The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Obtaining semantic information is crucial in order to implement complex robotic applications successfully. Therefore, it commonly expected from the robotics systems to be equipped with advanced hardware and software. In this study, the simulation results of a robotic arm, which manipulates the recognized objects using deep neural networks considering the physical features, are given for 10 different...
Automatic image captioning has received increasing attention in recent years. Although there are many English datasets developed for this problem, there is only one Turkish dataset and it is very small compared to its English counterparts. Creating a new dataset for image captioning is a very costly and time consuming task. This work is a first step towards transferring the available, large English...
This paper deals with the field of computer vision, mainly for the application of deep learning in object detection task. On the one hand, there is a simple summary of the datasets and deep learning algorithms commonly used in computer vision. On the other hand, a new dataset is built according to those commonly used datasets, and choose one of the network called faster r-cnn to work on this new dataset...
Convolution neural networks (CNNs) eliminate the need for feature extraction which is one of the most important and time-consuming part of traditional machine learning (ML) methods. However, the challenge of training a deep CNN model with a limited amount of training data still remains. Transfer learning and parameter fine-tuning have emerged as solutions to this problem. Following the recent trends,...
While the task of Optical Character Recognition is deemed to be a solved problem in many languages, it still requires certain improvements in some languages with more complex script structures such as Farsi. Furthermore, Deep Convolution Neural Networks have reached excellent results in various computer vision tasks, including character recognition. Although, these networks require a great amount...
No-Reference image quality assessment is a challenging problem of great interest to computer vision research community. This paper proposes to find a general solution to measure image quality for both human and computer vision system. A supervised deep neural network, called Deep Algorithm Quality (DAQ), is designed to blindly measure the human visual quality of benchmark images as well as to predict...
Three-dimensional head pose estimation has been an important and challenging task in computer vision partly because of its diverse applications. In this paper, we propose a new method to estimate head pose for the faces in the wild using deep neural network based on classification, rather than conventional regression. The network consists of three CNNs, corresponding to three head pose components,...
Human Activity detection is an imperative area of research in computer vision. This paper focuses on activity recognition by construction personnel at the construction sites. The method uses bag of features (BOF) approach to detect an activity. Here we have considered five types of activities done at construction sites namely ladder climbing, brick laying, carpentry work, painting and plastering work...
Human Activity analysis is one of the most captivating and important open problem in automated video surveillance community. In recent years, most of the analysis of human activities/behavior is carried out using computer vision & pattern recognition techniques and has paved the way for amalgamation of various such fields. This paper gives an assessment of this new development, proposed to analyze...
This paper presents an unsupervised visual theme discovery framework as a better (more compact and effective) alternative for semantic representation of visual contents. Firstly, a tag filtering algorithm was proposed focusing on the tag’s ability of visual content description. Then a spectral clustering algorithm is applied to cluster tags into visual themes based on their visual similarity...
A boosted convolutional neural network (BCNN) system is proposed to enhance the pedestrian detection performance in this work. Being inspired by the classic boosting idea, we develop a weighted loss function that emphasizes challenging samples in training a convolutional neural network (CNN). Two types of samples are considered challenging: 1) samples with detection scores falling in the decision...
Automatic crater detection in planetary images is an important task with many applications in planetary science, spacecraft navigation, landing, and control. Typically, crater detection algorithms consist of two main steps: candidate crater region extraction and crater verification. Various methods have been proposed for extracting candidate crater regions, ranging from detecting circular/elliptical...
Studying marine plankton is critical to assessing the health of the world's oceans. To sample these important populations, oceanographers are increasingly using specially engineered in situ digital imaging systems that produce very large data sets. Most automated annotation efforts have considered data from individual systems in isolation. This is predicated on the assumption that the images from...
In this paper we address the problem of human action recognition from video sequences. Inspired by the exemplary results obtained via automatic feature learning and deep learning approaches in computer vision, we focus our attention towards learning salient spatial features via a convolutional neural network (CNN) and then map their temporal relationship with the aid of Long-Short-Term-Memory (LSTM)...
Graph matching is an important problem in the field of computer vision. Graph matching problem can be represented as quadratic assignment problem. Because the problem is known to be NP-hard, optimal solution is hardly achievable so that a lot of algorithms are proposed to approximate it. Although there have been many studies about fast and accurate approximations, there have been few studies about...
Assessment of aging civil infrastructure should be done periodically to getting information about the structural condition. In context to it, classification, detection, and localization of cracks within these concrete structures is of paramount importance. The most commonly used procedure, i.e. visual inspection, is executed manually by human inspectors, and thus, its accuracy depends on personnel's...
Over the last five years Deep Neural Nets have offered more accurate solutions to many problems in speech recognition, and computer vision, and these solutions have surpassed a threshold of acceptability for many applications. As a result, Deep Neural Networks have supplanted other approaches to solving problems in these areas, and enabled many new applications. While the design of Deep Neural Nets...
Object detection is a challenging task in the field of pattern recognition. The objective of object detection is to locate the target objects in the testing images. In this paper, we use SVM trained active basis model as a sparse coding model for representing objects. The sparse coding model represents each image as the linear superposition of a small number of Gabor wavelets selected from an over-complete...
Hereby in this paper, we are interested to extraction methods and classification in case of image classification and recognition application. We expose the performance of training models on varying classifier algorithms on Caltech 101 images categories. For feature extraction functions we evaluate the use of the classical SURF technique against global color feature extraction. The purpose of our work...
Inferring the aesthetic quality of images is a challenging computer vision task due to its subjective and conceptual nature. Most image aesthetics evaluation approaches focused on designing handcrafted features, and only a few adopted learning of relevant and imperative characteristics in a data-driven manner. In this paper, we propose to attune Convolutional Neural Networks (CNNs) for image aesthetics...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.