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.
Recently, deep learning became very popular, and was applied to many fields. The convolutional neural networks are often used for representing the layers for deep learning. In this paper, we propose Convolutional Self Organizing Map, which can be applicable to deep learning. Conventional Self Organizing Map uses single layered architecture, and can visualizes and classifies the input data on 2 dimensional...
Human beings have an excellent ability which can form and recognise object categories. In this paper, a novel system of multimodal object recognition and categorization by performing interactive behaviours is introduced. Video clips are filmed as the raw input of the system. A dataset of 100 objects with 18 categories and five different interactions is used to evaluated the performance. The convolutional...
In this paper, we utilize deep Convolutional Neural Networks (CNNs) to classify handwritten music symbols in HOMUS data set. HOMUS data set is made up of various types of strokes which contain time information and it is expected that online techniques are more appropriate for classification. However, experimental results show that CNN which does not use time information achieved classification accuracy...
Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing this problem is to create features from unlabeled data. In this paper we propose a new method for training a CNN, with no need for labeled instances. This method for...
License Plate Recognition System (LPRS) plays a vital role in smart city initiatives such as traffic control, smart parking, toll management and security. In this article, a cloud-based LPRS is addressed in the context of efficiency where accuracy and speed of processing plays a critical role towards its success. Signature-based features technique as a deep convolutional neural network in a cloud...
The classification of graphs is a key challenge within many scientific fields using graphs to represent data and is an active area of research. Graph classification can be critical in identifying and labelling unknown graphs within a dataset and has seen application across many scientific fields. Graph classification poses two distinct problems: the classification of elements within a graph and the...
The paper proposes a method for human action recognition which focuses on solving the problems resulting from complex hand-crafted features. The method aggregates both spatial and temporal features and can be divided into two parts: multi-channel feature fusion and action classification. For adding motion and shape information, it firstly combines gray, optical flow and Difference of Gaussian(Dog)...
Even though face recognition in frontal view and normal lighting condition works very well, the performance degenerates sharply in extreme conditions. In real applications, both the lighting and pose variation will always be encountered at the same time. Accordingly we propose an end-to-end face recognition method to deal with pose and illumination simultaneously based on convolutional neural networks...
Deep learning is a rather new approach to machine learning that has achieved remarkable results in a large number of different image processing applications. Lately, application of deep learning to detect and classify spectral and spatio-spectral signatures in hyperspectral images has emerged. The high dimensionality of hyperspectral images and the limited amount of labelled training data makes deep...
Subjectivity detection aims to distinguish natural language as either opinionated (positive or negative) or neutral. In word vector based convolutional neural network models, a word meaning is simply a signal that helps to classify larger entities such as a document. Previous works do not usually consider prior distribution when using sliding windows to learn word embedding's and, hence, they are...
In this paper, we apply speech and audio processing techniques to bird vocalizations and for the classification of birds found in the lower Himalayan regions. Mel frequency cepstral coefficients (MFCC) are extracted from each recording. As a result, the recordings are now represented as varying length sets of feature vectors. Dynamic kernel based support vector machines (SVMs) and deep neural networks...
Face detection and face attribute recognition, as hot topics in the field of computer vision, have been well studied. However, over the years, face detection and attribute recognition are regarded as different tasks and designed separately, which ignores the fact that they both classify samples based on the knowledge of skin color, face outline and face components etc. In this paper, we describes...
Kernel methods and neural networks (NN) are two of the most powerful tools of machine learning to solve the engineering and science problems. In this paper, we propose kernel ridge regression (KRR) and NN to estimate the compressive strength (CS) of concrete with recycled aggregate based on the values of cement, natural aggregate, recycled aggregate, sand, and water. We collected a dataset of 182...
Recently deep Convolutional Neural Networks have been successfully applied in many computer vision tasks and achieved promising results. So some works have introduced the deep learning into face anti-spoofing. However, most approaches just use the final fully-connected layer to distinguish the real and fake faces. Inspired by the idea of each convolutional kernel can be regarded as a part filter,...
Convolution operations dominate the total execution time of deep convolutional neural networks (CNNs). In this paper, we aim at enhancing the performance of the state-of-the-art convolution algorithm (called Winograd convolution) on the GPU. Our work is based on two observations: (1) CNNs often have abundant zero weights and (2) the performance benefit of Winograd convolution is limited mainly due...
In this article, the modified probabilistic neural network (MPNN) is proposed. The network is an extension of conventional PNN with the weight coefficients introduced between pattern and summation layer of the model. These weights are calculated by using the sensitivity analysis (SA) procedure. MPNN is employed to the classification tasks and its performance is assessed on the basis of prediction...
This paper proposes a new approach to recognize iris from distantly acquired facial images by utilizing multiple feature descriptors and classifiers. Firstly, Log-Gabor (LG), Contourlet Transform (CT), Gradient Local Auto-Correlation (GLAC) and Convolutional Neural Network (CNN) descriptors are employed on segmented normalized iris image and contextual eye image to extract features. Then, K-Nearest...
Breast cancer is the second leading cause of cancer death in women according to World Health Organization (WHO). Development of computer aided diagnostic (CAD) systems has great importance as a secondary reader systems for a correct diagnosis and treatment process. In this paper, a deep learning based feature extraction method by convolutional neural network (CNN) is proposed for automated mitosis...
This study presents a new method based on convolutional neural network (CNN) for the gearbox fault identification and classification, which does not need the complex feature extraction process as those traditional recognition algorithms do, and it also depress the uncertainty of arbitrary feature selection. The vibration signals of the gearbox under normal and hybrid fault conditions were collected,...
In this manuscript we propose a novel method for jointly page stream segmentation and multi-page document classification.The end goal is to classify a stream of pages as belonging to different classes of documents. We take advantage of the recent state-of-the-art results achieved using deep architectures in related fields such as document image classification, and we adopt similar models to obtain...
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.