CAAI Transactions on Intelligence Technology最新文献

{"title":"Guest Editorial: Special issue on advances in representation learning for computer vision","authors":"Andrew Beng Jin Teoh, Thian Song Ong, Kian Ming Lim, Chin Poo Lee","doi":"10.1049/cit2.12290","DOIUrl":"https://doi.org/10.1049/cit2.12290","url":null,"abstract":"<p>Deep learning has been a catalyst for a transformative revolution in machine learning and computer vision in the past decade. Within these research domains, methods grounded in deep learning have exhibited exceptional performance across a spectrum of tasks. The success of deep learning methods can be attributed to their capability to derive potent representations from data, integral for a myriad of downstream applications. These representations encapsulate the intrinsic structure, features, or latent variables characterising the underlying statistics of visual data. Despite these achievements, the challenge persists in effectively conducting representation learning of visual data with deep models, particularly when confronted with vast and noisy datasets. This special issue is a dedicated platform for researchers worldwide to disseminate their latest, high-quality articles, aiming to enhance readers' comprehension of the principles, limitations, and diverse applications of representation learning in computer vision.</p><p>Wencheng Yang et al. present the first paper in this special issue. The authors thoroughly review feature extraction and learning methods in their work, specifically focusing on cancellable biometrics, a topic not addressed in previous survey articles. While preserving user data privacy, they emphasise the significance of cancellable biometrics in the capacity of feature representation for achieving good recognition accuracy. The paper states that selecting appropriate feature extraction and learning methods relies on individual applications' specific needs and restrictions. Deep learning-based feature learning has significantly improved cancellable biometrics in recent years, while hand-crafted feature extraction has matured. In addition, the research also discusses the problems and potential research areas in this field, providing valuable insights for future studies in cancellable biometrics, which attempts to strike a balance between privacy protection and recognition efficiency.</p><p>The second paper by Mecheter et al. delves into the intricate realm of medical image analysis, specifically focusing on the segmentation of Magnetic Resonance images. The challenge lies in achieving precise segmentation, particularly with incorporating deep learning networks and the scarcity of sufficient medical images. Mecheter et al. tackle this challenge by proposing a novel approach—transfer learning from T1-weighted to T2-weighted MR sequences. Their work aims to enhance bone segmentation while minimising computational resources. The paper introduces an innovative excitation-based convolutional neural network and explores four transfer learning mechanisms. The hybrid transfer learning approach is particularly interesting, addressing overfitting concerns, and preserving features from both modalities with minimal computation time. Evaluating 14 clinical 3D brain MR and CT images demonstrates the superior performance and efficiency of hy","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 1","pages":"1-3"},"PeriodicalIF":5.1,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12290","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139732277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Learning to represent 2D human face with mathematical model","authors":"Liping Zhang,&nbsp;Weijun Li,&nbsp;Linjun Sun,&nbsp;Lina Yu,&nbsp;Xin Ning,&nbsp;Xiaoli Dong","doi":"10.1049/cit2.12284","DOIUrl":"https://doi.org/10.1049/cit2.12284","url":null,"abstract":"<p>How to represent a human face pattern? While it is presented in a continuous way in human visual system, computers often store and process it in a discrete manner with 2D arrays of pixels. The authors attempt to learn a continuous surface representation for face image with explicit function. First, an explicit model (EmFace) for human face representation is proposed in the form of a finite sum of mathematical terms, where each term is an analytic function element. Further, to estimate the unknown parameters of EmFace, a novel neural network, EmNet, is designed with an encoder-decoder structure and trained from massive face images, where the encoder is defined by a deep convolutional neural network and the decoder is an explicit mathematical expression of EmFace. The authors demonstrate that our EmFace represents face image more accurate than the comparison method, with an average mean square error of 0.000888, 0.000936, 0.000953 on LFW, IARPA Janus Benchmark-B, and IJB-C datasets. Visualisation results show that, EmFace has a higher representation performance on faces with various expressions, postures, and other factors. Furthermore, EmFace achieves reasonable performance on several face image processing tasks, including face image restoration, denoising, and transformation.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 1","pages":"54-68"},"PeriodicalIF":5.1,"publicationDate":"2024-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12284","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139732400","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust zero-watermarking algorithm based on discrete wavelet transform and daisy descriptors for encrypted medical image","authors":"Yiyi Yuan,&nbsp;Jingbing Li,&nbsp;Jing Liu,&nbsp;Uzair Aslam Bhatti,&nbsp;Zilong Liu,&nbsp;Yen-wei Chen","doi":"10.1049/cit2.12282","DOIUrl":"https://doi.org/10.1049/cit2.12282","url":null,"abstract":"<p>In the intricate network environment, the secure transmission of medical images faces challenges such as information leakage and malicious tampering, significantly impacting the accuracy of disease diagnoses by medical professionals. To address this problem, the authors propose a robust feature watermarking algorithm for encrypted medical images based on multi-stage discrete wavelet transform (DWT), Daisy descriptor, and discrete cosine transform (DCT). The algorithm initially encrypts the original medical image through DWT-DCT and Logistic mapping. Subsequently, a 3-stage DWT transformation is applied to the encrypted medical image, with the centre point of the LL3 sub-band within its low-frequency component serving as the sampling point. The Daisy descriptor matrix for this point is then computed. Finally, a DCT transformation is performed on the Daisy descriptor matrix, and the low-frequency portion is processed using the perceptual hashing algorithm to generate a 32-bit binary feature vector for the medical image. This scheme utilises cryptographic knowledge and zero-watermarking technique to embed watermarks without modifying medical images and can extract the watermark from test images without the original image, which meets the basic requirements of medical image watermarking. The embedding and extraction of watermarks are accomplished in a mere 0.160 and 0.411s, respectively, with minimal computational overhead. Simulation results demonstrate the robustness of the algorithm against both conventional attacks and geometric attacks, with a notable performance in resisting rotation attacks.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 1","pages":"40-53"},"PeriodicalIF":5.1,"publicationDate":"2024-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12282","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139732407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feature extraction and learning approaches for cancellable biometrics: A survey","authors":"Wencheng Yang,&nbsp;Song Wang,&nbsp;Jiankun Hu,&nbsp;Xiaohui Tao,&nbsp;Yan Li","doi":"10.1049/cit2.12283","DOIUrl":"10.1049/cit2.12283","url":null,"abstract":"<p>Biometric recognition is a widely used technology for user authentication. In the application of this technology, biometric security and recognition accuracy are two important issues that should be considered. In terms of biometric security, cancellable biometrics is an effective technique for protecting biometric data. Regarding recognition accuracy, feature representation plays a significant role in the performance and reliability of cancellable biometric systems. How to design good feature representations for cancellable biometrics is a challenging topic that has attracted a great deal of attention from the computer vision community, especially from researchers of cancellable biometrics. Feature extraction and learning in cancellable biometrics is to find suitable feature representations with a view to achieving satisfactory recognition performance, while the privacy of biometric data is protected. This survey informs the progress, trend and challenges of feature extraction and learning for cancellable biometrics, thus shedding light on the latest developments and future research of this area.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 1","pages":"4-25"},"PeriodicalIF":5.1,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12283","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139606924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Image enhancement with intensity transformation on embedding space","authors":"Hanul Kim,&nbsp;Yeji Jeon,&nbsp;Yeong Jun Koh","doi":"10.1049/cit2.12279","DOIUrl":"10.1049/cit2.12279","url":null,"abstract":"<p>In recent times, an image enhancement approach, which learns the global transformation function using deep neural networks, has gained attention. However, many existing methods based on this approach have a limitation: their transformation functions are too simple to imitate complex colour transformations between low-quality images and manually retouched high-quality images. In order to address this limitation, a simple yet effective approach for image enhancement is proposed. The proposed algorithm based on the channel-wise intensity transformation is designed. However, this transformation is applied to the learnt embedding space instead of specific colour spaces and then return enhanced features to colours. To this end, the authors define the continuous intensity transformation (CIT) to describe the mapping between input and output intensities on the embedding space. Then, the enhancement network is developed, which produces multi-scale feature maps from input images, derives the set of transformation functions, and performs the CIT to obtain enhanced images. Extensive experiments on the MIT-Adobe 5K dataset demonstrate that the authors’ approach improves the performance of conventional intensity transforms on colour space metrics. Specifically, the authors achieved a 3.8% improvement in peak signal-to-noise ratio, a 1.8% improvement in structual similarity index measure, and a 27.5% improvement in learned perceptual image patch similarity. Also, the authors’ algorithm outperforms state-of-the-art alternatives on three image enhancement datasets: MIT-Adobe 5K, Low-Light, and Google HDR+.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 1","pages":"101-115"},"PeriodicalIF":5.1,"publicationDate":"2024-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12279","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139615138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogeneous decentralised machine unlearning with seed model distillation","authors":"Guanhua Ye,&nbsp;Tong Chen,&nbsp;Quoc Viet Hung Nguyen,&nbsp;Hongzhi Yin","doi":"10.1049/cit2.12281","DOIUrl":"10.1049/cit2.12281","url":null,"abstract":"<p>As some recent information security legislation endowed users with unconditional rights to be forgotten by any trained machine learning model, personalised IoT service providers have to put unlearning functionality into their consideration. The most straightforward method to unlearn users' contribution is to retrain the model from the initial state, which is not realistic in high throughput applications with frequent unlearning requests. Though some machine unlearning frameworks have been proposed to speed up the retraining process, they fail to match decentralised learning scenarios. A decentralised unlearning framework called heterogeneous decentralised unlearning framework with seed (HDUS) is designed, which uses distilled seed models to construct erasable ensembles for all clients. Moreover, the framework is compatible with heterogeneous on-device models, representing stronger scalability in real-world applications. Extensive experiments on three real-world datasets show that our HDUS achieves state-of-the-art performance.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 3","pages":"608-619"},"PeriodicalIF":5.1,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12281","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139617533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A topic-controllable keywords-to-text generator with knowledge base network","authors":"Li He,&nbsp;Kaize Shi,&nbsp;Dingxian Wang,&nbsp;Xianzhi Wang,&nbsp;Guandong Xu","doi":"10.1049/cit2.12280","DOIUrl":"10.1049/cit2.12280","url":null,"abstract":"<p>With the introduction of more recent deep learning models such as encoder-decoder, text generation frameworks have gained a lot of popularity. In Natural Language Generation (NLG), controlling the information and style of the output produced is a crucial and challenging task. The purpose of this paper is to develop informative and controllable text using social media language by incorporating topic knowledge into a keyword-to-text framework. A novel Topic-Controllable Key-to-Text (TC-K2T) generator that focuses on the issues of ignoring unordered keywords and utilising subject-controlled information from previous research is presented. TC-K2T is built on the framework of conditional language encoders. In order to guide the model to produce an informative and controllable language, the generator first inputs unordered keywords and uses subjects to simulate prior human knowledge. Using an additional probability term, the model increases the likelihood of topic words appearing in the generated text to bias the overall distribution. The proposed TC-K2T can produce more informative and controllable senescence, outperforming state-of-the-art models, according to empirical research on automatic evaluation metrics and human annotations.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 3","pages":"585-594"},"PeriodicalIF":5.1,"publicationDate":"2024-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12280","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139530560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Extraction of intersecting palm-vein and palmprint features for cancellable identity verification","authors":"Jaekwon Lee,&nbsp;Beom-Seok Oh,&nbsp;Kar-Ann Toh","doi":"10.1049/cit2.12277","DOIUrl":"10.1049/cit2.12277","url":null,"abstract":"<p>A novel method based on the cross-modality intersecting features of the palm-vein and the palmprint is proposed for identity verification. Capitalising on the unique geometrical relationship between the two biometric modalities, the cross-modality intersecting points provides a stable set of features for identity verification. To facilitate flexibility in template changes, a template transformation is proposed. While maintaining non-invertibility, the template transformation allows transformation sizes beyond that offered by the conventional means. Extensive experiments using three public palm databases are conducted to verify the effectiveness the proposed system for identity recognition.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 1","pages":"69-86"},"PeriodicalIF":5.1,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12277","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139625816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep learning fusion model for accurate classification of brain tumours in Magnetic Resonance images","authors":"Nechirvan Asaad Zebari,&nbsp;Chira Nadheef Mohammed,&nbsp;Dilovan Asaad Zebari,&nbsp;Mazin Abed Mohammed,&nbsp;Diyar Qader Zeebaree,&nbsp;Haydar Abdulameer Marhoon,&nbsp;Karrar Hameed Abdulkareem,&nbsp;Seifedine Kadry,&nbsp;Wattana Viriyasitavat,&nbsp;Jan Nedoma,&nbsp;Radek Martinek","doi":"10.1049/cit2.12276","DOIUrl":"10.1049/cit2.12276","url":null,"abstract":"<p>Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 4","pages":"790-804"},"PeriodicalIF":8.4,"publicationDate":"2024-01-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12276","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139536199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Guest Editorial: Special issue on intelligence technology for remote sensing image","authors":"Xiangtao Zheng,&nbsp;Benoit Vozel,&nbsp;Danfeng Hong","doi":"10.1049/cit2.12275","DOIUrl":"https://doi.org/10.1049/cit2.12275","url":null,"abstract":"&lt;p&gt;With the development of artificial intelligence, remote sensing scene interpretation task has attracted extensive attention, which mainly includes scene classification, target detection, hyperspectral classification, and multi-modal analysis. The remote sensing scene interpretation has effectively promoted the development of the Earth observation field. It was the intention for this Special Issue to serve as a platform for the publication of the most recent research concepts from remote sensing image.&lt;/p&gt;&lt;p&gt;To recognise remote sensing scenes, several methods have been proposed to represent the scene image. The first paper (Zhang et al.) proposes a lightweight privacy-preserving recognition framework which diffuses the error between the encryption block and the original block to adjacent blocks which makes the transmission of high-resolution images more secure and efficient. The second paper (Ning et al.) introduces a knowledge distillation network for aerial scene recognition, which produces consistent predictions by distilling the predictive distribution between different scales. With the development of scene recognition task, its branch scene retrieval task also emerges. In this regard, the third paper (Yuan et al.) shows how to efficiently optimise the average accuracy to improve remote sensing image retrieval. This approach enables a more flexible optimisation strategy by involving positive post-samples, which provides a new way to improve the retrieval performance.&lt;/p&gt;&lt;p&gt;To detect targets, a series of advanced methods have been developed to improve detection accuracy and efficiency. The fourth paper (Zhang et al.) proposes an intelligent anchor learning strategy for arbitrary orientation target detection. The fifth paper (Ma et al.) focuses on infrared image detection of small and weak targets and proposes an efficient deep learning method. The sixth paper (Zhou et al.) proposes a convolutional transformer method based on spectral-spatial sequence features for hyperspectral image change detection. With the maturity of target detection techniques, researchers have begun to focus on more complex challenges, namely anomaly detection. In this subfield, the seventh paper (Wang et al.) provides a new solution for semi-supervised hyperspectral anomaly detection. It maps the raw spectrum into the fractional Fourier domain, thereby enhancing the distinguishability between background and anomaly. Meanwhile, the eighth paper (Zhao et al.) utilises a memory-enhanced self-encoder to improve the separation of anomaly samples from background in hyperspectral images. These studies demonstrate the rapid development in the target detection field, such as change detection and anomaly detection.&lt;/p&gt;&lt;p&gt;To classify hyperspectral images, the ninth paper (Liao et al.) shows how to integrate the features of convolutional neural networks and transformers to enhance the performance of hyperspectral image classification. This approach fully utilises the respective a","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"8 4","pages":"1164-1165"},"PeriodicalIF":5.1,"publicationDate":"2023-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12275","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138678873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}