Search results for: product image
5540 Data Augmentation for Early-Stage Lung Nodules Using Deep Image Prior and Pix2pix
Authors: Qasim Munye, Juned Islam, Haseeb Qureshi, Syed Jung
Abstract:
Lung nodules are commonly identified in computed tomography (CT) scans by experienced radiologists at a relatively late stage. Early diagnosis can greatly increase survival. We propose using a pix2pix conditional generative adversarial network to generate realistic images simulating early-stage lung nodule growth. We have applied deep images prior to 2341 slices from 895 computed tomography (CT) scans from the Lung Image Database Consortium (LIDC) dataset to generate pseudo-healthy medical images. From these images, 819 were chosen to train a pix2pix network. We observed that for most of the images, the pix2pix network was able to generate images where the nodule increased in size and intensity across epochs. To evaluate the images, 400 generated images were chosen at random and shown to a medical student beside their corresponding original image. Of these 400 generated images, 384 were defined as satisfactory - meaning they resembled a nodule and were visually similar to the corresponding image. We believe that this generated dataset could be used as training data for neural networks to detect lung nodules at an early stage or to improve the accuracy of such networks. This is particularly significant as datasets containing the growth of early-stage nodules are scarce. This project shows that the combination of deep image prior and generative models could potentially open the door to creating larger datasets than currently possible and has the potential to increase the accuracy of medical classification tasks.Keywords: medical technology, artificial intelligence, radiology, lung cancer
Procedia PDF Downloads 605539 Real-Time Image Encryption Using a 3D Discrete Dual Chaotic Cipher
Authors: M. F. Haroun, T. A. Gulliver
Abstract:
In this paper, an encryption algorithm is proposed for real-time image encryption. The scheme employs a dual chaotic generator based on a three dimensional (3D) discrete Lorenz attractor. Encryption is achieved using non-autonomous modulation where the data is injected into the dynamics of the master chaotic generator. The second generator is used to permute the dynamics of the master generator using the same approach. Since the data stream can be regarded as a random source, the resulting permutations of the generator dynamics greatly increase the security of the transmitted signal. In addition, a technique is proposed to mitigate the error propagation due to the finite precision arithmetic of digital hardware. In particular, truncation and rounding errors are eliminated by employing an integer representation of the data which can easily be implemented. The simple hardware architecture of the algorithm makes it suitable for secure real-time applications.Keywords: chaotic systems, image encryption, non-autonomous modulation, FPGA
Procedia PDF Downloads 5015538 Object Detection in Digital Images under Non-Standardized Conditions Using Illumination and Shadow Filtering
Authors: Waqqas-ur-Rehman Butt, Martin Servin, Marion Pause
Abstract:
In recent years, object detection has gained much attention and very encouraging research area in the field of computer vision. The robust object boundaries detection in an image is demanded in numerous applications of human computer interaction and automated surveillance systems. Many methods and approaches have been developed for automatic object detection in various fields, such as automotive, quality control management and environmental services. Inappropriately, to the best of our knowledge, object detection under illumination with shadow consideration has not been well solved yet. Furthermore, this problem is also one of the major hurdles to keeping an object detection method from the practical applications. This paper presents an approach to automatic object detection in images under non-standardized environmental conditions. A key challenge is how to detect the object, particularly under uneven illumination conditions. Image capturing conditions the algorithms need to consider a variety of possible environmental factors as the colour information, lightening and shadows varies from image to image. Existing methods mostly failed to produce the appropriate result due to variation in colour information, lightening effects, threshold specifications, histogram dependencies and colour ranges. To overcome these limitations we propose an object detection algorithm, with pre-processing methods, to reduce the interference caused by shadow and illumination effects without fixed parameters. We use the Y CrCb colour model without any specific colour ranges and predefined threshold values. The segmented object regions are further classified using morphological operations (Erosion and Dilation) and contours. Proposed approach applied on a large image data set acquired under various environmental conditions for wood stack detection. Experiments show the promising result of the proposed approach in comparison with existing methods.Keywords: image processing, illumination equalization, shadow filtering, object detection
Procedia PDF Downloads 2075537 Integrated Intensity and Spatial Enhancement Technique for Color Images
Authors: Evan W. Krieger, Vijayan K. Asari, Saibabu Arigela
Abstract:
Video imagery captured for real-time security and surveillance applications is typically captured in complex lighting conditions. These less than ideal conditions can result in imagery that can have underexposed or overexposed regions. It is also typical that the video is too low in resolution for certain applications. The purpose of security and surveillance video is that we should be able to make accurate conclusions based on the images seen in the video. Therefore, if poor lighting and low resolution conditions occur in the captured video, the ability to make accurate conclusions based on the received information will be reduced. We propose a solution to this problem by using image preprocessing to improve these images before use in a particular application. The proposed algorithm will integrate an intensity enhancement algorithm with a super resolution technique. The intensity enhancement portion consists of a nonlinear inverse sign transformation and an adaptive contrast enhancement. The super resolution section is a single image super resolution technique is a Fourier phase feature based method that uses a machine learning approach with kernel regression. The proposed technique intelligently integrates these algorithms to be able to produce a high quality output while also being more efficient than the sequential use of these algorithms. This integration is accomplished by performing the proposed algorithm on the intensity image produced from the original color image. After enhancement and super resolution, a color restoration technique is employed to obtain an improved visibility color image.Keywords: dynamic range compression, multi-level Fourier features, nonlinear enhancement, super resolution
Procedia PDF Downloads 5435536 A Stochastic Vehicle Routing Problem with Ordered Customers and Collection of Two Similar Products
Authors: Epaminondas G. Kyriakidis, Theodosis D. Dimitrakos, Constantinos C. Karamatsoukis
Abstract:
The vehicle routing problem (VRP) is a well-known problem in Operations Research and has been widely studied during the last fifty-five years. The context of the VRP is that of delivering or collecting products to or from customers who are scattered in a geographical area and have placed orders for these products. A vehicle or a fleet of vehicles start their routes from a depot and visit the customers in order to satisfy their demands. Special attention has been given to the capacitated VRP in which the vehicles have limited carrying capacity for the goods that are delivered or collected. In the present work, we present a specific capacitated stochastic vehicle routing problem which has many realistic applications. We develop and analyze a mathematical model for a specific vehicle routing problem in which a vehicle starts its route from a depot and visits N customers according to a particular sequence in order to collect from them two similar but not identical products. We name these products, product 1 and product 2. Each customer possesses items either of product 1 or product 2 with known probabilities. The number of the items of product 1 or product 2 that each customer possesses is a discrete random variable with known distribution. The actual quantity and the actual type of product that each customer possesses are revealed only when the vehicle arrives at the customer’s site. It is assumed that the vehicle has two compartments. We name these compartments, compartment 1 and compartment 2. It is assumed that compartment 1 is suitable for loading product 1 and compartment 2 is suitable for loading product 2. However, it is permitted to load items of product 1 into compartment 2 and items of product 2 into compartment 1. These actions cause costs that are due to extra labor. The vehicle is allowed during its route to return to the depot to unload the items of both products. The travel costs between consecutive customers and the travel costs between the customers and the depot are known. The objective is to find the optimal routing strategy, i.e. the routing strategy that minimizes the total expected cost among all possible strategies for servicing all customers. It is possible to develop a suitable dynamic programming algorithm for the determination of the optimal routing strategy. It is also possible to prove that the optimal routing strategy has a specific threshold-type strategy. Specifically, it is shown that for each customer the optimal actions are characterized by some critical integers. This structural result enables us to design a special-purpose dynamic programming algorithm that operates only over these strategies having this structural property. Extensive numerical results provide strong evidence that the special-purpose dynamic programming algorithm is considerably more efficient than the initial dynamic programming algorithm. Furthermore, if we consider the same problem without the assumption that the customers are ordered, numerical experiments indicate that the optimal routing strategy can be computed if N is smaller or equal to eight.Keywords: dynamic programming, similar products, stochastic demands, stochastic preferences, vehicle routing problem
Procedia PDF Downloads 2475535 Damage Analysis in Open Hole Composite Specimens by Digital Image Correlation: Experimental Investigation
Authors: Faci Youcef
Abstract:
In the present work, an experimental study is carried out using the digital image correlation (DIC) technique to analyze the damage and behavior of woven composite carbon/epoxy under tensile loading. The tension mechanisms associated with failure modes of bolted joints in advanced composites are studied, as well as displacement distribution and strain distribution. The evolution value of bolt angle inclination during tensile tests was studied. In order to compare the distribution of displacements and strains along the surface, figures of image mapping are made. Several factors that are responsible for the failure of fiber-reinforced polymer composite materials are observed. It was found that strain concentrations observed in the specimens can be used to identify full-field damage onset and to monitor damage progression during loading. Moreover, there is an interaction between laminate pattern, laminate thickness, fastener size and type, surface strain concentrations, and out-of-plane displacement. Conclusions include a failure analysis associated with bolt angle inclinations and supported by microscopic visualizations of the composite specimen. The DIC results can be used to develop and accurately validate numerical models.Keywords: Carbone, woven, damage, digital image, bolted joint, the inclination of angle
Procedia PDF Downloads 675534 Sorting Fish by Hu Moments
Authors: J. M. Hernández-Ontiveros, E. E. García-Guerrero, E. Inzunza-González, O. R. López-Bonilla
Abstract:
This paper presents the implementation of an algorithm that identifies and accounts different fish species: Catfish, Sea bream, Sawfish, Tilapia, and Totoaba. The main contribution of the method is the fusion of the characteristics of invariance to the position, rotation and scale of the Hu moments, with the proper counting of fish. The identification and counting is performed, from an image under different noise conditions. From the experimental results obtained, it is inferred the potentiality of the proposed algorithm to be applied in different scenarios of aquaculture production.Keywords: counting fish, digital image processing, invariant moments, pattern recognition
Procedia PDF Downloads 3995533 Optimal Policies in a Two-Level Supply Chain with Defective Product and Price Dependent Demand
Authors: Samira Mohabbatdar, Abbas Ahmadi, Mohsen S. Sajadieh
Abstract:
This paper deals with a two-level supply chain consisted of one manufacturer and one retailer for single-type product. The demand function of the customers depends on price. We consider an integrated production inventory system where the manufacturer processes raw materials in order to deliver finished product with imperfect quality to the retailer. Then retailer inspects the products and after that delivers perfect products to customers. The proposed model is based on the joint total profit of both the manufacturer and the retailer, and it determines the optimal ordering lot-size, number of shipment and selling price of the retailer. A numerical example is provided to analyse and illustrate the behaviour and application of the model. Finally, sensitivity analysis of the key parameters are presented to test feasibility of the model.Keywords: supply chain, pricing policy, defective quality, joint economic lot sizing
Procedia PDF Downloads 3265532 Catalytic and Non-Catalytic Pyrolysis of Walnut Shell Waste to Biofuel: Characterisation of Catalytic Biochar and Biooil
Authors: Saimatun Nisa
Abstract:
Walnut is an important export product from the Union Territory of Jammy and Kashmir. After extraction of the kernel, the walnut shell forms a solid waste that needs to be managed. Pyrolysis is one interesting option for the utilization of this walnut waste. In this study microwave pyrolysis reactor is used to convert the walnut shell biomass into its value-added products. Catalytic and non-catalytic conversion of walnut shell waste to oil, gas and char was evaluated using a Co-based catalyst. The catalyst was characterized using XPS and SEM analysis. Pyrolysis temperature, reaction time, particle size and sweeping gas (N₂) flow rate were set in the ranges of 400–600 °C, 40 min, <0.6mm to < 4.75mm and 300 ml min−1, respectively. The heating rate was fixed at 40 °C min−1. Maximum gas yield was obtained at 600 °C, 40 min, particle size range 1.18-2.36, 0.5 molar catalytic as 45.2%. The liquid product catalytic and non-catalytic was characterized by GC–MS analyses. In addition, the solid product was analyzed by means of FTIR & SEM.Keywords: walnut shell, biooil, biochar, microwave pyrolysis
Procedia PDF Downloads 395531 Paddy/Rice Singulation for Determination of Husking Efficiency and Damage Using Machine Vision
Authors: M. Shaker, S. Minaei, M. H. Khoshtaghaza, A. Banakar, A. Jafari
Abstract:
In this study a system of machine vision and singulation was developed to separate paddy from rice and determine paddy husking and rice breakage percentages. The machine vision system consists of three main components including an imaging chamber, a digital camera, a computer equipped with image processing software. The singulation device consists of a kernel holding surface, a motor with vacuum fan, and a dimmer. For separation of paddy from rice (in the image), it was necessary to set a threshold. Therefore, some images of paddy and rice were sampled and the RGB values of the images were extracted using MATLAB software. Then mean and standard deviation of the data were determined. An Image processing algorithm was developed using MATLAB to determine paddy/rice separation and rice breakage and paddy husking percentages, using blue to red ratio. Tests showed that, a threshold of 0.75 is suitable for separating paddy from rice kernels. Results from the evaluation of the image processing algorithm showed that the accuracies obtained with the algorithm were 98.36% and 91.81% for paddy husking and rice breakage percentage, respectively. Analysis also showed that a suction of 45 mmHg to 50 mmHg yielding 81.3% separation efficiency is appropriate for operation of the kernel singulation system.Keywords: breakage, computer vision, husking, rice kernel
Procedia PDF Downloads 3675530 An Erudite Technique for Face Detection and Recognition Using Curvature Analysis
Authors: S. Jagadeesh Kumar
Abstract:
Face detection and recognition is an authoritative technology for image database management, video surveillance, and human computer interface (HCI). Face recognition is a rapidly nascent method, which has been extensively discarded in forensics such as felonious identification, tenable entree, and custodial security. This paper recommends an erudite technique using curvature analysis (CA) that has less false positives incidence, operative in different light environments and confiscates the artifacts that are introduced during image acquisition by ring correction in polar coordinate (RCP) method. This technique affronts mean and median filtering technique to remove the artifacts but it works in polar coordinate during image acquisition. Investigational fallouts for face detection and recognition confirms decent recitation even in diagonal orientation and stance variation.Keywords: curvature analysis, ring correction in polar coordinate method, face detection, face recognition, human computer interaction
Procedia PDF Downloads 2765529 Gene Names Identity Recognition Using Siamese Network for Biomedical Publications
Authors: Micheal Olaolu Arowolo, Muhammad Azam, Fei He, Mihail Popescu, Dong Xu
Abstract:
As the quantity of biological articles rises, so does the number of biological route figures. Each route figure shows gene names and relationships. Annotating pathway diagrams manually is time-consuming. Advanced image understanding models could speed up curation, but they must be more precise. There is rich information in biological pathway figures. The first step to performing image understanding of these figures is to recognize gene names automatically. Classical optical character recognition methods have been employed for gene name recognition, but they are not optimized for literature mining data. This study devised a method to recognize an image bounding box of gene name as a photo using deep Siamese neural network models to outperform the existing methods using ResNet, DenseNet and Inception architectures, the results obtained about 84% accuracy.Keywords: biological pathway, gene identification, object detection, Siamese network
Procedia PDF Downloads 2725528 Prediction of Product Size Distribution of a Vertical Stirred Mill Based on Breakage Kinetics
Authors: C. R. Danielle, S. Erik, T. Patrick, M. Hugh
Abstract:
In the last decade there has been an increase in demand for fine grinding due to the depletion of coarse-grained orebodies and an increase of processing fine disseminated minerals and complex orebodies. These ores have provided new challenges in concentrator design because fine and ultra-fine grinding is required to achieve acceptable recovery rates. Therefore, the correct design of a grinding circuit is important for minimizing unit costs and increasing product quality. The use of ball mills for grinding in fine size ranges is inefficient and, therefore, vertical stirred grinding mills are becoming increasingly popular in the mineral processing industry due to its already known high energy efficiency. This work presents a hypothesis of a methodology to predict the product size distribution of a vertical stirred mill using a Bond ball mill. The Population Balance Model (PBM) was used to empirically analyze the performance of a vertical mill and a Bond ball mill. The breakage parameters obtained for both grinding mills are compared to determine the possibility of predicting the product size distribution of a vertical mill based on the results obtained from the Bond ball mill. The biggest advantage of this methodology is that most of the minerals processing laboratories already have a Bond ball mill to perform the tests suggested in this study. Preliminary results show the possibility of predicting the performance of a laboratory vertical stirred mill using a Bond ball mill.Keywords: bond ball mill, population balance model, product size distribution, vertical stirred mill
Procedia PDF Downloads 2845527 X-Corner Detection for Camera Calibration Using Saddle Points
Authors: Abdulrahman S. Alturki, John S. Loomis
Abstract:
This paper discusses a corner detection algorithm for camera calibration. Calibration is a necessary step in many computer vision and image processing applications. Robust corner detection for an image of a checkerboard is required to determine intrinsic and extrinsic parameters. In this paper, an algorithm for fully automatic and robust X-corner detection is presented. Checkerboard corner points are automatically found in each image without user interaction or any prior information regarding the number of rows or columns. The approach represents each X-corner with a quadratic fitting function. Using the fact that the X-corners are saddle points, the coefficients in the fitting function are used to identify each corner location. The automation of this process greatly simplifies calibration. Our method is robust against noise and different camera orientations. Experimental analysis shows the accuracy of our method using actual images acquired at different camera locations and orientations.Keywords: camera calibration, corner detector, edge detector, saddle points
Procedia PDF Downloads 3995526 The Image of Uganda in Germany: Assessing the Perceptions of Germans about Uganda as a Tourist Destination
Authors: K. V. Nabichu
Abstract:
The rationale of this research was to review how Germans perceive Uganda as a tourism destination, after German visitors arrivals to Uganda remain few compared to other destinations like Kenya. It was assumed that Uganda suffers a negative image in Germany due to negative media influence. The study findings indicate that Uganda is not a popular travel destination in Germany, there is generally lack of travel information about Uganda. Despite the respondents’ hearing about Uganda’s and her beautiful attractions, good climate and friendly people, they also think Uganda is unsafe for travel. Findings further show that Uganda is a potential travel destination for Germans due to her beautifull landscape, rich culture, wild life, primates and the Nile, however political unrest, insecurity, the fear for diseases and poor hygiene hinder Germans from travelling to Uganda. The media, internet as well as friends and relatives were the major primary sources of information on Uganda while others knew about Uganda through their school lessons and sports. Uganda is not well advertised and promoted in Germany.Keywords: destination Uganda and Germany, image, perception, negative media influence
Procedia PDF Downloads 3315525 A Context-Sensitive Algorithm for Media Similarity Search
Authors: Guang-Ho Cha
Abstract:
This paper presents a context-sensitive media similarity search algorithm. One of the central problems regarding media search is the semantic gap between the low-level features computed automatically from media data and the human interpretation of them. This is because the notion of similarity is usually based on high-level abstraction but the low-level features do not sometimes reflect the human perception. Many media search algorithms have used the Minkowski metric to measure similarity between image pairs. However those functions cannot adequately capture the aspects of the characteristics of the human visual system as well as the nonlinear relationships in contextual information given by images in a collection. Our search algorithm tackles this problem by employing a similarity measure and a ranking strategy that reflect the nonlinearity of human perception and contextual information in a dataset. Similarity search in an image database based on this contextual information shows encouraging experimental results.Keywords: context-sensitive search, image search, similarity ranking, similarity search
Procedia PDF Downloads 3515524 Intervening into the World of a Cyber-Bully
Authors: Aanshika Puri, Sakshi Mehrotra
Abstract:
Technology has always been a double edged sword. The constant rut of updating oneself to a better and newer version is the new norm. ‘Being Online’ is the latest addition to one’s everyday routine. Availability of various social online platforms being served on a platter topped with easy and cheap access to the internet makes it simple and doable for people of all social backgrounds. Interestingly, in India, a recent development is the line of demarcation between people from varied backgrounds, doing the vanishing act. One finds everybody on at least one, if not more, social platforms in a desire to stay connected. For instance, this ranges from sending a ‘WhatsApp’ message to a vegetable vendor for ordering your daily needs to vendors and small entrepreneurs. Even a rickshaw puller now has access to a mobile phone, an internet connection and apps/ platforms to stay connected. Recent observations show the extent to which everyone is hooked on to their mobile phones/ tabs/ laptops/ etc. Young mothers use them to distract their children and keep them busy while they finish the task at hand. Exposure to this part of the technology at such a tender age requires responsible and careful handling. Talking of adolescents, their self- image depends on their online social image to a large extent. There is a desire to be liked and accepted by the peer group at all times. Cyber-bullying is a by-product of the 24/7 availability of these resources. There is enough research-based evidence to prove the psychosocial and emotional impact on the development and well-being of the victim. The present paper attempts to understand the dynamics of cyber bullying vis-à-vis the developmental and mental health issues faced by the bully.Keywords: Developmental Psychology, Empathy & Resilience Based Interventions, Mental Well-Being of Cyber Bully, Positive Psychology
Procedia PDF Downloads 2435523 Segmentation of Gray Scale Images of Dropwise Condensation on Textured Surfaces
Authors: Helene Martin, Solmaz Boroomandi Barati, Jean-Charles Pinoli, Stephane Valette, Yann Gavet
Abstract:
In the present work we developed an image processing algorithm to measure water droplets characteristics during dropwise condensation on pillared surfaces. The main problem in this process is the similarity between shape and size of water droplets and the pillars. The developed method divides droplets into four main groups based on their size and applies the corresponding algorithm to segment each group. These algorithms generate binary images of droplets based on both their geometrical and intensity properties. The information related to droplets evolution during time including mean radius and drops number per unit area are then extracted from the binary images. The developed image processing algorithm is verified using manual detection and applied to two different sets of images corresponding to two kinds of pillared surfaces.Keywords: dropwise condensation, textured surface, image processing, watershed
Procedia PDF Downloads 2155522 Cause-Related Marketing: A Review of the Literature
Authors: Chang Hung Chen
Abstract:
Typically the Cause-Related Marketing (CRM) is effective for promoting products, and is also accepted as a role of communication tool for creating a positive image of the corporate. Today, companies are taking Corporate Social Responsibility (CSR) as core activities to build a goal of sustainable development. CRM is not a synonym of CSR. Actually, CRM is a part of CSR, or a type of marketing strategy in CSR framework. This article focuses on the relationship between CSR and CRM, and how the CRM improves the CSR performance of the corporate. The research was conducted through review of literature on the subject area.Keywords: cause-related marketing, corporate social responsibility, corporate image, consumer behavior
Procedia PDF Downloads 3415521 Image Processing on Geosynthetic Reinforced Layers to Evaluate Shear Strength and Variations of the Strain Profiles
Authors: S. K. Khosrowshahi, E. Güler
Abstract:
This study investigates the reinforcement function of geosynthetics on the shear strength and strain profile of sand. Conducting a series of simple shear tests, the shearing behavior of the samples under static and cyclic loads was evaluated. Three different types of geosynthetics including geotextile and geonets were used as the reinforcement materials. An image processing analysis based on the optical flow method was performed to measure the lateral displacements and estimate the shear strains. It is shown that besides improving the shear strength, the geosynthetic reinforcement leads a remarkable reduction on the shear strains. The improved layer reduces the required thickness of the soil layer to resist against shear stresses. Consequently, the geosynthetic reinforcement can be considered as a proper approach for the sustainable designs, especially in the projects with huge amount of geotechnical applications like subgrade of the pavements, roadways, and railways.Keywords: image processing, soil reinforcement, geosynthetics, simple shear test, shear strain profile
Procedia PDF Downloads 2095520 Application of Improved Semantic Communication Technology in Remote Sensing Data Transmission
Authors: Tingwei Shu, Dong Zhou, Chengjun Guo
Abstract:
Semantic communication is an emerging form of communication that realize intelligent communication by extracting semantic information of data at the source and transmitting it, and recovering the data at the receiving end. It can effectively solve the problem of data transmission under the situation of large data volume, low SNR and restricted bandwidth. With the development of Deep Learning, semantic communication further matures and is gradually applied in the fields of the Internet of Things, Uumanned Air Vehicle cluster communication, remote sensing scenarios, etc. We propose an improved semantic communication system for the situation where the data volume is huge and the spectrum resources are limited during the transmission of remote sensing images. At the transmitting, we need to extract the semantic information of remote sensing images, but there are some problems. The traditional semantic communication system based on Convolutional Neural Network cannot take into account the global semantic information and local semantic information of the image, which results in less-than-ideal image recovery at the receiving end. Therefore, we adopt the improved vision-Transformer-based structure as the semantic encoder instead of the mainstream one using CNN to extract the image semantic features. In this paper, we first perform pre-processing operations on remote sensing images to improve the resolution of the images in order to obtain images with more semantic information. We use wavelet transform to decompose the image into high-frequency and low-frequency components, perform bilinear interpolation on the high-frequency components and bicubic interpolation on the low-frequency components, and finally perform wavelet inverse transform to obtain the preprocessed image. We adopt the improved Vision-Transformer structure as the semantic coder to extract and transmit the semantic information of remote sensing images. The Vision-Transformer structure can better train the huge data volume and extract better image semantic features, and adopt the multi-layer self-attention mechanism to better capture the correlation between semantic features and reduce redundant features. Secondly, to improve the coding efficiency, we reduce the quadratic complexity of the self-attentive mechanism itself to linear so as to improve the image data processing speed of the model. We conducted experimental simulations on the RSOD dataset and compared the designed system with a semantic communication system based on CNN and image coding methods such as BGP and JPEG to verify that the method can effectively alleviate the problem of excessive data volume and improve the performance of image data communication.Keywords: semantic communication, transformer, wavelet transform, data processing
Procedia PDF Downloads 705519 Enhancing Sell-In and Sell-Out Forecasting Using Ensemble Machine Learning Method
Authors: Vishal Das, Tianyi Mao, Zhicheng Geng, Carmen Flores, Diego Pelloso, Fang Wang
Abstract:
Accurate sell-in and sell-out forecasting is a ubiquitous problem in the retail industry. It is an important element of any demand planning activity. As a global food and beverage company, Nestlé has hundreds of products in each geographical location that they operate in. Each product has its sell-in and sell-out time series data, which are forecasted on a weekly and monthly scale for demand and financial planning. To address this challenge, Nestlé Chilein collaboration with Amazon Machine Learning Solutions Labhas developed their in-house solution of using machine learning models for forecasting. Similar products are combined together such that there is one model for each product category. In this way, the models learn from a larger set of data, and there are fewer models to maintain. The solution is scalable to all product categories and is developed to be flexible enough to include any new product or eliminate any existing product in a product category based on requirements. We show how we can use the machine learning development environment on Amazon Web Services (AWS) to explore a set of forecasting models and create business intelligence dashboards that can be used with the existing demand planning tools in Nestlé. We explored recent deep learning networks (DNN), which show promising results for a variety of time series forecasting problems. Specifically, we used a DeepAR autoregressive model that can group similar time series together and provide robust predictions. To further enhance the accuracy of the predictions and include domain-specific knowledge, we designed an ensemble approach using DeepAR and XGBoost regression model. As part of the ensemble approach, we interlinked the sell-out and sell-in information to ensure that a future sell-out influences the current sell-in predictions. Our approach outperforms the benchmark statistical models by more than 50%. The machine learning (ML) pipeline implemented in the cloud is currently being extended for other product categories and is getting adopted by other geomarkets.Keywords: sell-in and sell-out forecasting, demand planning, DeepAR, retail, ensemble machine learning, time-series
Procedia PDF Downloads 2455518 A Novel Probabilistic Spatial Locality of Reference Technique for Automatic Cleansing of Digital Maps
Authors: A. Abdullah, S. Abushalmat, A. Bakshwain, A. Basuhail, A. Aslam
Abstract:
GIS (Geographic Information System) applications require geo-referenced data, this data could be available as databases or in the form of digital or hard-copy agro-meteorological maps. These parameter maps are color-coded with different regions corresponding to different parameter values, converting these maps into a database is not very difficult. However, text and different planimetric elements overlaid on these maps makes an accurate image to database conversion a challenging problem. The reason being, it is almost impossible to exactly replace what was underneath the text or icons; thus, pointing to the need for inpainting. In this paper, we propose a probabilistic inpainting approach that uses the probability of spatial locality of colors in the map for replacing overlaid elements with underlying color. We tested the limits of our proposed technique using non-textual simulated data and compared text removing results with a popular image editing tool using public domain data with promising results.Keywords: noise, image, GIS, digital map, inpainting
Procedia PDF Downloads 3405517 Using Environmental Life Cycle Assessment to Design Sustainable Packaging
Authors: Timothy Francis Grant
Abstract:
There are conflicting purposes at play with the design of sustainable packaging which include material reduction, recycling compatibility, use of secondary content and performance of the package in protecting and delivering the product. Life Cycle Assessment (LCA) is able to evaluate these different strategies against environmental metrics such as climate change, land and water use and marine litter pollution. However, LCA has traditionally been too time consuming and expensive to be used effectively in packaging design process. To make LCA practical for packaging technologist and designers a simplified tool is needed to make LCA possible for non-environmental specialists. The Packaging Quick Evaluation Tool (PIQET) is a web-based solution for undertaking LCA of new and existing packaging designs considering the global supply chain and impacts from cradle to grave. PIQET is based on a pre-calculated LCA database covering the materials and processes involved in the packaging lifecycle from cradle to grave. This includes both virgin materials and recycled content, conversion of materials into packaging, and the transportation of packaging to the product filling. In addition, PIQET assesses the impacts once the package is filled looking at storage, transport and product loss through the supply chain. When applied to consumer packaging light weight packages which are note recyclable have lower impacts than more recyclable packages which have a higher mass. Its also apparent that for many products the impacts of product failure and product loss are more important environmentally compared to packaging material efficiency.Keywords: Climate change, Life Cycle Assessment, Marine litter, Packaging sustainability
Procedia PDF Downloads 1235516 Noise Removal Techniques in Medical Images
Authors: Amhimmid Mohammed Saffour, Abdelkader Salama
Abstract:
Filtering is a part of image enhancement techniques, it is used to enhance certain details such as edges in the image that are relevant to the application. Additionally, filtering can even be used to eliminate unwanted components of noise. Medical images typically contain salt and pepper noise and Poisson noise. This noise appears to the presence of minute grey scale variations within the image. In this paper, different filters techniques namely (Median, Wiener, Rank order3, Rank order5, and Average) were applied on CT medical images (Brain and chest). We using all these filters to remove salt and pepper noise from these images. This type of noise consists of random pixels being set to black or white. Peak Signal to Noise Ratio (PSNR), Mean Square Error r(MSE) and Histogram were used to evaluated the quality of filtered images. The results, which we have achieved shows that, these filters, are more useful and they prove to be helpful for general medical practitioners to analyze the symptoms of the patients with no difficulty.Keywords: CT imaging, median filter, adaptive filter and average filter, MATLAB
Procedia PDF Downloads 3075515 Image Reconstruction Method Based on L0 Norm
Authors: Jianhong Xiang, Hao Xiang, Linyu Wang
Abstract:
Compressed sensing (CS) has a wide range of applications in sparse signal reconstruction. Aiming at the problems of low recovery accuracy and long reconstruction time of existing reconstruction algorithms in medical imaging, this paper proposes a corrected smoothing L0 algorithm based on compressed sensing (CSL0). First, an approximate hyperbolic tangent function (AHTF) that is more similar to the L0 norm is proposed to approximate the L0 norm. Secondly, in view of the "sawtooth phenomenon" in the steepest descent method and the problem of sensitivity to the initial value selection in the modified Newton method, the use of the steepest descent method and the modified Newton method are jointly optimized to improve the reconstruction accuracy. Finally, the CSL0 algorithm is simulated on various images. The results show that the algorithm proposed in this paper improves the reconstruction accuracy of the test image by 0-0. 98dB.Keywords: smoothed L0, compressed sensing, image processing, sparse reconstruction
Procedia PDF Downloads 1105514 A t-SNE and UMAP Based Neural Network Image Classification Algorithm
Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang
Abstract:
Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.Keywords: t-SNE, UMAP, fashion MNIST, neural networks
Procedia PDF Downloads 1895513 A Neural Network Classifier for Estimation of the Degree of Infestation by Late Blight on Tomato Leaves
Authors: Gizelle K. Vianna, Gabriel V. Cunha, Gustavo S. Oliveira
Abstract:
Foliage diseases in plants can cause a reduction in both quality and quantity of agricultural production. Intelligent detection of plant diseases is an essential research topic as it may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. This work investigates ways to recognize the late blight disease from the analysis of tomato digital images, collected directly from the field. A pair of multilayer perceptron neural network analyzes the digital images, using data from both RGB and HSL color models, and classifies each image pixel. One neural network is responsible for the identification of healthy regions of the tomato leaf, while the other identifies the injured regions. The outputs of both networks are combined to generate the final classification of each pixel from the image and the pixel classes are used to repaint the original tomato images by using a color representation that highlights the injuries on the plant. The new images will have only green, red or black pixels, if they came from healthy or injured portions of the leaf, or from the background of the image, respectively. The system presented an accuracy of 97% in detection and estimation of the level of damage on the tomato leaves caused by late blight.Keywords: artificial neural networks, digital image processing, pattern recognition, phytosanitary
Procedia PDF Downloads 3215512 Approximation Property Pass to Free Product
Authors: Kankeyanathan Kannan
Abstract:
On approximation properties of group C* algebras is everywhere; it is powerful, important, backbone of countless breakthroughs. For a discrete group G, let A(G) denote its Fourier algebra, and let M₀A(G) denote the space of completely bounded Fourier multipliers on G. An approximate identity on G is a sequence (Φn) of finitely supported functions such that (Φn) uniformly converge to constant function 1 In this paper we prove that approximation property pass to free product.Keywords: approximation property, weakly amenable, strong invariant approximation property, invariant approximation property
Procedia PDF Downloads 6675511 Modeling Visual Memorability Assessment with Autoencoders Reveals Characteristics of Memorable Images
Authors: Elham Bagheri, Yalda Mohsenzadeh
Abstract:
Image memorability refers to the phenomenon where certain images are more likely to be remembered by humans than others. It is a quantifiable and intrinsic attribute of an image. Understanding how visual perception and memory interact is important in both cognitive science and artificial intelligence. It reveals the complex processes that support human cognition and helps to improve machine learning algorithms by mimicking the brain's efficient data processing and storage mechanisms. To explore the computational underpinnings of image memorability, this study examines the relationship between an image's reconstruction error, distinctiveness in latent space, and its memorability score. A trained autoencoder is used to replicate human-like memorability assessment inspired by the visual memory game employed in memorability estimations. This study leverages a VGG-based autoencoder that is pre-trained on the vast ImageNet dataset, enabling it to recognize patterns and features that are common to a wide and diverse range of images. An empirical analysis is conducted using the MemCat dataset, which includes 10,000 images from five broad categories: animals, sports, food, landscapes, and vehicles, along with their corresponding memorability scores. The memorability score assigned to each image represents the probability of that image being remembered by participants after a single exposure. The autoencoder is finetuned for one epoch with a batch size of one, attempting to create a scenario similar to human memorability experiments where memorability is quantified by the likelihood of an image being remembered after being seen only once. The reconstruction error, which is quantified as the difference between the original and reconstructed images, serves as a measure of how well the autoencoder has learned to represent the data. The reconstruction error of each image, the error reduction, and its distinctiveness in latent space are calculated and correlated with the memorability score. Distinctiveness is measured as the Euclidean distance between each image's latent representation and its nearest neighbor within the autoencoder's latent space. Different structural and perceptual loss functions are considered to quantify the reconstruction error. The results indicate that there is a strong correlation between the reconstruction error and the distinctiveness of images and their memorability scores. This suggests that images with more unique distinct features that challenge the autoencoder's compressive capacities are inherently more memorable. There is also a negative correlation between the reduction in reconstruction error compared to the autoencoder pre-trained on ImageNet, which suggests that highly memorable images are harder to reconstruct, probably due to having features that are more difficult to learn by the autoencoder. These insights suggest a new pathway for evaluating image memorability, which could potentially impact industries reliant on visual content and mark a step forward in merging the fields of artificial intelligence and cognitive science. The current research opens avenues for utilizing neural representations as instruments for understanding and predicting visual memory.Keywords: autoencoder, computational vision, image memorability, image reconstruction, memory retention, reconstruction error, visual perception
Procedia PDF Downloads 70