Haifeng Song¹, Weiwei Yang^1,*, Haiyan Yuan², Harold Bufford³

Intelligent Automation & Soft Computing, Vol.26, No.6, pp. 1441-1458, 2020, DOI:10.32604/iasc.2020.011988 - 24 December 2020

Abstract There are two main problems that lead to unsatisfactory classification performance for hyperspectral remote sensing images (HSIs). One issue is that the HSI data used for training in deep learning is insufficient, therefore a deeper network is unfavorable for spatial-spectral feature extraction. The other problem is that as the depth of a deep neural network increases, the network becomes more prone to overfitting. To address these problems, a dual-channel 3D-Multiscale DenseNet (3DMSS) is proposed to boost the discriminative capability for HSI classification. The proposed model has several distinct advantages. First, the model consists of dual… More >

Xiangchun Liu¹, Jing Yu²,Wei Song^{1, 3, *}, Xinping Zhang¹, Lizhi Zhao¹, Antai Wang⁴

CMC-Computers, Materials & Continua, Vol.65, No.2, pp. 1385-1395, 2020, DOI:10.32604/cmc.2020.011308 - 20 August 2020

Abstract With the development of satellite technology, the satellite imagery of the earth’s surface and the whole surface makes it possible to survey surface resources and master the dynamic changes of the earth with high efficiency and low consumption. As an important tool for satellite remote sensing image processing, remote sensing image classification has become a hot topic. According to the natural texture characteristics of remote sensing images, this paper combines different texture features with the Extreme Learning Machine, and proposes a new remote sensing image classification algorithm. The experimental tests are carried out through the More >

Mohammad Behrouzian Nejad¹, Mohammad Ebrahim Shiri^1,2,*

Computer Systems Science and Engineering, Vol.34, No.2, pp. 91-100, 2019, DOI:10.32604/csse.2019.34.091

Abstract In this paper we propose a new image classification technique. According to this note that most research focuses on extraction of features in the frequency domain, location, and reduction of feature dimensions, in this research we focused on learning step in image classification. The main aim is to use the heuristic methods to increase the function of the estimator of the learning algorithm and continue to achieve the desired state, as well as categorization without user interference and automatically performed by the model produced from the above steps. So, in this paper, a new learning… More >

Lu Wu, Quan Liu, Ping Lou

Intelligent Automation & Soft Computing, Vol.25, No.2, pp. 249-257, 2019, DOI:10.31209/2018.100000010

Abstract The scheme of spatial pyramid matching (SPM) causes feature ambiguity near dividing lines because it divides an image into different scales in a fixed manner. A new method called soft SPM (sSPM) is proposed in this paper to reduce feature ambiguity. First, an auxiliary area rotating around a dividing line in four orientations is used to correlate the feature relativity. Second, sSPM is performed to combine these four orientations to describe the image. Finally, an optimized multiple kernel learning (MKL) algorithm with three basic kernels for the support vector machine is applied. Specifically, for each More >

Mohammad Behrouzian Nejad¹, Mohammad Ebrahim Shiri Ahmadabadi^{1, 2, *}

CMES-Computer Modeling in Engineering & Sciences, Vol.119, No.1, pp. 185-205, 2019, DOI:10.32604/cmes.2019.01838

Abstract The main target of this paper is presentation of an efficient method for MRI images classification so that it can be used to diagnose patients and non-patients. Image classification is one of the prominent subset topics of machine learning and data mining that the most important image technique is the auto-categorization of images. MRI images with high resolution and appropriate accuracy allow physicians to decide on the diagnosis of various diseases and treat them. The auto categorization of MRI images toward diagnosing brain diseases has been being used to accurately diagnose hospitals, clinics, physicians and… More >

Hao Wu¹, Qi Liu^{2, 3, *}, Xiaodong Liu⁴

CMC-Computers, Materials & Continua, Vol.60, No.2, pp. 575-597, 2019, DOI:10.32604/cmc.2019.03595

Abstract Deep learning technology has brought great impetus to artificial intelligence, especially in the fields of image processing, pattern and object recognition in recent years. Present proposed artificial neural networks and optimization skills have effectively achieved large-scale deep learnt neural networks showing better performance with deeper depth and wider width of networks. With the efforts in the present deep learning approaches, factors, e.g., network structures, training methods and training data sets are playing critical roles in improving the performance of networks. In this paper, deep learning models in recent years are summarized and compared with detailed More >

Yang Yang^1,*, Jinbao Duan¹, Haitao Yu¹, Zhipeng Gao¹, Xuesong Qiu¹

CMES-Computer Modeling in Engineering & Sciences, Vol.117, No.3, pp. 555-575, 2018, DOI:10.31614/cmes.2018.04249

Abstract The development of deep learning has revolutionized image recognition technology. How to design faster and more accurate image classification algorithms has become our research interests. In this paper, we propose a new algorithm called stochastic depth networks with deep energy model (SADIE), and the model improves stochastic depth neural network with deep energy model to provide attributes of images and analysis their characteristics. First, the Bernoulli distribution probability is used to select the current layer of the neural network to prevent gradient dispersion during training. Then in the backpropagation process, the energy function is designed More >

Qidi Wu¹, Yibing Li¹, Yun Lin^1,*, Ruolin Zhou²

CMC-Computers, Materials & Continua, Vol.56, No.1, pp. 91-105, 2018, DOI:10.3970/cmc.2018.02771

Abstract The conventional sparse representation-based image classification usually codes the samples independently, which will ignore the correlation information existed in the data. Hence, if we can explore the correlation information hidden in the data, the classification result will be improved significantly. To this end, in this paper, a novel weighted supervised spare coding method is proposed to address the image classification problem. The proposed method firstly explores the structural information sufficiently hidden in the data based on the low rank representation. And then, it introduced the extracted structural information to a novel weighted sparse representation model More >