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.
Automatic segmentation of the left ventricle (LV) can become a useful tool in echocardiography, for instance to provide automatic ejection fraction measurements or to initialize deformation imaging algorithms. Deep neural networks have recently shown very promising results for improving image classification and segmentation. These methods learn using only a set of input and output data, but require...
As an artificial intelligent technique, artificial neural networks (ANNs) have been applied successfully in a wide range of fields due to its effective learning ability. In this paper, we conduct an empirical application on fragrance bottle form design due to its wide variety of appearances. For getting a better structure of the ANN model to develop the consumer-oriented expert system, we conduct...
We present a novel method for training (evolving) fully convolutional neural networks (CNNs) for deformable object manipulation. Instead of using a weight update rule, we evolve an ensemble of compositional pattern generating networks (CPPNs) by means of a genetic algorithm (GA). These ensembles generate the convolutional kernels that comprise the CNN. This allows the GA to search for fit kernels...
We present an approach for unsupervised computation of local shape descriptors, which relies on the use of linear autoencoders for characterizing local regions of complex shapes. The proposed approach responds to the need for a robust scheme to index binary images using local descriptors, which arises when only few examples of the complete images are available for training, thus making inaccurate...
The number of known and unknown plant species increases as time goes by. Research on plant species can be further advanced if there is a quick and accurate system that can identify plants and hasten the classification process. This system will not only help in accelerating plant classification, but will also allow people who are not morphological experts to conduct their own studies. LeaVes is an...
This paper presents an accurate and automatic algorithm to recognize and count fish in the video footages of fishery operations. The unique character of the approach is that it combines machine learning techniques with statistical methods to fully make use the benefits of these algorithms. The approach consists of three major stages including video data preparation such as noise deduction, preliminary...
Sparse representation-based classification (SRC) has been recently attracted a great interest among the signal processing society. SRC applies a discriminative representation using training samples to separate signals into their classes. In existing SRC methods, the dictionary size, which highly affects the performance, is manually set. Moreover, they are linear classifiers, and thus, they are not...
The fundamental problem in applying geophysical mapping to locate unexploded ordnance (UXO) is distinguishing true UXO from non-UXO. Enhancing the accuracy of UXO detection has multiple benefits, especially in the areas of cost savings and safety. We investigated discrimination approaches using both magnetic field data and numerically modeled data. Libraries of total field magnetic (TFM) responses...
Deep architectures have been used in transfer learning applications, with the aim of improving the performance of networks designed for a given problem by reusing knowledge from another problem. In this work we addressed the transfer of knowledge between deep networks used as classifiers of digit and shape images, considering cases where only the set of class labels, or only the data distribution,...
Gender recognition has important applications in apparel design, social security, and human-computer interaction systems. In this paper, we investigate gender-recognition technologies using 3-D human body shape. The front and side silhouettes from 459 female subjects and 107 male subjects were extracted and then modeled using normalized Elliptic Fourier descriptors. Principal Component Analysis (PCA)...
The voice conversion system modifies the speaker specific features of the source speaker so that it sounds like a target speaker speech. The voice individuality of the speech signal is characterized at various levels such as shape of the glottal excitation, shape of the vocal tract and the long term prosodic features. In this work, Line Spectral Frequencies (LSF) are used to represent the shape of...
This paper presents a comparative study of several classification methods for the task of recognizing traffic signs in urban areas. These classification methods are artificial neural network (ANN), k-nearest neighbors (kNN), support vector machine (SVM), and random forest (RF). First, HSI-based color segmentation process is applied to obtain candidate regions. Using centroid-based feature, these regions...
Pulse shape discrimination is investigated using artificial neural networks, namely linear vector quantization and self organizing maps which are employed for classifying neutron and gamma rays at a variety of energies and for different relative sizes of the training and test sets. While classification performance confirms that both approaches are capable of excellent discrimination, some differences...
Failure bitmaps of manufactured memory arrays may contain the information of some systematic defects and have hence been used to monitor the process and to improve the memory yield. It is important to have an accurate flow to classify the memory failure bitmap signatures. The memory bitmap signature classification can be either dictionary based or machine learning based. This paper introduces a hybrid...
In this paper we propose a novel face hallucination algorithm to synthesize a high-resolution face image from several low-resolution input face images. As described in Liu et al. [8]'s work, face hallucination uses two models: a global parametric model which synthesizes global face shapes from eigenfaces, and a local parametric model which enhances the local high frequency details. We follow a similar...
When studying mobile robot to recognize shape of object in dynamic surroundings, we proposed a hybrid recognition algorithm based on the combination of rough set theory and BP neural network. RS has the capability for intelligent data analysis, and BP network can approach most problems accurately and exactly, the algorithm put respective advantages of two theories to use. Firstly, information table...
Discriminating between the magnetizing inrush and the internal fault of a power transform is a major challenge when designing differential transformer protection. In this paper, a novel method, which is based on mathematical morphology (MM) and artificial neural network (ANN), is proposed to solve this problem. Firstly, an MM based stage is used to extract shape features from differential currents,...
Adaptive Neuro-Fuzzy Inference System (ANFIS) has become a popular tool in neuro-fuzzy modeling. However, since it includes many parameters needed to be set, its designing process is a complicated and time-intensive task for experimenters. To tackle this problem, in this paper we implement the Design of Experiment (DOE) technique to identify the significant parameters of ANFIS when it applies to the...
In this pater, we present a complete fingerprint recognition system using an Artificial Neural Network (ANN). The ANN is trained by back-propagation algorithm on a set of fingerprint images. Pseudo Zernike Moments (PZM) will be used as a features vector for all images. To detect the region of interest on the fingerprint image, we have used shape information whichis characterized by elliptical shape...
In this work, a combination of artificial neural network (ANN), Fourier descriptors (FD) and spatial domain analysis (SDA) has been proposed for the development of an automatic fruits identification and sorting system. Fruits images are captured using digital camera inclined at different angles to the horizontal. Segmentation is used for the classification of the preprocessed images into two non-overlapping...
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.