Search results for "Deep Learning"
showing 10 items of 337 documents
Outdoor Scenes Pixel-wise Semantic Segmentation using Polarimetry and Fully Convolutional Network
2019
International audience; In this paper, we propose a novel method for pixel-wise scene segmentation application using polarimetry. To address the difficulty of detecting highly reflective areas such as water and windows, we use the angle and degree of polarization of these areas, obtained by processing images from a polarimetric camera. A deep learning framework, based on encoder-decoder architecture, is used for the segmentation of regions of interest. Different methods of augmentation have been developed to obtain a sufficient amount of data, while preserving the physical properties of the polarimetric images. Moreover, we introduce a new dataset comprising both RGB and polarimetric images…
Deep Convolutional Neural Network Based Object Detection Inference Acceleration Using FPGA
2022
Object detection is one of the most challenging yet essential computer vision research areas. It means labeling and localizing all known objects of interest on an input image using tightly fit rectangular bounding boxes around the objects. Object detection, having passed through several evolutions and progressions, nowadays relies on the successes of image classification networks based on deep convolutional neural networks. However, as the depth and complication of convolutional neural networks increased, detection speed reduced, and accuracy increased. Unfortunately, most computer vision applications, such as real-time object tracking on an embedded system, requires lightweight, fast and a…
Detection of Hate Speech Spreaders using Convolutional Neural Networks
2021
In this paper we describe a deep learning model based on a Convolutional Neural Network (CNN). The model was developed for the Profiling Hate Speech Spreaders (HSSs) task proposed by PAN 2021 organizers and hosted at the 2021 CLEF Conference. Our approach to the task of classifying an author as HSS or not (nHSS) takes advantage of a CNN based on a single convolutional layer. In this binary classification task, on the tests performed using a 5-fold cross validation, the proposed model reaches a maximum accuracy of 0.80 on the multilingual (i.e., English and Spanish) training set, and a minimum loss value of 0.51 on the same set. As announced by the task organizers, the trained model presente…
Identifying Images with Ladders Using Deep CNN Transfer Learning
2019
Deep Convolutional Neural Networks (CNNs) as well as transfer learning using their pre-trained models often find applications in image classification tasks. In this paper, we explore the utilization of pre-trained CNNs for identifying images containing ladders. We target a particular use case, where an insurance firm, in order to decide the price for workers’ compensation insurance for its client companies, would like to assess the risk involved in their workplace environments. For this, the workplace images provided by the client companies can be utilized and the presence of ladders in such images can be considered as a workplace hazard and therefore an indicator of risk. To this end, we e…
Teaching in Higher Education: Students’ Deep Learning of Brewing by Labwork
2019
Abstract The amount of theoretical and practical information to be given to students from engineering food specialty is increasingly greater. Within this perspective, it is important to use teaching-learning methods which to develop students’ cognitive ability through the efficient by of them of knowledge acquired at fundamental and specialized disciplines. The article aims to present in an integrated graphical manner the laboratory entitled “Determination of alcoholic concentration of beer by distillation” within the discipline of “Technology and control in the malt and beer industry” that is taught to students in the field of Food Engineering. The integrative approach to the laboratory th…
ICDAR 2021 Competition on Historical Document Classification
2021
International audience; This competition investigated the performance of historical document classification. The analysis of historical documents is a difficult challenge commonly solved by trained humanists. We provided three different classification tasks, which can be solved individually or jointly: font group/script type, location, date. The document images are provided by several institutions and are taken from handwritten and printed books as well as from charters. In contrast to previous competitions, all participants relied upon Deep Learning based approaches. Nevertheless, we saw a great performance variety of the different submitted systems. The easiest task seemed to be font grou…
Fear Sells: Determinants of Fund-Raising Success in the cross-section of Initial Coin Offerings
2021
This paper explores cross-sectionally the determinants of ICO success as measured by the amount of raised funding. Our study is the first that retrieves an intensive hand-collected data library covering the entire population of all 5,033 ICOs launched in the 2014 – 2019 period. Another important novel aspect is that we address the question whether psychological and financial sentiment cached in whitepapers have an impact on the success of ICOs. We employ natural language procession tools and various sentiment dictionaries to assess the sentiment in whitepapers and our results suggest that ICO investors are largely guided by their emotions when making investment decisions. Additionally, to g…
Bridging human and machine learning for the needs of collective intelligence development
2020
There are no doubts that artificial and human intelligence enhance and complement each other. They are stronger together as a team of Collective (Collaborative) Intelligence. Both require training for personal development and high performance. However, the approaches to training (human vs. machine learning) are traditionally very different. If one needs efficient hybrid collective intelligence team, e.g. for managing processes within the Industry 4.0, then all the team members have to learn together. In this paper we point out the need for bridging the gap between the human and machine learning, so that some approaches used in machine learning will be useful for humans and vice-versa, some …
Measuring the Novelty of Natural Language Text Using the Conjunctive Clauses of a Tsetlin Machine Text Classifier
2020
Most supervised text classification approaches assume a closed world, counting on all classes being present in the data at training time. This assumption can lead to unpredictable behaviour during operation, whenever novel, previously unseen, classes appear. Although deep learning-based methods have recently been used for novelty detection, they are challenging to interpret due to their black-box nature. This paper addresses \emph{interpretable} open-world text classification, where the trained classifier must deal with novel classes during operation. To this end, we extend the recently introduced Tsetlin machine (TM) with a novelty scoring mechanism. The mechanism uses the conjunctive clau…
Multimodal biometric recognition systems using deep learning based on the finger vein and finger knuckle print fusion
2020
Recognition systems using multimodal biometrics attracts attention because they improve recognition efficiency and high-security level compared to the unimodal biometrics system. In this study, the authors present a secure multimodal biometrics recognition system based on the deep learning method that uses convolutional neural networks (CNNs). The authors propose two multimodal architectures using the finger knuckle print (FKP) and the finger vein (FV) biometrics with different levels of fusion: the features level fusion and scores level fusion. The features extraction for FKP and FV are performed using transfer learning CNN architectures: AlexNet, VGG16, and ResNet50. The key step aims to …