Alaa Thobhani^1,*, Beiji Zou¹, Xiaoyan Kui¹, Amr Abdussalam², Muhammad Asim³, Naveed Ahmed⁴, Mohammed Ali Alshara^4,5

CMC-Computers, Materials & Continua, Vol.81, No.2, pp. 2873-2894, 2024, DOI:10.32604/cmc.2024.054841 - 18 November 2024

Abstract Image captioning has gained increasing attention in recent years. Visual characteristics found in input images play a crucial role in generating high-quality captions. Prior studies have used visual attention mechanisms to dynamically focus on localized regions of the input image, improving the effectiveness of identifying relevant image regions at each step of caption generation. However, providing image captioning models with the capability of selecting the most relevant visual features from the input image and attending to them can significantly improve the utilization of these features. Consequently, this leads to enhanced captioning network performance. In light… More >

Yan Li, Qiyuan Wang^*, Kaidi Jia

CMC-Computers, Materials & Continua, Vol.78, No.2, pp. 2469-2489, 2024, DOI:10.32604/cmc.2024.047822 - 27 February 2024

Abstract Image description task is the intersection of computer vision and natural language processing, and it has important prospects, including helping computers understand images and obtaining information for the visually impaired. This study presents an innovative approach employing deep reinforcement learning to enhance the accuracy of natural language descriptions of images. Our method focuses on refining the reward function in deep reinforcement learning, facilitating the generation of precise descriptions by aligning visual and textual features more closely. Our approach comprises three key architectures. Firstly, it utilizes Residual Network 101 (ResNet-101) and Faster Region-based Convolutional Neural Network… More >

Manal M. Khayyat^1,2, Lamiaa A. Elrefaei^2,3, Mashael M. Khayyat^4,*

CMC-Computers, Materials & Continua, Vol.72, No.1, pp. 2109-2125, 2022, DOI:10.32604/cmc.2022.024975 - 24 February 2022

Abstract Classifying the visual features in images to retrieve a specific image is a significant problem within the computer vision field especially when dealing with historical faded colored images. Thus, there were lots of efforts trying to automate the classification operation and retrieve similar images accurately. To reach this goal, we developed a VGG19 deep convolutional neural network to extract the visual features from the images automatically. Then, the distances among the extracted features vectors are measured and a similarity score is generated using a Siamese deep neural network. The Siamese model built and trained at… More >

Mengmeng Ge¹, Xiangzhan Yu^1,*, Lin Ye^1,2, Jiantao Shi¹

CMC-Computers, Materials & Continua, Vol.71, No.2, pp. 3393-3405, 2022, DOI:10.32604/cmc.2022.017220 - 07 December 2021

Abstract With the rapid development of the Internet, the types of webpages are more abundant than in previous decades. However, it becomes severe that people are facing more and more significant network security risks and enormous losses caused by phishing webpages, which imitate the interface of real webpages and deceive the victims. To better identify and distinguish phishing webpages, a visual feature extraction method and a visual similarity algorithm are proposed. First, the visual feature extraction method improves the Vision-based Page Segmentation (VIPS) algorithm to extract the visual block and calculate its signature by perceptual hash… More >

Qiuyan Wang^{1, *}, Haibing Dong²

Journal on Artificial Intelligence, Vol.1, No.2, pp. 101-110, 2019, DOI:10.32604/jai.2019.08170

Abstract It is the development trend of library information management, which applies the mature and cutting-edge information technology to library information retrieval. In order to realize the rapid retrieval of massive book information, this paper proposes a book retrieval method combining QR code with image retrieval technology. This method analyzes the visual features of book images, design a book image retrieval method based on boundary contour and regional pixel distribution features, and realizes the association retrieval of book information combined with the QR code, so as to improve the efficiency of book retrieval. The experimental results More >

Yanpeng Wu¹, Xiaoqi Peng^1,*, Nur Mohammad²

Journal on Internet of Things, Vol.1, No.2, pp. 63-69, 2019, DOI:10.32604/jiot.2019.06111

Abstract The dosage of gold-antimony flotation process of 5 main drugs, including Copper Sulfate, Lead Nitrate, Yellow Medicine, No. 2 Oil, Black Medicine, with corresponding visual features of foam images, including Stability, Gray Scale, Mean R, Mean G, Mean B, Mean Average, Dimension and Degree Variance, were recorded. Parameter correlation analysis showed that the correlation among Copper Sulfate, Yellow Medicine, Black Medicine, as well as the correlation among Gray Scale, Mean R, Mean G, Mean B, is strong, and the correlation among Dimension, Gray Scale, Mean R, Mean G, Mean B, as well as the correlation More >