In this paper, the performance of Convolution Neural Network (CNN) in image recognition and emotion recognition in speech will be presented. Feature extraction and selection in pattern recognition is an important issue and have been frequently discussed. Moreover, twodimensional signals such as image and voice signals are hard to be modelled well by traditional models like SVM. The ability of C...

Machine learning methods are used today for most recognition problems. Convolutional Neural Networks (CNN) have time and again proved successful for many image processing tasks primarily for their architecture. In this paper we propose to apply CNN to small data sets like for example, personal albums or other similar environs where the size of training dataset is a limitation, within the framew...

Pedestrian detection is a vision task with many practical applications in video surveillance, road safety, autonomous driving and military. However, it is much more difficult compared to the detection of other visual objects, because of the tremendous variations in the inner region as well as the outer shape of the pedestrian pattern. In this paper, we propose a pedestrian detection approach th...

Scene text recognition plays an important role in many computer vision applications. The small size of available public available scene text datasets is the main challenge when training a text recognition CNN model. In this paper, we propose a CNN based Chinese text recognition algorithm. To enlarge the dataset for training the CNN model, we design a synthetic data engine for Chinese scene char...

Convolutional Neural Networks (CNNs) are powerful models that achieve impressive results for image classification. In addition, pre-trained CNNs are also useful for other computer vision tasks as generic feature extractors [1]. This paper aims to gain insight into the feature aspect of CNN and demonstrate other uses of CNN features. Our results show that CNN feature maps can be used with Random...

A novel variational autoencoder is developed to model images, as well as associated labels or captions. The Deep Generative Deconvolutional Network (DGDN) is used as a decoder of the latent image features, and a deep Convolutional Neural Network (CNN) is used as an image encoder; the CNN is used to approximate a distribution for the latent DGDN features/code. The latent code is also linked to g...

The adaptability of the convolutional neural network (CNN) technique for aerodynamic meta-modeling tasks is probed in this work. The primary objective is to develop suitable CNN architecture for variable flow conditions and object geometry, in addition to identifying a sufficient data preparation process. Multiple CNN structures were trained to learn the lift coefficients of the airfoils with a...

The relationship between Cellular Neural/Nonlinear Networks (CNNs) and Partial Differential Equations (PDEs) is investigated. The equivalence between a discrete-space CNN model and a continuous-space PDE model is rigorously defined. The problem of the equivalence is split into two sub-problems: approximation and topological equivalence, that can be explicitly studied for any CNN models. It is k...

Fast and robust classification of feature vectors is a crucial task in a number of real-time systems. A cellular neural/nonlinear network universal machine (CNN-UM) [1, 2] can be applied very efficiently as a feature detector and also for post-processing the results for object recognition. This paper shows how a robust classification scheme based on adaptive resonance theory (ART) [3] can also ...

Recent CNN-based object detection methods have drastically improved their performances but still use a single classifier as opposed to ”multiple experts” in categorizing objects. The main motivation of introducing multi-experts is twofold: i) to allow different experts to specialize in different fundamental object shape priors and ii) to better capture the appearance variations caused by differ...