Search results for: object recognition

Authors: Abe Degale D., Cheng Jian

Abstract:

When creating automated video surveillance systems, violent action recognition is crucial. In recent years, hand-crafted feature detectors have been the primary method for achieving violence detection, such as the recognition of fighting activity. Researchers have also looked into learning-based representational models. On benchmark datasets created especially for the detection of violent sequences in sports and movies, these methods produced good accuracy results. The Hockey dataset's videos with surveillance camera motion present challenges for these algorithms for learning discriminating features. Image recognition and human activity detection challenges have shown success with deep representation-based methods. For the purpose of detecting violent images and identifying aggressive human behaviours, this research suggested a deep representation-based model using the transfer learning idea. The results show that the suggested approach outperforms state-of-the-art accuracy levels by learning the most discriminating features, attaining 99.34% and 99.98% accuracy levels on the Hockey and Movies datasets, respectively.

Keywords: violence detection, faster RCNN, transfer learning and, surveillance video

Procedia PDF Downloads 73

Authors: Dionisio Andujar, Juan lópez-Correa, Hugo Moreno, Angela Ri

Abstract:

The increased number of weeds in tomato crops highly lower yields. Weed identification with the aim of machine learning is important to carry out site-specific control. The last advances in computer vision are a powerful tool to face the problem. The analysis of RGB (Red, Green, Blue) images through Artificial Neural Networks had been rapidly developed in the past few years, providing new methods for weed classification. The development of the algorithms for crop and weed species classification looks for a real-time classification system using Object Detection algorithms based on Convolutional Neural Networks. The site study was located in commercial corn fields. The classification system has been tested. The procedure can detect and classify weed seedlings in tomato fields. The input to the Neural Network was a set of 10,000 RGB images with a natural infestation of Cyperus rotundus l., Echinochloa crus galli L., Setaria italica L., Portulaca oeracea L., and Solanum nigrum L. The validation process was done with a random selection of RGB images containing the aforementioned species. The mean average precision (mAP) was established as the metric for object detection. The results showed agreements higher than 95 %. The system will provide the input for an online spraying system. Thus, this work plays an important role in Site Specific Weed Management by reducing herbicide use in a single step.

Keywords: deep learning, object detection, cnn, tomato, weeds

Procedia PDF Downloads 82

Authors: Mohamed Barbary, Mohamed H. Abd El-azeem

Abstract:

Maneuvering non-ellipsoidal extended object tracking (M-NEOT) using high-resolution inverse synthetic aperture radar (ISAR) observations is gaining momentum recently. This work presents a new robust implementation of the Jump Markov (JM) multi-Bernoulli (MB) filter for M-NEOT, where the M-NEOT’s ISAR observations are characterized using a skewed (SK) non-symmetrically normal distribution. To cope with the possible abrupt change of kinematic state, extension, and observation distribution over an extended object when a target maneuvers, a multiple model technique is represented based on an MB-track-before-detect (TBD) filter supported by SK-sub-random matrix model (RMM) or sub-ellipses framework. Simulation results demonstrate this remarkable impact.

Keywords: maneuvering extended objects, ISAR, skewed normal distribution, sub-RMM, JM-MB-TBD filter

Procedia PDF Downloads 34

Authors: Miklos Taliga

Abstract:

In the present case study we examined the development and testing methods of systems that contain safety-critical elements in different industrial fields. Consequentially, we observed the classical object-oriented development and testing environment, as both medical technology and automobile industry approaches the development of safety critical elements that way. Subsequently, we examined model-based development. We introduce the quality parameters that define development and testing. While taking modern agile methodology (scrum) into consideration, we examined whether and to what extent the methodologies we found fit into this environment.

Keywords: safety-critical elements, quality managent, unit verification, model base testing, agile methods, scrum, metamodel, object-oriented programming, field specific modelling, sprint, user story, UML Standard

Procedia PDF Downloads 561

Authors: Po-Hao Huang, Pei-Ju Chiang

Abstract:

The structured light 3D scanner is commonly used for measuring the 3D shape of an object. Through projecting designed light patterns on the object, deformed patterns can be obtained and used for the geometric shape reconstruction. At present, Gray code is the most reliable and commonly used light pattern in the structured light 3D scanner. However, the trade-off between scanning efficiency and accuracy is a long-standing and challenging problem. The design of light patterns plays a significant role in the scanning efficiency and accuracy. Thereby, we proposed a novel encoding method integrating color information and Gray-code to improve the scanning efficiency. We will demonstrate that with the proposed method, the scanning time can be reduced to approximate half of the one needed by Gray-code without reduction of precision.

Keywords: gray-code, structured light scanner, 3D shape acquisition, 3D reconstruction

Procedia PDF Downloads 433

Authors: Mohammadamin Abbasnejad

Abstract:

The analysis of expression and facial Action Units (AUs) detection are very important tasks in fields of computer vision and Human Computer Interaction (HCI) due to the wide range of applications in human life. Many works have been done during the past few years which has their own advantages and disadvantages. In this work, we present a new model based on Gaussian Conditional Random Field. We solve our objective problem using ADMM and we show how well the proposed model works. We train and test our work on two facial expression datasets, CK+, and RU-FACS. Experimental evaluation shows that our proposed approach outperform state of the art expression recognition.

Keywords: Gaussian Conditional Random Field, ADMM, convergence, gradient descent

Procedia PDF Downloads 330

Authors: Christina Adly, Meena Abdelmeseeh, Tamer Basha

Abstract:

This paper proposes a system for hand movement recognition using multichannel surface EMG(sEMG) signals obtained from 40 subjects using 40 different exercises, which are available on the Ninapro(Non-Invasive Adaptive Prosthetics) database. First, we applied processing methods to the raw sEMG signals to convert them to their amplitudes. Second, we used deep learning methods to solve our problem by passing the preprocessed signals to Fully connected neural networks(FCNN) and recurrent neural networks(RNN) with Long Short Term Memory(LSTM). Using intrasubject evaluation, The accuracy using the FCNN is 72%, with a processing time for training around 76 minutes, and for RNN's accuracy is 79.9%, with 8 minutes and 22 seconds processing time. Third, we applied some postprocessing methods to improve the accuracy, like majority voting(MV) and Movement Error Rate(MER). The accuracy after applying MV is 75% and 86% for FCNN and RNN, respectively. The MER value has an inverse relationship with the prediction delay while varying the window length for measuring the MV. The different part uses the RNN with the intersubject evaluation. The experimental results showed that to get a good accuracy for testing with reasonable processing time, we should use around 20 subjects.

Keywords: hand movement recognition, recurrent neural network, movement error rate, intrasubject evaluation, intersubject evaluation

Procedia PDF Downloads 111

Authors: Wale Agbaje

Abstract:

The aim of this research study is to assess the impact of financial statement fraud on profitability of some selected Nigerian manufacturing firms covering (2002-2016). The specific objectives focused on to ascertain the effect of incorrect asset valuation on return on assets (ROA) and to ascertain the relationship between improper expense recognition and return on assets (ROA). To achieve these objectives, descriptive research design was used for the study while secondary data were collected from the financial reports of the selected firms and website of security and exchange commission. The analysis of covariance (ANCOVA) was used and STATA II econometric method was used in the analysis of the data. Altman model and operating expenses ratio was adopted in the analysis of the financial reports to create a dummy variable for the selected firms from 2002-2016 and validation of the parameters were ascertained using various statistical techniques such as t-test, co-efficient of determination (R2), F-statistics and Wald chi-square. Two hypotheses were formulated and tested using the t-statistics at 5% level of significance. The findings of the analysis revealed that there is a significant relationship between financial statement fraud and profitability in Nigerian manufacturing industry. It was revealed that incorrect assets valuation has a significant positive relationship and so also is the improper expense recognition on return on assets (ROA) which serves as a proxy for profitability. The implication of this is that distortion of asset valuation and expense recognition leads to decreasing profit in the long run in the manufacturing industry. The study therefore recommended that pragmatic policy options need to be taken in the manufacturing industry to effectively manage incorrect asset valuation and improper expense recognition in order to enhance manufacturing industry performance in the country and also stemming of financial statement fraud should be adequately inculcated into the internal control system of manufacturing firms for the effective running of the manufacturing industry in Nigeria.

Keywords: Althman's Model, improper expense recognition, incorrect asset valuation, return on assets

Procedia PDF Downloads 133

Authors: Hee-Choul Kwon, Hyungjin Cho, Heeyong Kwon

Abstract:

Image rotation is one of main pre-processing step in image processing or image pattern recognition. It is implemented with rotation matrix multiplication. However it requires lots of floating point arithmetic operations and trigonometric function calculations, so it takes long execution time. We propose a new high speed image rotation algorithm without two major time-consuming operations. We compare the proposed algorithm with the conventional rotation one with various size images. Experimental results show that the proposed algorithm is superior to the conventional rotation ones.

Keywords: high speed rotation operation, image processing, image rotation, pattern recognition, transformation matrix

Procedia PDF Downloads 478

Authors: L. Kiefer, C. Richter, G. Reinhart

Abstract:

The uprising complexity in production systems due to an increasing amount of variants up to customer innovated products leads to requirements that hierarchical control systems are not able to fulfil. Therefore, factory planners can install autonomous manufacturing systems. The fundamental requirement for an autonomous control is the identification of objects within production systems. In this approach an attribute-based identification is focused for avoiding dose-dependent identification costs. Instead of using an identification mark (ID) like a radio frequency identification (RFID)-Tag, an object type is directly identified by its attributes. To facilitate that it’s recommended to include the identification and the corresponding sensors within handling processes, which connect all manufacturing processes and therefore ensure a high identification rate and reduce blind spots. The presented methodology reduces the individual effort to integrate identification processes in handling systems. First, suitable object attributes and sensor systems for object identification in a production environment are defined. By categorising these sensor systems as well as handling systems, it is possible to match them universal within a compatibility matrix. Based on that compatibility further requirements like identification time are analysed, which decide whether the combination of handling and sensor system is well suited for parallel handling and identification within an autonomous control. By analysing a list of more than thousand possible attributes, first investigations have shown, that five main characteristics (weight, form, colour, amount, and position of subattributes as drillings) are sufficient for an integrable identification. This knowledge limits the variety of identification systems and leads to a manageable complexity within the selection process. Besides the procedure, several tools, as an example a sensor pool are presented. These tools include the generated specific expert knowledge and simplify the selection. The primary tool is a pool of preconfigured identification processes depending on the chosen combination of sensor and handling device. By following the defined procedure and using the created tools, even laypeople out of other scientific fields can choose an appropriate combination of handling devices and sensors which enable parallel handling and identification.

Keywords: agent systems, autonomous control, handling systems, identification

Procedia PDF Downloads 155

Authors: Achut Manandhar, Kenneth D. Morton, Peter A. Torrione, Leslie M. Collins

Abstract:

The current trends in affect recognition research are to consider continuous observations from spontaneous natural interactions in people using multiple feature modalities, and to represent affect in terms of continuous dimensions, incorporate spatio-temporal correlation among affect dimensions, and provide fast affect predictions. These research efforts have been propelled by a growing effort to develop affect recognition system that can be implemented to enable seamless real-time human-computer interaction in a wide variety of applications. Motivated by these desired attributes of an affect recognition system, in this work a multi-dimensional affect prediction approach is proposed by integrating multivariate Relevance Vector Machine (MVRVM) with a recently developed Output-associative Relevance Vector Machine (OARVM) approach. The resulting approach can provide fast continuous affect predictions by jointly modeling the multiple affect dimensions and their correlations. Experiments on the RECOLA database show that the proposed approach performs competitively with the OARVM while providing faster predictions during testing.

Keywords: dimensional affect prediction, output-associative RVM, multivariate regression, fast testing

Procedia PDF Downloads 262

Authors: Naoum Abderrahmane, Boumehed Meriem, Alshaqaqi Belal

Abstract:

Background subtraction algorithm is a larger used technique for detecting moving objects in video surveillance to extract the foreground objects from a reference background image. There are many challenges to test a good background subtraction algorithm, like changes in illumination, dynamic background such as swinging leaves, rain, snow, and the changes in the background, for example, moving and stopping of vehicles. In this paper, we propose an efficient and accurate background subtraction method for moving object detection in video surveillance. The main idea is to use a developed fast-independent component analysis (ICA) algorithm to separate background, noise, and foreground masks from an image sequence in practical environments. The fast-ICA algorithm is adapted and adjusted with a matrix calculation and searching for an optimum non-quadratic function to be faster and more robust. Moreover, in order to estimate the de-mixing matrix and the denoising de-mixing matrix parameters, we propose to convert all images to YCrCb color space, where the luma component Y (brightness of the color) gives suitable results. The proposed technique has been verified on the publicly available datasets CD net 2012 and CD net 2014, and experimental results show that our algorithm can detect competently and accurately moving objects in challenging conditions compared to other methods in the literature in terms of quantitative and qualitative evaluations with real-time frame rate.

Keywords: background subtraction, moving object detection, fast-ICA, de-mixing matrix

Procedia PDF Downloads 71

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and ECG-based systems are unquestionably the best choice due to their appealing inherent characteristics. The CNNs are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the calibre of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest FAR of 0.04 percent and the highest FRR of 5%, the best performing network achieved an identification accuracy of 99.94 percent. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, Dense Networks, Identification Rate, Train/Test split ratio

Procedia PDF Downloads 139

Authors: H. Gonzalez-Rivera, J. L. Palmeros-Torres

Abstract:

This paper describes the application of traditional computer vision techniques as a procedure for automatic measurement of the secondary dendrite arm spacing (SDAS) from microscopic images. The algorithm is capable of finding the lineal or curve-shaped secondary column of the main microstructure, measuring its length size in a micro-meter and counting the number of spaces between dendrites. The automatic characterization was compared with a set of 1728 manually characterized images, leading to an accuracy of −0.27 µm for the length size determination and a precision of ± 2.78 counts for dendrite spacing counting, also reducing the characterization time from 7 hours to 2 minutes.

Keywords: dendrite arm spacing, microstructure inspection, pattern recognition, polynomial regression

Procedia PDF Downloads 18

Authors: Laura Victoria Vigoya Morales, David Rolando Suarez Mora

Abstract:

The problem of detecting enterococcus faecalis is receiving considerable attention with the new cases of beachgoers infected with the bacteria, which can be found in fecal matter. The process detection of this kind of bacteria would be taking a long time, which waste time and money as a result of closing recreation place, like beach or pools. Hence, new methods for automating the process of detecting and recognition of this bacteria has become in a challenge. This article describes a novel approach to detect the enterococcus faecalis bacteria in water by using an octave algorithm, which embody a network neural. This document shows result of performance, quality and integrity of the algorithm.

Keywords: Enterococcus faecalis, image treatment, octave and network neuronal

Procedia PDF Downloads 200

Authors: Aparna Gulhane

Abstract:

Biometrics is the science and technology of measuring and analyzing biological data form the basis of research in biological measuring techniques for the purpose of people identification and recognition. In information technology, biometrics refers to technologies that measure and analyze human body characteristics, such as DNA, fingerprints, eye retinas and irises, voice patterns, facial patterns and hand measurements. Biometric systems are used to authenticate the person's identity. The idea is to use the special characteristics of a person to identify him. These papers present a biometric authentication techniques and actual deployment of potential by overall invocation of biometrics recognition, with an independent testing of various biometric authentication products and technology.

Keywords: types of biometrics, importance of biometric, review for biometrics and getting a new implementation, biometric authentication technique

Procedia PDF Downloads 293

Authors: Monica Gonzalez Machorro

Abstract:

Dementia is hard to diagnose because of the lack of early physical symptoms. Early dementia recognition is key to improving the living condition of patients. Speech technology is considered a valuable biomarker for this challenge. Recent works have utilized conventional acoustic features and machine learning methods to detect dementia in speech. BERT-like classifiers have reported the most promising performance. One constraint, nonetheless, is that these studies are either based on human transcripts or on transcripts produced by automatic speech recognition (ASR) systems. This research contribution is to explore a method that does not require transcriptions to detect early Alzheimer’s disease (AD) and mild cognitive impairment (MCI). This is achieved by fine-tuning a pre-trained ASR model for the downstream early AD and MCI tasks. To do so, a subset of the thoroughly studied Pitt Corpus is customized. The subset is balanced for class, age, and gender. Data processing also involves cropping the samples into 10-second segments. For comparison purposes, a baseline model is defined by training and testing a Random Forest with 20 extracted acoustic features using the librosa library implemented in Python. These are: zero-crossing rate, MFCCs, spectral bandwidth, spectral centroid, root mean square, and short-time Fourier transform. The baseline model achieved a 58% accuracy. To fine-tune HuBERT as a classifier, an average pooling strategy is employed to merge the 3D representations from audio into 2D representations, and a linear layer is added. The pre-trained model used is ‘hubert-large-ls960-ft’. Empirically, the number of epochs selected is 5, and the batch size defined is 1. Experiments show that our proposed method reaches a 69% balanced accuracy. This suggests that the linguistic and speech information encoded in the self-supervised ASR-based model is able to learn acoustic cues of AD and MCI.

Keywords: automatic speech recognition, early Alzheimer’s recognition, mild cognitive impairment, speech impairment

Procedia PDF Downloads 101

Authors: Ágoston Nagy

Abstract:

This paper introduces a method of using unsupervised machine learning to visualize the feature space of a dataset in 2D, in order to find most characteristic segments in the set. After dimension reduction, users can select clusters by manual drawing. Selected clusters are recorded into a data model that is used for later predictions, based on realtime data. Predictions are made with supervised learning, using Gesture Recognition Toolkit. The paper introduces two example applications: a semantic audio organizer for analyzing incoming sounds, and a gesture database organizer where gestural data (recorded by a Leap motion) is visualized for further manipulation.

Keywords: gesture recognition, machine learning, real-time interaction, visualization

Procedia PDF Downloads 325

Authors: Maria Barriga

Abstract:

The article focuses on the analysis of three images of the last five years that represent different visions of social groups in the context of the so call “Conflicto Mapuche” in la Araucanía, Chile. Using a multimodal social semiotic approach, we analyze the meaning making of these images and the social groups strategies to achieve visibility and recognition in political contexts. We explore the making and appropriation of symbols and concepts and analyze the different strategies that groups use to built hegemonic views. Among these strategies, we compare the use of digital technologies in design these images and the influence of Chilean Estate's vision on the Mapuche political conflict. Finally, we propose visual strategies to improve basic conditions for dialogue and recognition among these groups.

Keywords: visual culture, power, conflict, indigenous people

Procedia PDF Downloads 264

Authors: Anthony Albanese

Abstract:

While much of the literature concerning Max Weber’s concept of charisma has addressed the importance of the follower’s recognition of and devotion to the charismatic leader, very little has been said about the processes that lead to the development of follower charisma. This article examines this largely overlooked aspect of the concept, as doing so (1) exacts the dynamics behind charisma’s transferability by moving beyond follower-centric models that focus on the recognition of the leader and toward one that emphasizes the follower’s generation and exhibition of charisma, (2) bridges a crucial gap between the rather wanting “losers of modernization” thesis and the social actor’s proclivity to produce stories and self-cast in said stories, (3) presents authoritarian dispositions as a reaction to the weakening effects everydayness have on charisma, and (4) complicates Weber’s formulation by reassessing the role of continually demonstrable mastery. To illustrate these dynamics, one should turn to the January 6th Capitol attack in the United States.

Keywords: max weber, extremism, right-wing populism, charisma

Procedia PDF Downloads 62

Authors: Daseul Lee, Jeong Jun Lee, Ok-Sang Jung

Abstract:

Self-assembly of a series of ZnX2 (X- = Cl-, Br-, and I-) with 2,3-bis(4’-nicotinamidephenoxy)naphthalene (L) as a new bidentate pyridyl-donor ligand yields systematic metallacyclodimeric unit, [ZnX2L]2. The supramolecule constitutes a characteristically stacked forming both 1D suprachannels and cages. Weak C-H⋯π and inter-digitated π⋯π interactions are main driving forces in the formation of both suprachannels and cages. The slightly different features between the suprachannel and cage have been investigated by 1H NMR and TG analysis, which solvent quantitatively exchange within only suprachannels. Photo-unstable CH2I2 molecules are stabilized via capturing within suprachannels, which is monitored by UV-Vis spectroscopy. Furthermore, the photoluminescence intensity, from the chromophore naphthyl moiety of [ZnCl2L]2, gradually decreases with the addition of CH2I2. And washing off the CH2I2 by dichloromethane returned the PL intensity back to its approximately original signal.

Keywords: metallacyclodimer, suprachannel, π⋯π interaction, molecular recognition

Procedia PDF Downloads 295

Authors: Cheng Fang, Lingwei Quan, Cunyue Lu

Abstract:

Human pose estimation and tracking are to accurately identify and locate the positions of human joints in the video. It is a computer vision task which is of great significance for human motion recognition, behavior understanding and scene analysis. There has been remarkable progress on human pose estimation in recent years. However, more researches are needed for human pose tracking especially for online tracking. In this paper, a framework, called PoseSRPN, is proposed for online single-person pose estimation and tracking. We use Siamese network attaching a pose estimation branch to incorporate Single-person Pose Tracking (SPT) and Visual Object Tracking (VOT) into one framework. The pose estimation branch has a simple network structure that replaces the complex upsampling and convolution network structure with deconvolution. By augmenting the loss of fully convolutional Siamese network with the pose estimation task, pose estimation and tracking can be trained in one stage. Once trained, PoseSRPN only relies on a single bounding box initialization and producing human joints location. The experimental results show that while maintaining the good accuracy of pose estimation on COCO and PoseTrack datasets, the proposed method achieves a speed of 59 frame/s, which is superior to other pose tracking frameworks.

Keywords: computer vision, pose estimation, pose tracking, Siamese network

Procedia PDF Downloads 128

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 PDF Downloads 112

Authors: Iqraq Kamal, Akmal Razif, Sivadas Chandra Sekaran, Ahmad Syazwan Hisaburi

Abstract:

Painting plays a crucial role in the aerospace manufacturing industry, serving both protective and cosmetic purposes for components. However, the traditional manual painting method is time-consuming and labor-intensive, posing challenges for the sector in achieving higher efficiency. Additionally, the current automated robot path planning has been a bottleneck for spray painting processes, as typical manual teaching methods are time-consuming, error-prone, and skill-dependent. Therefore, it is essential to develop automated tool path planning methods to replace manual ones, reducing costs and improving product quality. Focusing on flat panel painting in aerospace manufacturing, this study aims to address issues related to unreliable part identification techniques caused by the high-mixture, low-volume nature of the industry. The proposed solution involves using a spray gun and a UR10 robotic arm with a vision system that utilizes one-shot object detection (OS2D) to identify parts accurately. Additionally, the research optimizes path planning by concentrating on the region of interest—specifically, the identified part, rather than uniformly covering the entire painting tray.

Keywords: aerospace manufacturing, one-shot object detection, automated spray painting, vision-based path optimization, deep learning, automation, robotic arm

Procedia PDF Downloads 52

Authors: R. Nagarani

Abstract:

An intrinsic property of software in a real-world environment is its need to evolve, which is usually accompanied by the increase of software complexity and deterioration of software quality, making software maintenance a tough problem. Refactoring is regarded as an effective way to address this problem. Many refactoring approaches at the method and class level have been proposed. But the extent of research on software refactoring at the package level is less. This work presents a novel approach to refactor the package structures of object oriented software using genetic algorithm based community detection. It uses software networks to represent classes and their dependencies. It uses a constrained community detection algorithm to obtain the optimized community structures in software networks, which also correspond to the optimized package structures. It finally provides a list of classes as refactoring candidates by comparing the optimized package structures with the real package structures.

Keywords: community detection, complex network, genetic algorithm, package, refactoring

Procedia PDF Downloads 395

Authors: Bipasha Sen, Aditya Agarwal

Abstract:

Multilingual automatic speech recognition (ASR) system is a single entity capable of transcribing multiple languages sharing a common phone space. Performance of such a system is highly dependent on the compatibility of the languages. State of the art speech recognition systems are built using sequential architectures based on recurrent neural networks (RNN) limiting the computational parallelization in training. This poses a significant challenge in terms of time taken to bootstrap and validate the compatibility of multiple languages for building a robust multilingual system. Complex architectural choices based on self-attention networks are made to improve the parallelization thereby reducing the training time. In this work, we propose Reed, a simple system based on 1D convolutions which uses very short context to improve the training time. To improve the performance of our system, we use raw time-domain speech signals directly as input. This enables the convolutional layers to learn feature representations rather than relying on handcrafted features such as MFCC. We report improvement on training and inference times by atleast a factor of 4x and 7.4x respectively with comparable WERs against standard RNN based baseline systems on SpeechOcean's multilingual low resource dataset.

Keywords: convolutional neural networks, language compatibility, low resource languages, multilingual automatic speech recognition

Procedia PDF Downloads 96

Authors: Lin Cheng, Zijiang Yang

Abstract:

Program synthesis is the task to automatically generate programs based on user specification. In this paper, we present a framework that synthesizes programs from flow charts that serve as accurate and intuitive specification. In order doing so, we propose a deep neural network called GRCNN that recognizes graph structure from its image. GRCNN is trained end-to-end, which can predict edge and node information of the flow chart simultaneously. Experiments show that the accuracy rate to synthesize a program is 66.4%, and the accuracy rates to recognize edge and node are 94.1% and 67.9%, respectively. On average, it takes about 60 milliseconds to synthesize a program.

Keywords: program synthesis, flow chart, specification, graph recognition, CNN

Procedia PDF Downloads 99

Authors: Ashis Pradhan, Mohan P. Pradhan

Abstract:

Pattern Matching is useful for recognizing character in a digital image. OCR is one such technique which reads character from a digital image and recognizes them. Line segmentation is initially used for identifying character in an image and later refined by morphological operations like binarization, erosion, thinning, etc. The work discusses a recognition technique that defines a set of morphological operators based on its orientation in a character. These operators are further categorized into groups having similar shape but different orientation for efficient utilization of memory. Finally the characters are recognized in accordance with the occurrence of frequency in hierarchy of significant pattern of those morphological operators and by comparing them with the existing database of each character.

Keywords: binary image, morphological patterns, frequency count, priority, reduction data set and recognition

Procedia PDF Downloads 391

Authors: Thang V. Kieu, Long P. Nguyen

Abstract:

Kernelized Correlation Filter (KCF) based trackers have gained a lot of attention recently because of their accuracy and fast calculation speed. However, this algorithm is not robust in cases where the object is lost by a sudden change of direction, being obscured or going out of view. In order to improve KCF performance in long-term tracking, this paper proposes an anomaly detection method for target loss warning by analyzing the response map of each frame, and a classification algorithm for reliable target re-locating mechanism by using Random fern. Being tested with Visual Tracker Benchmark and Visual Object Tracking datasets, the experimental results indicated that the precision and success rate of the proposed algorithm were 2.92 and 2.61 times higher than that of the original KCF algorithm, respectively. Moreover, the proposed tracker handles occlusion better than many state-of-the-art long-term tracking methods while running at 60 frames per second.

Keywords: correlation filter, long-term tracking, random fern, real-time tracking

Procedia PDF Downloads 117

Authors: Alexander A. Karabutov, Natalia B. Podymova, Elena B. Cherepetskaya

Abstract:

The theoretical analysis is carried out to get the relation between the ultrasonic wave velocity and the value of residual stresses. The laser-ultrasonic method is developed to evaluate the residual stresses and subsurface defects in metals. The method is based on the laser thermooptical excitation of longitudinal ultrasonic wave sand their detection by a broadband piezoelectric detector. A laser pulse with the time duration of 8 ns of the full width at half of maximum and with the energy of 300 µJ is absorbed in a thin layer of the special generator that is inclined relative to the object under study. The non-uniform heating of the generator causes the formation of a broadband powerful pulse of longitudinal ultrasonic waves. It is shown that the temporal profile of this pulse is the convolution of the temporal envelope of the laser pulse and the profile of the in-depth distribution of the heat sources. The ultrasonic waves reach the surface of the object through the prism that serves as an acoustic duct. At the interface ‚laser-ultrasonic transducer-object‘ the conversion of the most part of the longitudinal wave energy takes place into the shear, subsurface longitudinal and Rayleigh waves. They spread within the subsurface layer of the studied object and are detected by the piezoelectric detector. The electrical signal that corresponds to the detected acoustic signal is acquired by an analog-to-digital converter and when is mathematically processed and visualized with a personal computer. The distance between the generator and the piezodetector as well as the spread times of acoustic waves in the acoustic ducts are the characteristic parameters of the laser-ultrasonic transducer and are determined using the calibration samples. There lative precision of the measurement of the velocity of longitudinal ultrasonic waves is 0.05% that corresponds to approximately ±3 m/s for the steels of conventional quality. This precision allows one to determine the mechanical stress in the steel samples with the minimal detection threshold of approximately 22.7 MPa. The results are presented for the measured dependencies of the velocity of longitudinal ultrasonic waves in the samples on the values of the applied compression stress in the range of 20-100 MPa.

Keywords: laser-ultrasonic method, longitudinal ultrasonic waves, metals, residual stresses

Procedia PDF Downloads 298