S. Harish, G. Narendra Kumar

Abstract:

Uncontrolled growth of abnormal cells in the lung in the form of tumor can be either benign (non-cancerous) or malignant (cancerous). Patients with Lung Cancer (LC) have an average of five years life span expectancy provided diagnosis, detection and prediction, which reduces many treatment options to risk of invasive surgery increasing survival rate. Computed Tomography (CT), Positron Emission Tomography (PET), and Magnetic Resonance Imaging (MRI) for earlier detection of cancer are common. Gaussian filter along with median filter used for smoothing and noise removal, Histogram Equalization (HE) for image enhancement gives the best results without inviting further opinions. Lung cavities are extracted and the background portion other than two lung cavities is completely removed with right and left lungs segmented separately. Region properties measurements area, perimeter, diameter, centroid and eccentricity measured for the tumor segmented image, while texture is characterized by Gray-Level Co-occurrence Matrix (GLCM) functions, feature extraction provides Region of Interest (ROI) given as input to classifier. Two levels of classifications, K-Nearest Neighbor (KNN) is used for determining patient condition as normal or abnormal, while Artificial Neural Networks (ANN) is used for identifying the cancer stage is employed. Discrete Wavelet Transform (DWT) algorithm is used for the main feature extraction leading to best efficiency. The developed technology finds encouraging results for real time information and on line detection for future research.

Keywords: ANN, DWT, GLCM, KNN, ROI, artificial neural networks, discrete wavelet transform, gray-level co-occurrence matrix, k-nearest neighbor, region of interest.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 960

Authors: Dyah E. Herwindiati

Abstract:

A clustering is process to identify a homogeneous groups of object called as cluster. Clustering is one interesting topic on data mining. A group or class behaves similarly characteristics. This paper discusses a robust clustering process for data images with two reduction dimension approaches; i.e. the two dimensional principal component analysis (2DPCA) and principal component analysis (PCA). A standard approach to overcome this problem is dimension reduction, which transforms a high-dimensional data into a lower-dimensional space with limited loss of information. One of the most common forms of dimensionality reduction is the principal components analysis (PCA). The 2DPCA is often called a variant of principal component (PCA), the image matrices were directly treated as 2D matrices; they do not need to be transformed into a vector so that the covariance matrix of image can be constructed directly using the original image matrices. The decomposed classical covariance matrix is very sensitive to outlying observations. The objective of paper is to compare the performance of robust minimizing vector variance (MVV) in the two dimensional projection PCA (2DPCA) and the PCA for clustering on an arbitrary data image when outliers are hiden in the data set. The simulation aspects of robustness and the illustration of clustering images are discussed in the end of paper

Keywords: Breakdown point, Consistency, 2DPCA, PCA, Outlier, Vector Variance

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1697