This work uses newly introduced variations of the sparse representation-based classifier (SRC) to challenge the issue of automatic facial expression recognition (FER) with faces belonging to a wide span of ages. Since...
详细信息
This work uses newly introduced variations of the sparse representation-based classifier (SRC) to challenge the issue of automatic facial expression recognition (FER) with faces belonging to a wide span of ages. Since facial expression is one of the most powerful and immediate ways to disclose individuals' emotions and intentions, the study of emotional traits is an active research topic both in psychology and in engineering fields. To date, automatic FER systems work well with frontal and clean faces, but disturbance factors can dramatically decrease their performance. Aging is a critical disruption element, which is present in any real-world situation and which can finally be considered thanks to the recent introduction of new databases storing expressions over a lifespan. This study addresses the FER with aging challenge using sparse coding (SC) that represents the input signal as the linear combination of the columns of a dictionary. Dictionary learning (DL) is a subfield of SC that aims to learn from the training samples the best space capable of representing the query image. Focusing on one of the main challenges of SC, this work compares the performance of recently introduced DL algorithms. We run both a mixed-age experiment, where all faces are mixed, and a within-age experiment, where faces of young, middle-aged, and old actors are processed independently. We first work with the entire face and then we improve our initial performance using only discriminative patches of the face. Experimental results provide a fair comparison between the two recently developed DL techniques. Finally, the same algorithms are also tested on a database of expressive faces without the aging disturbance element, so as to evaluate DL algorithms' performance strictly on FER.
The marine gas turbine works under variable conditions. High working temperature and complex environment can easily cause defects and failure of blade coating. Since traditional sensors cannot meet the detection requi...
详细信息
ISBN:
(纸本)9781538651957
The marine gas turbine works under variable conditions. High working temperature and complex environment can easily cause defects and failure of blade coating. Since traditional sensors cannot meet the detection requirement of working environment, using infrared thermal wave nondestructive detection has been a research hotspot in recent years. The porosity is an important criterion for evaluating the quality and service life of coatings. This paper proposed a porosity detection method based on Gray Gradient Space Histogram Entropy (GGSHE) combined with sparse representation-based classifier (SRC). First, a 3D model of thermal barrier was established and the surface temperature distributions under different porosities were obtained. Then the difference of average temperature and difference of relative maximum temperature as well as GGSHE are used as the inputs. Through optimization and fitting of the inputs and outputs using SRC, the porosity could be derived. Finally, the corresponding dataset of infrared thermal image was built and porosity prediction experiments using the algorithm were implemented. The results proved that our algorithm can precisely achieve coating porosity detection with acceptable time cost and had practical value in engineering.
Retina located in the back of the eye contains useful information in the diagnosis of certain diseases. By locating a blood vessel's width, color, reflectivity, tortuosity and abnormal branching, one can deduce th...
详细信息
ISBN:
(纸本)9783642139222
Retina located in the back of the eye contains useful information in the diagnosis of certain diseases. By locating a blood vessel's width, color, reflectivity, tortuosity and abnormal branching, one can deduce the existence of these diseases. In order for this to be achieved, blood vessels first need to be extracted from its background in fundus image. In this paper we propose a new method to extract vessels based on Multiscale Production of Matched Filter (MPMF) and sparse representation-based classifier (SRC). First, we locate vessel centerline candidates using multi-scale Gaussian filtering, scale production, double thresholding and centerline detection. Then, the candidates which are centerline pixels are classified with SRC. Particularly, two dictionary elements of vessel and non-vessel are used in the SRC process. Experimental results on two public databases show that the proposed method is good at distinguishing vessel from non-vessel objects and extracting the centerlines of small vessels.
Smart environments with ubiquitous computers are the next generation of information technology, which requires improved human computer interfaces. That is, the computer of the future must be aware of the people in its...
详细信息
Smart environments with ubiquitous computers are the next generation of information technology, which requires improved human computer interfaces. That is, the computer of the future must be aware of the people in its environment;it must know their identities and must understand their moods. Despite the great effort made in the past decades, the development of a system capable of automatic facial emotion recognition is still rather difficult. In this paper, we challenge the benchmark algorithm on emotion classification of the Extended Cohn-Kanade (CK+) database, and we present a facial component-based system for emotion classification, which beats the given benchmark performance: using a 2D emotional face, we searched for highly discriminative areas, we classified them independently, and we fused all results together to allow for facial emotion recognition. The use of the sparse-representation-basedclassifier allows for the automatic selection of the two most successful blocks and obtains the best results by beating the given benchmark performance by six percentage points. Finally, using the most promising algorithms for facial analysis, we created equivalent facial component-based systems and we made a fair comparison among them.
In recent years, sparserepresentation-based techniques have shown great potential for pattern recognition problems. In this paper, the problem of polarimetric synthetic aperture radar (PolSAR) image classification is...
详细信息
In recent years, sparserepresentation-based techniques have shown great potential for pattern recognition problems. In this paper, the problem of polarimetric synthetic aperture radar (PolSAR) image classification is investigated using sparse representation-based classifiers (SRCs). We propose to take advantage of both polarimetric information and contextual information by combining sparsity-based classification methods with the concept of superpixels. based on polarimetric feature vectors constructed by stacking a variety of polarimetric signatures and a superpixel map, two strategies are considered to perform polarimetric-contextual classification of PolSAR images. The first strategy starts by classifying the PolSAR image with pixel-wise SRC. Then, spatial regularization is imposed on the pixel-wise classification map by using majority voting within superpixels. In the second strategy, the PolSAR image is classified by taking superpixels as processing elements. The joint sparse representation-based classifier (JSRC) is employed to combine the polarimetric information contained in feature vectors and the contextual information provided by superpixels. Experimental results on real PolSAR datasets demonstrate the feasibility of the proposed approaches. It is proven that the classification performance is improved by using contextual information. A comparison with several other approaches also verifies the effectiveness of the proposed approach.
Automatic facial expression recognition has made considerable gains in the body of research available due to its vital role in human-computer interaction. So far, research on this problem or problems alike has propose...
详细信息
Automatic facial expression recognition has made considerable gains in the body of research available due to its vital role in human-computer interaction. So far, research on this problem or problems alike has proposed a wide verity of techniques and algorithms for both information representation and classification. Very recently, Farajzadeh et al. in Int J Pattern Recognit Artif Intell 25(8):1219-1241, (2011) proposed a novel information representation approach that uses machine-learning techniques to derive a set of new informative and descriptive features from the original features. The new features, so called meta probability codes (MPC), have shown a good performance in a wide range of domains. In this paper, we aim to study the performance of the MPC features for the recognition of facial expression via proposing an MPC-based framework. In the proposed framework any feature extractor and classifier can be incorporated using the meta-feature generation mechanism. In the experimental studies, we use four state-of-the-art information representation techniques;local binary pattern, Gabor-wavelet, Zernike moment and facial fiducial point, as the original feature extractors;and four multiclass classifiers, support vector machine, k-nearest neighbor, radial basis function neural network, and sparse representation-based classifier. The results of the extensive experiments conducted on three facial expression datasets, Cohn-Kanade, JAFFE, and TFEID, show that the MPC features promote the performance of facial expression recognition inherently.
暂无评论