International Journal of Pattern Recognition and Artificial Intelligence

Deepfake technology, especially deep voice, which has been derived from artificial intelligence in recent years, is potentially harmful, and the public is not yet wary. However, many speech synthesis models measure the degree of true restitution by Mean Opinion Rating (MOS), a subjective assessment of naturalness and quality of speech by human subjects, but in future it will be difficult to distinguish the interlocutor’s identity through the screen. For this reason, this study addresses the threat posed by this new technology by combining representational learning and 0transfer learning in two sub-systems: a recognition system and a voice print system. The recognition system is responsible for the detection of which voice is a fake voice generated by speech conversion or speech synthesis techniques, while the acoustic system is responsible for the verification of the speaker’s identity through acoustic features. In the speech recognition system, we use the representation learning method and the transfer classification method. We use X-vector data for training, and then fine-tune the model using four types of marker data to learn the representation vectors of real and fake voice, and use support vector machine to classify real and fake voice in the back-end to reduce the negative effect of the new technique.

At present, some achievements have been made in the research of plant leaf classification such as the introduction of artificial intelligence algorithm. But there are still some problems. First, the existing achievements do not consider the subjective perception mechanism and role of human visual system in leaf classification data labels. Second, the implementation of the deep learning algorithm completely depends on the computing power level of the high-cost machine hardware and the large-scale image database. Finally, these research results rarely consider the noise pollution of leaf image samples. In order to solve the above problems, the paper fully considered the subjective perception principle and characteristics of human vision system (HVS), and proposed a lightweight classification method of noisy plant leaves (LCM-NPLs) based on visual domain perception. First, the most suitable HVS front-end perception characteristics were applied to the physical visual processing of leaves. Then the plant leaves were denoised through the information processing mechanism of HVS back-end. The visual effect of regular and orderly plant leaves is obtained. Finally, the classification is realized by principal component analysis (PCA) and third-order nearest neighbor algorithm. The results of ablation contrast experiments show that the classification accuracy of the method in this paper is 82.50% for plant leaves in the presence of serious noise interference with PSNR of 10.2421, more than 90% for plant leaves with general noise pollution transmission with PSNR of more than 15.3759, and 98.33% for plant leaves of light pollution with PSNR of 20.5659. The proposed method has achieved very good results. The proposed method can not only accurately classify plant leaves in different growth periods, but also maintain a high classification accuracy rate in the presence of serious noise interference.

Forgery detection is one of the challenging subjects in computer vision. Forgery is performed using image manipulation with editor tools. Image manipulation tries to change the concept of the image but preserves the integrity of the texture and structure of the image as much as possible. Images are used as evidence in some applications, so if the images are manipulated, they will not be reliable. The copy-move forgery is one of the simplest image manipulation methods. This method removes or inserts information into the image with the least clue by copying a part of the image and pasting it into other places of the same image. Recently, traditional (block-based and keypoint-based) and deep learning methods have been proposed to detect forgery images. Traditional methods include two main steps, feature extraction, and feature matching. Unlike the traditional methods, the deep learning method performs the forgery detection automatically by extracting hierarchical features directly from the data. This paper presents a deep learning method for forgery detection at both image and pixel levels. In this method, we used a pre-trained deep model with a global average pooling (GAP) layer instead of default fully connected layers to detect forgery. The GAP layer creates a good dependency between the feature maps and the classes. In pixel forgery detection, a visualization technique called heatmap activation is used in forgery images. This technique identifies parts of the image that are candidates for forgery. Then, the best candidate is selected and the location of the forgery is determined. The proposed method is performed on the CoMoFod and MICC datasets. The extensive experiments showed the satisfactory performance of the proposed method.

Deep models need a large number of labeled samples to be trained. Furthermore, in practical application settings where objects’ features are added or changed over time, it is difficult and expensive to get enough labeled samples in the beginning. Cognitive learning mechanism can actively raise the deep models’ proficiency online with a few training labels gradually. In this paper, inspired by human being’s cognition procedure to acquire new knowledge stage by stage, we develop a novel deep active recognition framework based on the analysis of models’ cognitive error knowledge to fine-tune the deep models online. The transformation of the cognitive errors is defined, and the corresponding knowledge is obtained to identify the models’ cognitive information. Based on the cognitive knowledge, the sensitive samples are selected to finely tune the models online. To avoid forgetting the previous learned knowledge, the selected prior training samples are used as the refreshening samples at the same time. The experiments demonstrate that the sensitive samples can benefit the target recognition and the cognitive learning mechanism can boost the deep models’ performance efficiently. The characterization of cognitive information can restrain the other samples’ disturbance to the models’ cognition effectively and the online training method can save mass of the time evidently. In conclusion, we introduce this work to provide a trial of thought about the cognitive lifelong learning used in deep learning scenarios.

Extracting information from scanned invoices and other commercial documents, a critical component of corporate function, typically requires significant manual processing. Much research has been conducted in the field of automated information extraction and document processing to alleviate the manual resources used for document analysis, but resultant literature and commercially available products have demonstrated limitations in customizability for identifying specific information. In this paper, we propose a customized machine learning-based pipeline for extracting and tabulating relevant key–value pairs from commercial invoice documents. Specifically, the pipeline combines general document understanding, OCR extraction, and key–value matching with custom rules pertaining to a provided invoice dataset. Then, we demonstrate that the pipeline greatly outperforms a commercially available product and can significantly reduce the amount of manual labor required to process invoice documents. Future work will focus on generalizing the pipeline, so as to apply it on more varied datasets.

This study investigated the three-dimensional (3D) printing of tubular tissue, especially vascular tissue, using a self-developed 3D bioprinter platform and tubular tissue support frame system based on machine vision technology. A 3D printing quality inspection scheme for tubular tissue based on machine vision was proposed by combining the current advanced image acquisition sensor device and theoretical and experimental analysis to measure the printing area in real time. A quantitative relationship between the quality of the tissue profile and the angle and brightness of tissue printed by hydrogel was established by changing the process parameters. A mathematical model for the visual inspection of tissue contour quality was established to realize its visual inspection and evaluation. This method can monitor the quality status of the printing target in real time and provide a basis for improving the accuracy of 3D bioprinting of tubular tissue and shortening the printing time.

Due to the problem of low tracking accuracy and weak tracking stability of current multi-object pedestrian tracking algorithms in complex scenes for videos, a Detection-based Online Multi-Object Pedestrian Tracking (DOMOPT) network is proposed. First, a Multi-Level Feature Fusion (MLFF) pedestrian detection network is proposed based on the Center and Scale Prediction (CSP) algorithm. The pyramid convolutional neural network is used as the backbone to enhance the feature extraction capability for small objects. The shallow features and deep features at multiple levels are integrated to fully obtain the position and semantic information to further improve the detection performance for small objects. Then, on the basis of Joint Detection and Embedding (JDE) architecture, a Multi-Branch Pedestrian Appearance (MBPA) feature extraction network is proposed and added into the pedestrian detection network to extract the appearance feature vector corresponding to each pedestrian. The pedestrian appearance feature extraction is treated as a classification task jointly training with the pedestrian detection task, using the multi-task learning strategy. Experimental results show that the proposed network has better tracking accuracy and stability compared with state-of-the-art algorithms.

The response to a natural disaster ultimately depends on credible and real-time information regarding impacted people and areas. Nowadays, social media platforms such as Twitter have emerged as the primary and fastest means of disseminating information. Due to the massive, imprecise, and redundant information on Twitter, efficient automatic sentiment analysis (SA) plays a crucial role in enhancing disaster response. This paper proposes a novel methodology to efficiently perform SA of Twitter data during a natural disaster. The tweets during a natural calamity are biased toward the negative polarity, producing imbalanced data. The proposed methodology has reduced the misclassification of minority class samples through the adaptive synthetic sampling technique. A binary modified equilibrium optimizer has been used to remove irrelevant and redundant features. The k-nearest neighbor has been used for sentiment classification with the optimized value of k. The nine datasets on natural disasters have been used for evaluation. The performance of the proposed methodology has been validated using the Friedman mean rank test against nine state-of-the-art techniques, including two optimized, one transfer learning, one deep learning, two ensemble learning, and three baseline classifiers. The results show the significance of the proposed methodology through the average improvement of 6.9%, 13.3%, 20.2%, and 18% for accuracy, precision, recall, and F1-score, respectively, as compared to nine state-of-the-art techniques.

Coastal grounding electrodes are currently an important means to alleviate land grounding electrode land constraints. In order to better invert the terrestrial geodesic resistivity in the coastal region, this paper proposes a complete set of inversion technology schemes. First, this paper proposes a layered land model for the coastal region, and a composite geodetic model is modeled by the fold junction of the land model and the ocean. Based on this, an adaptive subdivision boundary element method is proposed for solving the composite soil grounding calculation problem, and the accuracy and advantages of the method are demonstrated by examples. Finally, the paper uses the differential evolutionary algorithm to invert the exploration data of the four-point method in the coastal area, and obtains the parameters of the terrestrial layered geodetic model that meet the engineering requirements. The comparison with the grounding software CDEGS illustrates the effectiveness of the method. This paper carries out the research on the modeling and inversion methods of composite layered soil model, combining advanced numerical calculation methods and artificial intelligence algorithms to provide the support of computational tools for coastal resistivity inversion.

As a meta-heuristic algorithm, the ant colony algorithm has been successfully used to solve various combinatorial optimization problems. However, the existing algorithm that takes the power of ants to solve distributed constraint optimization problems (ACO_DCOP) is easy to fall into local optima. To deal with this issue, this paper presents an adaptive ant colony algorithm based on local information entropy to solve distributed constraint optimization problems, named LIEAD. In LIEAD, the local information entropy is introduced to help agents adaptively select the pheromone update strategy and value selection strategy, which improves the convergence speed and the quality of the solution. Moreover, a restart mechanism is designed to break the accumulation state of pheromone, which increases the population diversity and helps the algorithm jump out of the local optima. The extensive experimental results indicate that LIEAD can significantly outperform ACO_DCOP and is competitive with the state-of-the-art DCOPs algorithms.