Jiajie Mai¹, Xuemiao Xu^2,*, Guorong Xiao³, Zijun Deng², Jiaxing Chen²

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 847-855, 2020, DOI:10.32604/iasc.2020.010119

Abstract The Salient object detection aims to segment out the most visually distinctive objects in an image, which is a challenging task in computer vision. In this paper, we present the PGCA-Net equipped with the pyramid guided channel attention fusion block (PGCAFB) for the saliency detection task. Given an input image, the hierarchical features are extracted using a deep convolutional neural network (DCNN), then starting from the highest-level semantic features, we stage-by-stage restore the spatial saliency details by aggregating the lowerlevel detailed features. Since for the weak discriminative ability of the shallow detailed features, directly introducing them to the semantic features… More >

Eslam Mohammed Abdelkader^1,2,*, Osama Moselhi³, Mohamed Marzouk⁴, Tarek Zayed⁵

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 643-661, 2020, DOI:10.32604/iasc.2020.010100

Abstract Image segmentation is one of the fundamental stages in computer vision applications. Several meta-heuristics have been applied to solve the segmentation problems by extending the Otsu and entropy functions. However, no single-objective function can optimally handle the diversity of information in images besides the multimodality issues of gray-level images. This paper presents a self-adaptive multi-objective optimization-based method for the detection of crack images in reinforced concrete bridges. The proposed method combines the flexibility of information theory functions in addition to the invasive weed optimization algorithm for bi-level thresholding. The capabilities of the proposed method are demonstrated through comparisons with singleobjective… More >

Guangli Zhu, Wenting Liu, Shunxiang Zhang^*, Xiang Chen , Chang Yin

Computer Systems Science and Engineering, Vol.35, No.3, pp. 223-232, 2020, DOI:10.32604/csse.2020.35.223

Abstract The current method of extracting new login sentiment words not only ignores the diversity of patterns constituted by new multi-character words (the number of words is greater than two), but also disregards the influence of other new words co-occurring with a new word connoting sentiment. To solve this problem, this paper proposes a method for extracting new login sentiment words from Chinese micro-blog based on improved mutual information. First, micro-blog data are preprocessed, taking into consideration some nonsense signals such as web links and punctuation. Based on preprocessed data, the candidate strings are obtained by applying the N-gram segmentation method.… More >

Thamotharan B^1,*, Venkatraman B², Chandrasekaran S³

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 335-340, 2020, DOI:10.31209/2019.100000156

Abstract Accumulation of impurities within cold trap device results in degradation of efficient performance in a nuclear reactor systems. The impurities have to be identified and the device has to be replaced periodically based on the accumulation level. Though there are a few techniques available to identify these impurities from the cold trap device, there are certain limitations in these techniques. In order to overcome these constraints, a new harmless and easy approach for identifying and separating the impurities using the radiographic images of cold traps is proposed in this paper. It includes a new segmentation algorithm to segregate the deposited… More >

R.V.V. Krishna^1,*, S. Srinivas Kumar²

Intelligent Automation & Soft Computing, Vol.26, No.2, pp. 281-290, 2020, DOI:10.31209/2019.100000121

Abstract In this paper, a color image segmentation algorithm is proposed by extracting both texture and color features and applying them to the one -against-all multi class support vector machine (MSVM) classifier for segmentation. Local Binary Pattern is used for extracting the textural features and L*a*b color model is used for obtaining the color features. The MSVM is trained using the samples obtained from a novel soft rough fuzzy c-means (SRFCM) clustering. The fuzzy set based membership functions capably handle the problem of overlapping clusters. The lower and upper approximation concepts of rough sets deal well with uncertainty, vagueness, and incompleteness… More >

Yong Luo¹, Xiaojie Li², Chao Luo², Feng Wang¹, Xi Wu², Imran Mumtaz³, Cheng Yi^{1, *}

CMC-Computers, Materials & Continua, Vol.65, No.2, pp. 1771-1780, 2020, DOI:10.32604/cmc.2020.010069

Abstract Tissue segmentation is a fundamental and important task in nasopharyngeal images analysis. However, it is a challenging task to accurately and quickly segment various tissues in the nasopharynx region due to the small difference in gray value between tissues in the nasopharyngeal image and the complexity of the tissue structure. In this paper, we propose a novel tissue segmentation approach based on a two-stage learning framework and U-Net. In the proposed methodology, the network consists of two segmentation modules. The first module performs rough segmentation and the second module performs accurate segmentation. Considering the training time and the limitation of… More >

Li-Hong Juang^a, Ming-Ni Wu^b, Feng-Mao Tsou^b

Intelligent Automation & Soft Computing, Vol.24, No.4, pp. 739-745, 2018, DOI:10.1080/10798587.2017.1327549

Abstract Kinect(+openCV); Dynamic portrait segmentation; Skeletal tracking; Edge transparent processing; Video interactive More >

N. Mohanapriya¹, Dr. B. Kalaavathi²

Intelligent Automation & Soft Computing, Vol.25, No.4, pp. 663-672, 2019, DOI:10.31209/2018.100000041

Abstract Medical images are obtained straight from the medical acquisition devices so that, the image quality becomes poor and may contain noises. Low contrast and poor quality are the major issues in the production of medical images. Medical imaging enhancement technology gives way to solve these issues; it helps the doctors to see the interior portions of the body for early diagnosis, also it improves the features the visual aspects of an image for a right diagnosis. This paper proposes a new blend of Particle Swarm Optimization (PSO) and Accelerated Particle Swarm Optimization (APSO) called Hybrid Partial Swarm Optimization (HPSO) to… More >

Fatma Mallouli

Intelligent Automation & Soft Computing, Vol.25, No.2, pp. 243-248, 2019, DOI:10.31209/2019.100000069

Abstract Density estimation via Gaussian mixture modelling has been successfully applied to image segmentation. In this paper, we have learned distributions mixture model to the pixel of an iris image as training data. We introduce the proposed algorithm by adapting the Expectation-Maximization (EM) algorithm. To further improve the accuracy for iris segmentation, we consider the EM algorithm in Markovian and non Markovian cases. Simulated data proves the accuracy of our algorithm. The proposed method is tested on a subset of the CASIA database by Chinese Academy of Sciences Institute of Automation-IrisTwins. The obtained results have shown a significant improvement of our… More >

Xu Han^{1, #}, Huijun Yang^{1, 4, *}, Qiufeng Shen^{1, #}, Jiangtao Yang², Huihui Liang¹, Cancan Bao¹, Shuang Cang³

CMC-Computers, Materials & Continua, Vol.65, No.1, pp. 579-596, 2020, DOI:10.32604/cmc.2020.011262

Abstract Although predecessors have made great contributions to the semantic segmentation of 3D indoor scenes, there still exist some challenges in the debris recognition of terrain data. Compared with hundreds of thousands of indoor point clouds, the amount of terrain point cloud is up to millions. Apart from that, terrain point cloud data obtained from remote sensing is measured in meters, but the indoor scene is measured in centimeters. In this case, the terrain debris obtained from remote sensing mapping only have dozens of points, which means that sufficient training information cannot be obtained only through the convolution of points. In… More >