Search results for: ADBT and image processing.
2189 DocPro: A Framework for Processing Semantic and Layout Information in Business Documents
Authors: Ming-Jen Huang, Chun-Fang Huang, Chiching Wei
Abstract:
With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.
Keywords: Document processing, framework, formal definition, machine learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6462188 Hiding Data in Images Using PCP
Authors: Souvik Bhattacharyya, Gautam Sanyal
Abstract:
In recent years, everything is trending toward digitalization and with the rapid development of the Internet technologies, digital media needs to be transmitted conveniently over the network. Attacks, misuse or unauthorized access of information is of great concern today which makes the protection of documents through digital media a priority problem. This urges us to devise new data hiding techniques to protect and secure the data of vital significance. In this respect, steganography often comes to the fore as a tool for hiding information. Steganography is a process that involves hiding a message in an appropriate carrier like image or audio. It is of Greek origin and means "covered or hidden writing". The goal of steganography is covert communication. Here the carrier can be sent to a receiver without any one except the authenticated receiver only knows existence of the information. Considerable amount of work has been carried out by different researchers on steganography. In this work the authors propose a novel Steganographic method for hiding information within the spatial domain of the gray scale image. The proposed approach works by selecting the embedding pixels using some mathematical function and then finds the 8 neighborhood of the each selected pixel and map each bit of the secret message in each of the neighbor pixel coordinate position in a specified manner. Before embedding a checking has been done to find out whether the selected pixel or its neighbor lies at the boundary of the image or not. This solution is independent of the nature of the data to be hidden and produces a stego image with minimum degradation.Keywords: Cover Image, LSB, Pixel Coordinate Position (PCP), Stego Image.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18232187 2D Gabor Functions and FCMI Algorithm for Flaws Detection in Ultrasonic Images
Authors: Kechida Ahmed, Drai Redouane, Khelil Mohamed
Abstract:
In this paper we present a new approach to detecting a flaw in T.O.F.D (Time Of Flight Diffraction) type ultrasonic image based on texture features. Texture is one of the most important features used in recognizing patterns in an image. The paper describes texture features based on 2D Gabor functions, i.e., Gaussian shaped band-pass filters, with dyadic treatment of the radial spatial frequency range and multiple orientations, which represent an appropriate choice for tasks requiring simultaneous measurement in both space and frequency domains. The most relevant features are used as input data on a Fuzzy c-mean clustering classifier. The classes that exist are only two: 'defects' or 'no defects'. The proposed approach is tested on the T.O.F.D image achieved at the laboratory and on the industrial field.Keywords: 2D Gabor Functions, flaw detection, fuzzy c-mean clustering, non destructive testing, texture analysis, T.O.F.D Image (Time of Flight Diffraction).
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17592186 A New Face Detection Technique using 2D DCT and Self Organizing Feature Map
Authors: Abdallah S. Abdallah, A. Lynn Abbott, Mohamad Abou El-Nasr
Abstract:
This paper presents a new technique for detection of human faces within color images. The approach relies on image segmentation based on skin color, features extracted from the two-dimensional discrete cosine transform (DCT), and self-organizing maps (SOM). After candidate skin regions are extracted, feature vectors are constructed using DCT coefficients computed from those regions. A supervised SOM training session is used to cluster feature vectors into groups, and to assign “face" or “non-face" labels to those clusters. Evaluation was performed using a new image database of 286 images, containing 1027 faces. After training, our detection technique achieved a detection rate of 77.94% during subsequent tests, with a false positive rate of 5.14%. To our knowledge, the proposed technique is the first to combine DCT-based feature extraction with a SOM for detecting human faces within color images. It is also one of a few attempts to combine a feature-invariant approach, such as color-based skin segmentation, together with appearance-based face detection. The main advantage of the new technique is its low computational requirements, in terms of both processing speed and memory utilization.Keywords: Face detection, skin color segmentation, self-organizingmap.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25452185 View-Point Insensitive Human Pose Recognition using Neural Network and CUDA
Authors: Sanghyeok Oh, Keechul Jung
Abstract:
Although lots of research work has been done for human pose recognition, the view-point of cameras is still critical problem of overall recognition system. In this paper, view-point insensitive human pose recognition is proposed. The aims of the proposed system are view-point insensitivity and real-time processing. Recognition system consists of feature extraction module, neural network and real-time feed forward calculation. First, histogram-based method is used to extract feature from silhouette image and it is suitable for represent the shape of human pose. To reduce the dimension of feature vector, Principle Component Analysis(PCA) is used. Second, real-time processing is implemented by using Compute Unified Device Architecture(CUDA) and this architecture improves the speed of feed-forward calculation of neural network. We demonstrate the effectiveness of our approach with experiments on real environment.Keywords: computer vision, neural network, pose recognition, view-point insensitive, PCA, CUDA.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13442184 Maximum Entropy Based Image Segmentation of Human Skin Lesion
Authors: Sheema Shuja Khattak, Gule Saman, Imran Khan, Abdus Salam
Abstract:
Image segmentation plays an important role in medical imaging applications. Therefore, accurate methods are needed for the successful segmentation of medical images for diagnosis and detection of various diseases. In this paper, we have used maximum entropy to achieve image segmentation. Maximum entropy has been calculated using Shannon, Renyi and Tsallis entropies. This work has novelty based on the detection of skin lesion caused by the bite of a parasite called Sand Fly causing the disease is called Cutaneous Leishmaniasis.
Keywords: Shannon, Maximum entropy, Renyi, Tsallis entropy.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 23992183 Improved Feature Processing for Iris Biometric Authentication System
Authors: Somnath Dey, Debasis Samanta
Abstract:
Iris-based biometric authentication is gaining importance in recent times. Iris biometric processing however, is a complex process and computationally very expensive. In the overall processing of iris biometric in an iris-based biometric authentication system, feature processing is an important task. In feature processing, we extract iris features, which are ultimately used in matching. Since there is a large number of iris features and computational time increases as the number of features increases, it is therefore a challenge to develop an iris processing system with as few as possible number of features and at the same time without compromising the correctness. In this paper, we address this issue and present an approach to feature extraction and feature matching process. We apply Daubechies D4 wavelet with 4 levels to extract features from iris images. These features are encoded with 2 bits by quantizing into 4 quantization levels. With our proposed approach it is possible to represent an iris template with only 304 bits, whereas existing approaches require as many as 1024 bits. In addition, we assign different weights to different iris region to compare two iris templates which significantly increases the accuracy. Further, we match the iris template based on a weighted similarity measure. Experimental results on several iris databases substantiate the efficacy of our approach.Keywords: Iris recognition, biometric, feature processing, patternrecognition, pattern matching.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21432182 Goal Based Episodic Processing in Implicit Learning
Authors: Peter A. Bibby
Abstract:
Research has suggested that implicit learning tasks may rely on episodic processing to generate above chance performance on the standard classification tasks. The current research examines the invariant features task (McGeorge and Burton, 1990) and argues that such episodic processing is indeed important. The results of the experiment suggest that both rejection and similarity strategies are used by participants in this task to simultaneously reject unfamiliar items and to accept (falsely) familiar items. Primarily these decisions are based on the presence of low or high frequency goal based features of the stimuli presented in the incidental learning phase. It is proposed that a goal based analysis of the incidental learning task provides a simple step in understanding which features of the episodic processing are most important for explaining the match between incidental, implicit learning and test performance.Keywords: Episodic processing, incidental learning, implicitlearning, invariant learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14402181 Standard Deviation of Mean and Variance of Rows and Columns of Images for CBIR
Authors: H. B. Kekre, Kavita Patil
Abstract:
This paper describes a novel and effective approach to content-based image retrieval (CBIR) that represents each image in the database by a vector of feature values called “Standard deviation of mean vectors of color distribution of rows and columns of images for CBIR". In many areas of commerce, government, academia, and hospitals, large collections of digital images are being created. This paper describes the approach that uses contents as feature vector for retrieval of similar images. There are several classes of features that are used to specify queries: colour, texture, shape, spatial layout. Colour features are often easily obtained directly from the pixel intensities. In this paper feature extraction is done for the texture descriptor that is 'variance' and 'Variance of Variances'. First standard deviation of each row and column mean is calculated for R, G, and B planes. These six values are obtained for one image which acts as a feature vector. Secondly we calculate variance of the row and column of R, G and B planes of an image. Then six standard deviations of these variance sequences are calculated to form a feature vector of dimension six. We applied our approach to a database of 300 BMP images. We have determined the capability of automatic indexing by analyzing image content: color and texture as features and by applying a similarity measure Euclidean distance.
Keywords: Standard deviation Image retrieval, color distribution, Variance, Variance of Variance, Euclidean distance.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 37492180 The Causal Relationships between Destination Image, Tourist Satisfaction and Revisit Intention: A Case of the United Arab Emirates
Authors: Abdul Raheem Jasim Mohammed, Mohd Salehuddin Mohd Zahari, Salim Abdul Talib, Mohd Zulhilmi Suhaimi
Abstract:
The connection between past travel experience and tourists’ revisit behavioral intentions has not been widely explored but the existing studies suggest a close relationship between them. Destination image can equally be construed as having effects on the attitudes of the tourists at the end of their actual visitation and the satisfaction of a tourist with his or her travel experiences contributes to a revisit intention towards a particular destination. With strong marketing efforts, UAE is not only considered to be successful in attracting foreign investors, but is becoming the most popular tourism destination in the Arab region. UAE is seriously developing its tourism image and taking serious initiatives to attract new or repeat visitations from the international tourists. This study empirically investigates the causal relationships between tourism destination image, tourist satisfaction and revisit intention using UAE as a contextual study setting. A very clear picture emerged which provides a host country with potential implications for its tourism industry practitioners, Department of Tourism and Commerce Marketing and the travel agencies who act as the intermediaries between the potential tourists and the hotel operators.
Keywords: Destination image, tourist satisfaction, revisit intention.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 32212179 Dark and Bright Envelopes for Dehazing Images
Authors: Zihan Yu, Kohei Inoue, Kiichi Urahama
Abstract:
We present a method for dehazing images. A dark envelope image is derived with the bilateral minimum filter and a bright envelope is derived with the bilateral maximum filter. The ambient light and transmission of the scene are estimated from these two envelope images. An image without haze is reconstructed from the estimated ambient light and transmission.
Keywords: Image dehazing, bilateral minimum filter, bilateral maximum filter, local contrast.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20072178 Image Transmission: A Case Study on Combined Scheme of LDPC-STBC in Asynchronous Cooperative MIMO Systems
Authors: Shan Ding, Lijia Zhang, Hongming Xu
Abstract:
this paper presents a novel scheme which is capable of reducing the error rate and improves the transmission performance in the asynchronous cooperative MIMO systems. A case study of image transmission is applied to prove the efficient of scheme. The linear dispersion structure is employed to accommodate the cooperative wireless communication network in the dynamic topology of structure, as well as to achieve higher throughput than conventional space–time codes based on orthogonal designs. The LDPC encoder without girth-4 and the STBC encoder with guard intervals are respectively introduced. The experiment results show that the combined coder of LDPC-STBC with guard intervals can be the good error correcting coders and BER performance in the asynchronous cooperative communication. In the case study of image transmission, the results show that in the transmission process, the image quality which is obtained by applied combined scheme is much better than it which is not applied the scheme in the asynchronous cooperative MIMO systems.
Keywords: Cooperative MIMO, image transmission, lineardispersion codes, Low-Density Parity-Check (LDPC)
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19362177 Wavelet based Image Registration Technique for Matching Dental x-rays
Authors: P. Ramprasad, H. C. Nagaraj, M. K. Parasuram
Abstract:
Image registration plays an important role in the diagnosis of dental pathologies such as dental caries, alveolar bone loss and periapical lesions etc. This paper presents a new wavelet based algorithm for registering noisy and poor contrast dental x-rays. Proposed algorithm has two stages. First stage is a preprocessing stage, removes the noise from the x-ray images. Gaussian filter has been used. Second stage is a geometric transformation stage. Proposed work uses two levels of affine transformation. Wavelet coefficients are correlated instead of gray values. Algorithm has been applied on number of pre and post RCT (Root canal treatment) periapical radiographs. Root Mean Square Error (RMSE) and Correlation coefficients (CC) are used for quantitative evaluation. Proposed technique outperforms conventional Multiresolution strategy based image registration technique and manual registration technique.Keywords: Diagnostic imaging, geometric transformation, image registration, multiresolution.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17642176 Local Mesh Co-Occurrence Pattern for Content Based Image Retrieval
Authors: C. Yesubai Rubavathi, R. Ravi
Abstract:
This paper presents the local mesh co-occurrence patterns (LMCoP) using HSV color space for image retrieval system. HSV color space is used in this method to utilize color, intensity and brightness of images. Local mesh patterns are applied to define the local information of image and gray level co-occurrence is used to obtain the co-occurrence of LMeP pixels. Local mesh co-occurrence pattern extracts the local directional information from local mesh pattern and converts it into a well-mannered feature vector using gray level co-occurrence matrix. The proposed method is tested on three different databases called MIT VisTex, Corel, and STex. Also, this algorithm is compared with existing methods, and results in terms of precision and recall are shown in this paper.Keywords: Content-based image retrieval system, HSV color space, gray level co-occurrence matrix, local mesh pattern.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 22242175 Nuclear Medical Image Treatment System Based On FPGA in Real Time
Authors: B. Mahmoud, M.H. Bedoui, R. Raychev, H. Essabbah
Abstract:
We present in this paper an acquisition and treatment system designed for semi-analog Gamma-camera. It consists of a nuclear medical Image Acquisition, Treatment and Display chain(IATD) ensuring the acquisition, the treatment of the signals(resulting from the Gamma-camera detection head) and the scintigraphic image construction in real time. This chain is composed by an analog treatment board and a digital treatment board. We describe the designed systems and the digital treatment algorithms in which we have improved the performance and the flexibility. The digital treatment algorithms are implemented in a specific reprogrammable circuit FPGA (Field Programmable Gate Array).interface for semi-analog cameras of Sopha Medical Vision(SMVi) by taking as example SOPHY DS7. The developed system consists of an Image Acquisition, Treatment and Display (IATD) ensuring the acquisition and the treatment of the signals resulting from the DH. The developed chain is formed by a treatment analog board and a digital treatment board designed around a DSP [2]. In this paper we have presented the architecture of a new version of our chain IATD in which the integration of the treatment algorithms is executed on an FPGA (Field Programmable Gate Array)
Keywords: Nuclear medical image, scintigraphic image, digitaltreatment, linearity, spectrometry, FPGA.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16782174 Image-Based (RBG) Technique for Estimating Phosphorus Levels of Crops
Authors: M. M. Ali, Ahmed Al-Ani, Derek Eamus, Daniel K. Y. Tan
Abstract:
In this glasshouse study, we developed a new imagebased non-destructive technique for detecting leaf P status of different crops such as cotton, tomato and lettuce. The plants were grown on a nutrient solution containing different P concentrations, e.g. 0%, 50% and 100% of recommended P concentration (P0 = no P, L; P1 = 2.5 mL 10 L-1 of P and P2 = 5 mL 10 L-1 of P). After 7 weeks of treatment, the plants were harvested and data on leaf P contents were collected using the standard destructive laboratory method and at the same time leaf images were collected by a handheld crop image sensor. We calculated leaf area, leaf perimeter and RGB (red, green and blue) values of these images. These data were further used in linear discriminant analysis (LDA) to estimate leaf P contents, which successfully classified these plants on the basis of leaf P contents. The data indicated that P deficiency in crop plants can be predicted using leaf image and morphological data. Our proposed nondestructive imaging method is precise in estimating P requirements of different crop species.Keywords: Image-based techniques, leaf area, leaf P contents, linear discriminant analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16522173 Research on IBR-Driven Distributed Collaborative Visualization System
Authors: Yin Runmin, Song Changfeng
Abstract:
Image-based Rendering(IBR) techniques recently reached in broad fields which leads to a critical challenge to build up IBR-Driven visualization platform where meets requirement of high performance, large bounds of distributed visualization resource aggregation and concentration, multiple operators deploying and CSCW design employing. This paper presents an unique IBR-based visualization dataflow model refer to specific characters of IBR techniques and then discusses prominent feature of IBR-Driven distributed collaborative visualization (DCV) system before finally proposing an novel prototype. The prototype provides a well-defined three level modules especially work as Central Visualization Server, Local Proxy Server and Visualization Aid Environment, by which data and control for collaboration move through them followed the previous dataflow model. With aid of this triple hierarchy architecture of that, IBR oriented application construction turns to be easy. The employed augmented collaboration strategy not only achieve convenient multiple users synchronous control and stable processing management, but also is extendable and scalable.Keywords: Image-Based Rendering, Distributed CollaborativeVisualization, Computer Supported Cooperative Work, Model andSimulation, Modular Visualization Environment.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14892172 Adaptive Weighted Averaging Filter Using the Appropriate Number of Consecutive Frames
Authors: Mahmoud Saeidi, Ali Nazemipour
Abstract:
In this paper, we propose a novel adaptive spatiotemporal filter that utilizes image sequences in order to remove noise. The consecutive frames include: current, previous and next noisy frames. The filter proposed in this paper is based upon the weighted averaging pixels intensity and noise variance in image sequences. It utilizes the Appropriate Number of Consecutive Frames (ANCF) based on the noisy pixels intensity among the frames. The number of consecutive frames is adaptively calculated for each region in image and its value may change from one region to another region depending on the pixels intensity within the region. The weights are determined by a well-defined mathematical criterion, which is adaptive to the feature of spatiotemporal pixels of the consecutive frames. It is experimentally shown that the proposed filter can preserve image structures and edges under motion while suppressing noise, and thus can be effectively used in image sequences filtering. In addition, the AWA filter using ANCF is particularly well suited for filtering sequences that contain segments with abruptly changing scene content due to, for example, rapid zooming and changes in the view of the camera.Keywords: Appropriate Number of Consecutive Frames, Adaptive Weighted Averaging, Motion Estimation, Noise Variance, Motion Compensation
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18222171 A Simple and Empirical Refraction Correction Method for UAV-Based Shallow-Water Photogrammetry
Authors: I GD Yudha Partama, A. Kanno, Y. Akamatsu, R. Inui, M. Goto, M. Sekine
Abstract:
The aerial photogrammetry of shallow water bottoms has the potential to be an efficient high-resolution survey technique for shallow water topography, thanks to the advent of convenient UAV and automatic image processing techniques Structure-from-Motion (SfM) and Multi-View Stereo (MVS)). However, it suffers from the systematic overestimation of the bottom elevation, due to the light refraction at the air-water interface. In this study, we present an empirical method to correct for the effect of refraction after the usual SfM-MVS processing, using common software. The presented method utilizes the empirical relation between the measured true depth and the estimated apparent depth to generate an empirical correction factor. Furthermore, this correction factor was utilized to convert the apparent water depth into a refraction-corrected (real-scale) water depth. To examine its effectiveness, we applied the method to two river sites, and compared the RMS errors in the corrected bottom elevations with those obtained by three existing methods. The result shows that the presented method is more effective than the two existing methods: The method without applying correction factor and the method utilizes the refractive index of water (1.34) as correction factor. In comparison with the remaining existing method, which used the additive terms (offset) after calculating correction factor, the presented method performs well in Site 2 and worse in Site 1. However, we found this linear regression method to be unstable when the training data used for calibration are limited. It also suffers from a large negative bias in the correction factor when the apparent water depth estimated is affected by noise, according to our numerical experiment. Overall, the good accuracy of refraction correction method depends on various factors such as the locations, image acquisition, and GPS measurement conditions. The most effective method can be selected by using statistical selection (e.g. leave-one-out cross validation).Keywords: Bottom elevation, multi-view stereo, river, structure-from-motion.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15832170 Multi-VSS Scheme by Shifting Random Grids
Authors: Joy Jo-Yi Chang, Justie Su-Tzu Juan
Abstract:
Visual secret sharing (VSS) was proposed by Naor and Shamir in 1995. Visual secret sharing schemes encode a secret image into two or more share images, and single share image can’t obtain any information about the secret image. When superimposes the shares, it can restore the secret by human vision. Due to the traditional VSS have some problems like pixel expansion and the cost of sophisticated. And this method only can encode one secret image. The schemes of encrypting more secret images by random grids into two shares were proposed by Chen et al. in 2008. But when those restored secret images have much distortion, those schemes are almost limited in decoding. In the other words, if there is too much distortion, we can’t encrypt too much information. So, if we can adjust distortion to very small, we can encrypt more secret images. In this paper, four new algorithms which based on Chang et al.’s scheme be held in 2010 are proposed. First algorithm can adjust distortion to very small. Second algorithm distributes the distortion into two restored secret images. Third algorithm achieves no distortion for special secret images. Fourth algorithm encrypts three secret images, which not only retain the advantage of VSS but also improve on the problems of decoding.
Keywords: Visual cryptography, visual secret sharing, random grids, multiple, secret image sharing
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15302169 The Design of a Die for the Processing of Aluminum through Equal Channel Angular Pressing
Authors: P. G. F. Siqueira, N. G. S. Almeida, P. M. A. Stemler, P. R. Cetlin, M. T. P. Aguilar
Abstract:
The processing of metals through Equal Channel Angular Pressing (ECAP) leads to their remarkable strengthening. The ECAP dies control the amount of strain imposed on the material through its geometry, especially through the angle between the die channels, and thus the microstructural and mechanical properties evolution of the material. The present study describes the design of an ECAP die whose utilization and maintenance are facilitated, and that also controls the eventual undesired flow of the material during processing. The proposed design was validated through numerical simulations procedures using commercial software. The die was manufactured according to the present design and tested. Tests using aluminum alloys also indicated to be suitable for the processing of higher strength alloys.
Keywords: ECAP, mechanical design, numerical methods, SPD.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 7902168 An Evaluation of Neural Network Efficacies for Image Recognition on Edge-AI Computer Vision Platform
Abstract:
Image recognition enables machine-like robotics to understand a scene and plays an important role in computer vision applications. Computer vision platforms as physical infrastructure, supporting Neural Networks for image recognition, are deterministic to leverage the performance of different Neural Networks. In this paper, three different computer vision platforms – edge AI (Jetson Nano, with 4GB), a standalone laptop (with RTX 3000s, using CUDA), and a web-based device (Google Colab, using GPU) are investigated. In the case study, four prominent neural network architectures (including AlexNet, VGG16, GoogleNet, and ResNet (34/50)), are deployed. By using public ImageNets (Cifar-10), our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.
Keywords: AlexNet, VGG, GoogleNet, ResNet, ImageNet, Cifar-10, Edge AI, Jetson Nano, CUDA, GPU.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2322167 Effectual Reversible Watermarking Method for Hide the Patient Details in Brain Tumor Image
Authors: K. Amudha, C. Nelson Kennedy Babu, S. Balu
Abstract:
The security of the medical images and its related data is the major research area which is to be concentrated in today’s era. Security in the medical image indicates that the physician may hide patients’ related data in the medical image and transfer it safely to a defined location using reversible watermarking. Many reversible watermarking methods had proposed over the decade. This paper enhances the security level in brain tumor images to hide the patient’s detail, which has to be conferred with other physician’s suggestions. The details or the information will be hidden in Non-ROI area of the image by using the block cipher algorithm. The block cipher uses different keys to extract the details that are difficult for the intruder to detect all the keys and to spot the details, which are the key advantage of this method. The ROI is the tumor area and Non-ROI is the area rest of ROI. The Non-ROI should not be spoiled in any cause and the details in the Non-ROI should be extracted correctly. The reversible watermarking method proposed in this paper performs well when compared to existing methods in the process of extraction of an original image and providing information security.Keywords: Brain tumor images, Block Cipher, Reversible watermarking, ROI.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 13412166 3D Anisotropic Diffusion for Liver Segmentation
Authors: Wan Nural Jawahir Wan Yussof, Hans Burkhardt
Abstract:
Liver segmentation is the first significant process for liver diagnosis of the Computed Tomography. It segments the liver structure from other abdominal organs. Sophisticated filtering techniques are indispensable for a proper segmentation. In this paper, we employ a 3D anisotropic diffusion as a preprocessing step. While removing image noise, this technique preserve the significant parts of the image, typically edges, lines or other details that are important for the interpretation of the image. The segmentation task is done by using thresholding with automatic threshold values selection and finally the false liver region is eliminated using 3D connected component. The result shows that by employing the 3D anisotropic filtering, better liver segmentation results could be achieved eventhough simple segmentation technique is used.Keywords: 3D Anisotropic Diffusion, non-linear filtering, CT Liver.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16012165 A Novel Computer Vision Method for Evaluating Deformations of Fibers Cross Section in False Twist Textured Yarns
Authors: Dariush Semnani, Mehdi Ahangareianabhari, Hossein Ghayoor
Abstract:
In recent five decades, textured yarns of polyester fiber produced by false twist method are the most important and mass-produced manmade fibers. There are many parameters of cross section which affect the physical and mechanical properties of textured yarns. These parameters are surface area, perimeter, equivalent diameter, large diameter, small diameter, convexity, stiffness, eccentricity, and hydraulic diameter. These parameters were evaluated by digital image processing techniques. To find trends between production criteria and evaluated parameters of cross section, three criteria of production line have been adjusted and different types of yarns were produced. These criteria are temperature, drafting ratio, and D/Y ratio. Finally the relations between production criteria and cross section parameters were considered. The results showed that the presented technique can recognize and measure the parameters of fiber cross section in acceptable accuracy. Also, the optimum condition of adjustments has been estimated from results of image analysis evaluation.Keywords: Computer Vision, Cross Section Analysis, Fibers Deformation, Textured Yarn
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16502164 In Vitro Study of Coded Transmission in Synthetic Aperture Ultrasound Imaging Systems
Authors: Ihor Trots, Yuriy Tasinkevych, Andrzej Nowicki, Marcin Lewandowski
Abstract:
In the paper the study of synthetic transmit aperture method applying the Golay coded transmission for medical ultrasound imaging is presented. Longer coded excitation allows to increase the total energy of the transmitted signal without increasing the peak pressure. Moreover signal-to-noise ratio and penetration depth are improved while maintaining high ultrasound image resolution. In the work the 128-element linear transducer array with 0.3 mm inter-element spacing excited by one cycle and the 8 and 16- bit Golay coded sequences at nominal frequency 4 MHz was used. To generate a spherical wave covering the full image region a single element transmission aperture was used and all the elements received the echo signals. The comparison of 2D ultrasound images of the tissue mimicking phantom and in vitro measurements of the beef liver is presented to illustrate the benefits of the coded transmission. The results were obtained using the synthetic aperture algorithm with transmit and receive signals correction based on a single element directivity function.Keywords: Golay coded sequences, radiation pattern, signal processing, synthetic aperture, ultrasound imaging.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16772163 The Use of Appeals in Green Printed Advertisements: A Case of Product Orientation and Organizational Image Orientation Ads
Authors: Chutima Ruanguttamanun
Abstract:
Despite the relatively large number of studies that have examined the use of appeals in advertisements, research on the use of appeals in green advertisements is still underdeveloped and needs to be investigated further, as it is definitely a tool for marketers to create illustrious ads. In this study, content analysis was employed to examine the nature of green advertising appeals and to match the appeals with the green advertisements. Two different types of green print advertisings, product orientation and organizational image orientation were used. Thirty highly educated participants with different backgrounds were asked individually to ascertain three appeals out of thirty-four given appeals found among forty real green advertisements. To analyze participant responses and to group them based on common appeals, two-step K-mean clustering is used. The clustering solution indicates that eye-catching graphics and imaginative appeals are highly notable in both types of green ads. Depressed, meaningful and sad appeals are found to be highly used in organizational image orientation ads, whereas, corporate image, informative and natural appeals are found to be essential for product orientation ads.
Keywords: Advertising appeals, green marketing, green advertisement, printed advertisement.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 29372162 Gait Biometric for Person Re-Identification
Authors: Lavanya Srinivasan
Abstract:
Biometric identification is to identify unique features in a person like fingerprints, iris, ear, and voice recognition that need the subject's permission and physical contact. Gait biometric is used to identify the unique gait of the person by extracting moving features. The main advantage of gait biometric to identify the gait of a person at a distance, without any physical contact. In this work, the gait biometric is used for person re-identification. The person walking naturally compared with the same person walking with bag, coat and case recorded using long wave infrared, short wave infrared, medium wave infrared and visible cameras. The videos are recorded in rural and in urban environments. The pre-processing technique includes human identified using You Only Look Once, background subtraction, silhouettes extraction and synthesis Gait Entropy Image by averaging the silhouettes. The moving features are extracted from the Gait Entropy Energy Image. The extracted features are dimensionality reduced by the Principal Component Analysis and recognized using different classifiers. The comparative results with the different classifier show that Linear Discriminant Analysis outperform other classifiers with 95.8% for visible in the rural dataset and 94.8% for longwave infrared in the urban dataset.
Keywords: biometric, gait, silhouettes, You Only Look Once
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5372161 An Approximation of Daily Rainfall by Using a Pixel Value Data Approach
Authors: Sarisa Pinkham, Kanyarat Bussaban
Abstract:
The research aims to approximate the amount of daily rainfall by using a pixel value data approach. The daily rainfall maps from the Thailand Meteorological Department in period of time from January to December 2013 were the data used in this study. The results showed that this approach can approximate the amount of daily rainfall with RMSE=3.343.
Keywords: Daily rainfall, Image processing, Approximation, Pixel value data.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17592160 New Nonlinear Filtering Strategies for Eliminating Short and Long Tailed Noise in Images with Edge Preservation Properties
Authors: E. Srinivasan, D. Ebenezer
Abstract:
Midpoint filter is quite effective in recovering the images confounded by the short-tailed (uniform) noise. It, however, performs poorly in the presence of additive long-tailed (impulse) noise and it does not preserve the edge structures of the image signals. Median smoother discards outliers (impulses) effectively, but it fails to provide adequate smoothing for images corrupted with nonimpulse noise. In this paper, two nonlinear techniques for image filtering, namely, New Filter I and New Filter II are proposed based on a nonlinear high-pass filter algorithm. New Filter I is constructed using a midpoint filter, a highpass filter and a combiner. It suppresses uniform noise quite well. New Filter II is configured using an alpha trimmed midpoint filter, a median smoother of window size 3x3, the high pass filter and the combiner. It is robust against impulse noise and attenuates uniform noise satisfactorily. Both the filters are shown to exhibit good response at the image boundaries (edges). The proposed filters are evaluated for their performance on a test image and the results obtained are included.Keywords: Image filters, Midpoint filter, Nonlinear filters, Nonlinear highpass filter, Order-statistic filters, Rank-order filters.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1452