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.
In real-world applications, factors such as head pose variation, occlusion, and poor image quality make facial expression recognition (FER) an open challenge. In this paper, a novel conditional convolutional neural network enhanced random forest (CoNERF) is proposed for FER in unconstrained environment. Our method extracts robust deep salient features from saliency-guided facial patches to reduce...
This paper aims to classify normal/abnormal heart sound signals from PhysioNet/CinC challenge 2016. The heart sound signals are segmented into four states, i.e., the first heart sound, systolic interval, the second heart sound, and diastolic interval. Multi-features are extracted from time domain, frequency domain and entropy, which are formed into three features sets. The first features set includes...
Coin recognition is one of the prime important activities for modern banking and currency processing systems in which machine vision is widely used. The technique at the heart of such systems is object recognition in a digital image. Although it has high recognition speed, the traditional method of coin recognition can not recognize the coins with similar sizes. This paper presents a method based...
In this paper, we address the problem of natural flower classification. It is a challenging task due to the non-rigid deformation, illumination changes, and inter-class similarity. We build a large dataset of flower images in the wide with 79 categories and propose a novel framework based on convolutional neural network (CNN) to solve this problem. Unlike other methods using hand-crafted visual features,...
Interactive learning in class or off-class is crucial to teaching and learning. In this paper, we propose an intelligent learning system for supporting student interactive learning through engagement study, which is based on three modules, i.e., attendance management, teacher-student (T&S) communication, visual focus of attention(VFOA) recognition. Attendance management matches the student's identity...
To overcome the deficiencies of the existing methods used in the estimation of the crowd flow with high-density and multi-motion direction, a crowd flow estimation method based on dynamic texture and generalized regression neural network (GRNN) is presented in this paper. The method firstly extracts the dynamic texture features through optical flow, performs the moving crowd segmentation by the dynamic...
Visual Object tracking is one of the key problems is machine vision. A contourlet transform based visual object tracking method is given in this paper. Being one of the multi-scale geometric analysis methods, the contourlet transform has better performance than the traditional wavelet transform to describe the edge feature of visual objects. The contourlet coefficients are firstly obtained and parts...
It is conductive to discover the fire or smoke leakage in the monitor region that detecting the smoke area clearly. Firstly, an adaptive LOG algorithm of smoke detection based on energy difference is proposed by the paper. After detecting the enhancement smoke area by energy difference between frames, dynamic accumulation, filtering and extracting smoke leakage position will be performed. The experiment...
A new framework of image encryption via voice feature is proposed. Voice data is preprocessed and the MFCC coefficients are firstly calculated on each sub-frame; an iterated vector quantization is then applied on the MFCC data to obtain the key to image encryption and decryption. Image encryption and decryption is done in the frequency domain with a simple XOR operation. Due to the uniqueness and...
This paper analyzes the craft of vacuum casting and proposes modularized frame of a new automated vacuum casting controlling system which is integrated by four sub-modules that are main-control module, electric control module, execution module and detection module. Specially, because bubbles affect quality of casting and realization of full automated control, this paper studied an on-line automated...
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.