Yue Zhao¹, Jianjian Yue¹, Wei Song^1,*, Xiaona Xu¹, Xiali Li¹, Licheng Wu¹, Qiang Ji²

Journal on Internet of Things, Vol.1, No.1, pp. 17-23, 2019, DOI:10.32604/jiot.2019.05866

Abstract We proposed a method using latent regression Bayesian network (LRBN) to extract the shared speech feature for the input of end-to-end speech recognition model. The structure of LRBN is compact and its parameter learning is fast. Compared with Convolutional Neural Network, it has a simpler and understood structure and less parameters to learn. Experimental results show that the advantage of hybrid LRBN/Bidirectional Long Short-Term Memory-Connectionist Temporal Classification architecture for Tibetan multi-dialect speech recognition, and demonstrate the LRBN is helpful to differentiate among multiple language speech sets. More >

Zhizheng Zhang¹, Jing Feng^1,*, Jun Yan², Xiaolei Wang¹, Xiaocun Shu¹

Journal of New Media, Vol.1, No.1, pp. 1-9, 2019, DOI:10.32604/jnm.2019.05937

Abstract Clouds play an important role in modulating radiation processes and climate changes in the Earth's atmosphere. Currently, measurement of meteorological elements such as temperature, air pressure, humidity, and wind has been automated. However, the cloud's automatic identification technology is still not perfect. Thus, this paper presents an approach that extracts dense scale-invariant feature transform (Dense_SIFT) as the local features of four typical cloud images. The extracted cloud features are then clustered by K-means algorithm, and the bag-of-words (BoW) model is used to describe each ground-based cloud image. Finally, support vector machine (SVM) is used for classification and recognition. Based on… More >

Junhao Yang¹, Chunxiao Chen^1,*, Qingyang Zang¹, Jianfei Li¹

Molecular & Cellular Biomechanics, Vol.15, No.4, pp. 203-214, 2018, DOI:10.32604/mcb.2018.03824

Abstract Pathological slide is increasingly applied in the diagnosis of breast tumors despite the issues of large amount of data, slow viewing and high subjectivity. To overcome these problems, a micrograph recognition method based on convolutional neural network is proposed for pathological slide of breast tumor. Combined with multi-channel threshold and watershed segmentation, a sample database including single cell, adhesive cell and invalid cell was established. Then, the convolution neural network with six layers is constructed, which has ability to classify the stained breast tumor cells with accuracy of more than 90%, and evaluate the proliferation level with relative error of… More >

Wei Sun^1,3,*, Hongji Du¹, Shoubai Nie^2,3, Xiaozheng He⁴

CMC-Computers, Materials & Continua, Vol.60, No.1, pp. 147-161, 2019, DOI:10.32604/cmc.2019.03581

Abstract Traffic sign recognition (TSR), as a critical task to automated driving and driver assistance systems, is challenging due to the color fading, motion blur, and occlusion. Traditional methods based on convolutional neural network (CNN) only use an end-layer feature as the input to TSR that requires massive data for network training. The computation-intensive network training process results in an inaccurate or delayed classification. Thereby, the current state-of-the-art methods have limited applications. This paper proposes a new TSR method integrating multi-layer feature and kernel extreme learning machine (ELM) classifier. The proposed method applies CNN to extract the multi-layer features of traffic… More >

Lili Pan¹, Jiaohua Qin^1,*, Hao Chen², Xuyu Xiang¹, Cong Li¹, Ran Chen¹

CMC-Computers, Materials & Continua, Vol.59, No.1, pp. 297-313, 2019, DOI:10.32604/cmc.2019.04097

Abstract Image retrieval for food ingredients is important work, tremendously tiring, uninteresting, and expensive. Computer vision systems have extraordinary advancements in image retrieval with CNNs skills. But it is not feasible for small-size food datasets using convolutional neural networks directly. In this study, a novel image retrieval approach is presented for small and medium-scale food datasets, which both augments images utilizing image transformation techniques to enlarge the size of datasets, and promotes the average accuracy of food recognition with state-of-the-art deep learning technologies. First, typical image transformation techniques are used to augment food images. Then transfer learning technology based on deep… More >

Chunlong Hu^1,*, Jianjun Chen¹, Xin Zuo¹, Haitao Zou¹, Xing Deng¹, Yucheng Shu²

CMES-Computer Modeling in Engineering & Sciences, Vol.118, No.3, pp. 547-559, 2019, DOI:10.31614/cmes.2019.04032

Abstract Micro-expression recognition has attracted growing research interests in the field of compute vision. However, micro-expression usually lasts a few seconds, thus it is difficult to detect. This paper presents a new framework to recognize micro-expression using pyramid histogram of Centralized Gabor Binary Pattern from Three Orthogonal Panels (CGBP-TOP) which is an extension of Local Gabor Binary Pattern from Three Orthogonal Panels feature. CGBP-TOP performs spatial and temporal analysis to capture the local facial characteristics of micro-expression image sequences. In order to keep more local information of the face, CGBP-TOP is extracted based on pyramid sub-regions of the micro-expression video frame.… More >

Munish Kumar¹, Simpel Rani Jindal²

CMES-Computer Modeling in Engineering & Sciences, Vol.113, No.2, pp. 195-202, 2017, DOI:10.3970/cmes.2017.113.201

Abstract Grading of writers in perspective of their handwriting is a challenging task owing to various writing styles of different individuals. This paper presents a framework for grading of Devanagari writers in perspective of their handwriting. This framework of grading can be useful in conducting the handwriting competitions and then deciding the winners on the basis of an automated process. Selecting the set of features is a challenging task for implementing a handwriting grading system of particular language. In this paper, curvature features, namely, parabola curve fitting and power curve fitting have been considered for extracting the vital information of writers,… More >

Liming Yang¹, Yongping Gao², Qun Sun³

CMES-Computer Modeling in Engineering & Sciences, Vol.104, No.6, pp. 493-506, 2015, DOI:10.3970/cmes.2015.104.493

Abstract Minimax probability machine (MPM) has been recently proposed and shown its advantage in pattern recognition. In this paper, we present a new minimax probabilistic approach (MPA),which can provide an explicit lower bound on prediction accuracy. Applying the Chebyshev-Cantelli inequality, the MPA is posed as a second order cone program formulation and solved effectively. Following that, this method is exploited directly to recognize the purity of hybrid seeds using near-infrared spectroscopic data. Experimental results in different spectral regions show that the proposed MPA is competitive with the existing minimax probability machine and support vector machine in generalization, while requires less computational… More >

Jia Dongyao^1,2, Zhu Huaihua¹, Ai Yanke¹, Zou Shengxiong¹

CMES-Computer Modeling in Engineering & Sciences, Vol.103, No.6, pp. 411-427, 2014, DOI:10.3970/cmes.2014.103.411

Abstract The existing study on the image segmentation methods based on the image of vehicle lights is insufficient both at home and abroad, and its segmentation efficiency and accuracy is low as well. On the basis of the analysis of the regional characteristics of vehicle lights and a level set model, an image segmentation method for complex vehicle lights based on adaptive significance level set contour model is proposed in this paper. Adaptive positioning algorithm of the significant initial contour curve based on two-dimensional convex hull is designed to obtain the initial position of evolution curve, thus the adaptive ability of… More >

Maria João M. Vasconcelos¹, João Manuel R. S. Tavares¹

CMES-Computer Modeling in Engineering & Sciences, Vol.36, No.3, pp. 213-242, 2008, DOI:10.3970/cmes.2008.036.213

Abstract In this work we developed methods to automatically extract significant points of objects like hand palms and faces represented in images that can be used to build Point Distribution Models automatically. These models are further used to segment the modelled objects in new images, through the use of Active Shape Models or Active Appearance Models. These models showed to be efficient in the segmentation of objects, but had as drawback the fact that the labelling of the landmark points was usually manually made and consequently time consuming. Thus, in this paper we describe some methods capable to extract significant points… More >