Image Recognition Performance Research Articles

AdvU-Net: Generating Adversarial Example Based on Medical Image and Targeting U-Net Model

Deep neural networks (DNNs) provide excellent performance in image recognition, speech recognition, video recognition, and pattern analysis. These neural networks are often applied in the medical field to predict or classify patients’ illnesses. One such network, the U-Net model, has shown good performance in data segmentation and is an important technology in medical imaging. However, deep neural networks such as those applied in medicine are vulnerable to attack by adversarial examples. Adversarial examples are samples created by adding a small amount of noise to an original data sample that is difficult for a human to see but that induces misclassification by the targeted model. In this paper, we propose AdvU-Net, a method for generating an adversarial example targeting the U-Net model used in segmentation. Performance was analyzed according to epsilon, using the fast gradient sign method (FGSM) for generating adversarial examples. We used ISBI 2012 as the dataset and TensorFlow as the machine learning library. In the experiment, when an adversarial example was generated using an epsilon value of 0.3, the pixel error was 3.54 or greater while the pixel error of the original sample was maintained at 0.15 or less.

Classification of Fetal Heart Based on Images Augmentation Using Convolutional Neural Network Method

Standard fetal heart echocardiography view consists of several specific views that can be prolific to optimize the visualization of various structures and anomalies including three vessel and trachea view, right ventricular outflow tract view, four chamber view, left ventricular outflow tract, and right ventricular outflow tract. With the use of current technological developments specifically deep learning, it can classify images from the visualization of the echocardiography point of view obtained. One of the deep learning models that has the best performance in image recognition and classification is the Convolutional Neural Network. Research consists of several stages, namely data collection, data pre-processing, data augmentation, data sharing designing the Convolutional Neural Network model architecture, training, testing, and results. 5 types of echocardiography videos were used based on the echocardiography point of view, resulting in 3,995 images consisting of 3,196 training data and 799 test data. The implementation of convolutional neural networks for the classification of fetal echocardiography images based on point of view obtained good results. The Convolutional Neural Network used consists of 2 convolution layers, 2 layers, 1 flatten layer, 2 dense layers, and 2 Dropout layers. The accuracy rate obtained from the CNN model with a learning rate value of 0.01 and the number of epochs of 50 gets an accuracy value of 98%.

Embedding metric learning into an extreme learning machine for scene recognition

Metric learning can be very useful to improve the performance of a distance-dependent classifier. However, separating metric learning from the classifier learning possibly degenerates the performance, for instance in scene recognition, especially for some complicated scene images. To address this issue, we propose to embed metric learning into an extreme learning machine (EML-ELM) to tackle scene recognition. Specifically, metric learning is conducted to fully explore discriminative features by taking into account all label information, rendering samples of the same class more compact and those of different classes more separable. An extreme learning machine is employed as a classifier thanks to its effectiveness and fast learning process. By explicitly embedding metric learning into an extreme learning machine, we can jointly learn the discriminative features and an effective classifier in a unified framework, thereby improving the recognition performance for complicated scene images. Extensive experiments on four benchmark scene datasets demonstrate the competitive performance of EML-ELM in comparison with state-of-the-art methods.

Analysis and Evaluation Research on the Construction of the Music Art Management Curriculum System Based on the Deep Learning Model

In view of the fact that music courses are seldom offered in schools and lack of management, there are many problems in the management system of music and art. In order to improve the learning effect of students in music courses, this paper proposes to build a music art management curriculum system based on the in-depth learning model. This paper puts forward the requirements of in-depth learning in music and art curriculum indicators and puts forward the model framework of music and art learning. Through the combined application of music courses, first of all, the current music course model is compared with Ghostnet music course, Mobilenet music course, and traditional music course to verify that the current music course model has certain advantages in accuracy, precision, recall, and image recognition performance. This proves that the current music curriculum is more suitable for the construction of this model. Secondly, the proposed model has a high score through the comprehensive application of several indicators in the course. Finally, under the model constructed by deep learning, the opening of music courses in schools has also increased significantly and improves the interest point and the application of people on the music art course so as to achieve the final application effect.

SAR-BagNet: An Ante-hoc Interpretable Recognition Model Based on Deep Network for SAR Image

Convolutional neural networks (CNNs) have been widely used in SAR image recognition and have achieved high recognition accuracy on some public datasets. However, due to the opacity of the decision-making mechanism, the reliability and credibility of CNNs are insufficient at present, which hinders their application in some important fields such as SAR image recognition. In recent years, various interpretable network structures have been proposed to discern the relationship between a CNN’s decision and image regions. Unfortunately, most interpretable networks are based on optical images, which have poor recognition performance for SAR images, and most of them cannot accurately explain the relationship between image parts and classification decisions. Based on the above problems, in this study, we present SAR-BagNet, which is a novel interpretable recognition framework for SAR images. SAR-BagNet can provide a clear heatmap that can accurately reflect the impact of each part of a SAR image on the final network decision. Except for the good interpretability, SAR-BagNet also has high recognition accuracy and can achieve 98.25% test accuracy.

Textual Adversarial Training of Machine Learning Model for Resistance to Adversarial Examples

Deep neural networks provide good performance for image recognition, speech recognition, text recognition, and pattern recognition. However, such networks are vulnerable to attack by adversarial examples. Adversarial examples are created by adding a small amount of noise to an original sample in such a way that no problem is perceptible to humans, yet the sample will be incorrectly recognized by a model. Adversarial examples have been studied mainly in the context of images, but research has expanded to include the text domain. In the textual context, an adversarial example is a sample of text in which certain important words have been changed so that the sample will be misclassified by a model even though to humans it is the same as the original text in terms of meaning and grammar. In the text domain, there have been relatively few studies on defenses against adversarial examples compared with the number of studies on adversarial example attacks. In this paper, we propose an adversarial training method to defend against adversarial examples that target the latest text model, bidirectional encoder representations from transformers (BERT). In the proposed method, adversarial examples are generated using various parameters and then are applied in additional training of the target model to instill robustness against unknown adversarial examples. Experiments were conducted using five datasets (AG’s News, a movie review dataset, the IMDB Large Movie Review Dataset (IMDB), the Stanford Natural Language Inference (SNLI) corpus, and the Multi-Genre Natural Language Inference (MultiNLI) corpus), with TensorFlow as the machine learning library. According to the experimental results, the baseline model had an accuracy of 88.1% on the original sentences and an accuracy of 9.2% on the adversarial sentences, whereas the model that underwent the proposed training method maintained an average accuracy of 87.2% on the original sentences and had an average accuracy of 22.5% on the adversarial sentences.

Unsupervised domain adaptation based on adaptive local manifold learning

Transfer learning is known to an effective method dealing with domain shift. When the same task is shared in different domains, it is usually called domain adaptation. The problem of distribution difference is inevitable in domain adaption works. The subspace method can transform the data into a new feature representation, which is helpful to reduce the distribution differences. At present, many researchers have made extensive exploration on subspace learning in domain adaptation works. The weakness of many existed domain adaptation methods based on subspace learning either ignores the local manifold information or has the problem of parameter selection in local manifold regularization term which may limit the effectiveness of cross - domain image classification. Therefore, a novel transfer learning method termed unsupervised domain adaptation based on adaptive local manifold learning (UDA-ALML) is proposed in this paper, which is mainly utilized to cross-domain image classification. For the sake of preserving the structure information of original data, the proposed method combines sparse representation, manifold learning and low rank representation to learn the transformation matrix. To be specific, the weight matrix in traditional local manifold regularization term is replaced by the reconstruction coefficient matrix. Large quantities of experiments show that it has a remarkable performance in cross-domain image recognition.

Batik Classification Using Convolutional Neural Network with Data Improvements

Batik is one of the Indonesian cultures that UNESCO has recognized. Batik has a variety of unique and distinctive patterns that reflect the area of origin of the batik motif. Batik motifs usually have a 'core motif' printed repeatedly on the fabric. The entry of digitization makes batik motif designs more diverse and unique. However, with so many batik motifs spread on the internet, it is difficult for ordinary people to recognize the types of batik motifs. This makes an automatic classification of batik motifs must continue to be developed. Automation of batik motif classification can be assisted with artificial intelligence. Machine learning and deep learning have produced much good performance in image recognition. In this study, we use deep learning based on a Convolutional Neural Network (CNN) to automate the classification of batik motifs. There are two datasets used in this study. The old dataset comes from a public repository with 598 data with five types of motifs. Meanwhile, the new dataset updates the old dataset by replacing the anomalous data in the old dataset with 621 data with five types of motifs. The lereng motif is changed to pisanbali due to the difficulty of obtaining the lereng motif. Each dataset was divided into three ways: original, balance patch, and patch. We used ResNet-18 architecture, which used a pre-trained model to shorten the training time. The best test results were obtained in the new dataset with the patch way of 88.88 % ±0.88, and in the old dataset, the best accuracy was found in the patch way on the test data of 66.14 % ±3.7. The data augmentation in this study did not significantly affect the accuracy because the most significant increase in accuracy is only up to 1.22%.

Convolutional Locality-Sensitive Dictionary Learning for Facial Expressions Detection

Facial Expression (FE) detection is a popular research area, particularly in the field of Image Classification, Pattern Recognition and Computer Vision. Sparse Representation (SR) and Dictionary Learning (DL) have significantly enhanced the classification performance of image recognition and also resolved the problem of the nonlinear distribution of face images and its implementation with DL. However, the locality structure of face image data containing more discriminative information, which is very critical for classification has not been fully explored by state-of-the-art existing SR-based approaches. Furthermore, similar coding results between test samples and neighboring training data, contained in the feature space are not being fully realized from the image features with similar image categorizations, to effectively capture the embedded discriminative information. In an attempt to resolve the forgoing issues, we propose a novel DL method, Convolutional locality-sensitive Dictionary Learning (CLSDL) for Facial Expression detection.

Ensemble transfer attack targeting text classification systems

Deep neural networks provide good performance for image recognition, speech recognition, text recognition, and pattern recognition. However, such networks are vulnerable to attack by adversarial examples. Adversarial examples are created by adding a small amount of noise to an original sample in such a way that no problem is perceptible to humans yet the sample will be incorrectly classified by a classification model. Adversarial examples have been studied mainly in the context of images, but research has expanded to include the text domain. In the textual context, an adversarial example is a sample of text in which certain important words have been changed so that the sample will be misclassified by a model even though to humans it is the same as the original text in terms of meaning and grammar. However, studies of black box attacks using text adversarial examples are sparse. In this paper, we propose the ensemble transfer textfooler method. This method performs a black box attack on an unknown model after generating an ensemble adversarial example that simultaneously deceives several models. Experiments were conducted using a movie review dataset and with TensorFlow as the machine learning library. The experimental results show that the proposed method has an attack success rate of 71.64%, in contrast to the 19.01%, 24.29%, and 44.96% attack success rate for the conventional transfer attacks using an adversarial example generated to deceive a WordCNN, WordLSTM, and BERT model.

Discrimination of Types of Seizure Using Brain Rhythms Based on Markov Transition Field and Deep Learning

Discrimination of types of seizure using the Electroencephalogram (EEG) signal has always been a challenging task due to minuscule differences among different types of seizures. In this regard, deep learning (DL) which has already evidenced notable performance in image recognition could be suitable. However, a few attempts have been made so far in this regard mainly by constructing 2D input images for DL from 1D EEG signals directly using various techniques. Besides, the quality of the generated images has not been verified. Therefore, in this work, 2D images for the DL pipeline have been generated from brain rhythms, which already displayed remarkable performance in analyzing various brain activities. For this purpose, the Markov transition field transformation technique has been employed for 2D image construction by preserving statistical dynamics characteristics of EEG signals, which are very important during the discrimination of different types of seizures. And, a convolution neural network (CNN) has been used for classification. Further, the quality of the 2D image along with appropriate brain rhythms have also been investigated. For experimental validation, EEG recordings of six different types of seizure that are provided by the Temple University EEG dataset (TUH v1.5.2) has been taken into account. The proposed method has achieved the highest classification accuracy and weighted F1-score up to 91.1% and 91.0% respectively. Further analysis shows that higher image resolution can provide the best classification accuracy. In addition, the d rhythm has been found the most suitable in seizure type classification. In a comparative study, the proposed idea demonstrated its superiority by displaying the uppermost classification performance.

SST: Spatial and Semantic Transformers for Multi-Label Image Recognition.

Multi-label image recognition has attracted considerable research attention and achieved great success in recent years. Capturing label correlations is an effective manner to advance the performance of multi-label image recognition. Two types of label correlations were principally studied, i.e., the spatial and semantic correlations. However, in the literature, previous methods considered only either of them. In this work, inspired by the great success of Transformer, we propose a plug-and-play module, named the Spatial and Semantic Transformers (SST), to simultaneously capture spatial and semantic correlations in multi-label images. Our proposal is mainly comprised of two independent transformers, aiming to capture the spatial and semantic correlations respectively. Specifically, our Spatial Transformer is designed to model the correlations between features from different spatial positions, while the Semantic Transformer is leveraged to capture the co-existence of labels without manually defined rules. Other than methodological contributions, we also prove that spatial and semantic correlations complement each other and deserve to be leveraged simultaneously in multi-label image recognition. Benefitting from the Transformer's ability to capture long-range correlations, our method remarkably outperforms state-of-the-art methods on four popular multi-label benchmark datasets. In addition, extensive ablation studies and visualizations are provided to validate the essential components of our method.

Image Analysis by Fractional-Order Gaussian-Hermite Moments.

Moments and moment invariants are effective feature descriptors. They have widespread applications in the field of image processing. The recent researches show that fractional-order moments have notable image representation ability. Hermite polynomials are defined over the interval from negative infinity to positive one. Such unboundedness prevents us from developing fractional-order Gaussian-Hermite moments via the existing ideas or approaches. In this paper, we propose fractional-order Gaussian-Hermite moments by forcing the definition domain of Hermite polynomials to be a bounded interval, meanwhile, resorting to a value-decreasing standard deviation to maintain the orthogonality. Moreover, we successfully develop contrast, translation and rotation invariants from the proposed moments based on the inherent properties of Hermite polynomials. The reconstructions of different types of images demonstrate that the proposed moments have more superior image representation ability to the most existing popular orthogonal moments. Besides, the salient performance in invariant image recognition, noise robustness and region-of-interest feature extraction reflect that these moments and their invariants possess the stronger discrimination power and the better noise robustness in comparison with the existing orthogonal moments. Furthermore, both complexity analysis and time consumption indicate that the proposed moments and their invariants are easy to implement, they are suitable for practical engineering applications.

SMART: Semantic-Aware Masked Attention Relational Transformer for Multi-label Image Recognition

As objects usually co-exist in an image, learning the label co-occurrence is a compelling approach to improving the performance of multi-label image recognition. However, the dependencies among the non-exist categories in an image cannot be effectively evaluated. These redundant label dependencies may bring noise and further decrease the performance of classification. Therefore, we proposed SMART, a Semantic-aware Masked Attention Relational Transformer for Multi-label Image Recognition for multi-label image recognition tasks. In addition to leveraging Transformer to model the inter-class dependencies, the proposed masked attention filters out the redundant dependencies among the non-exist categories. SMART is able to explicitly and accurately capture the label dependencies without extra word embeddings. Moreover, our method achieves new state-of-the-art results on two benchmarks for multi-label image recognition: MS-COCO 2014 and NUS-WIDE. In addition, extensive ablation studies and empirical analysis are provided to demonstrate the effectiveness of the essential components of our method under different factors.

Multiclass classification of histology on colorectal cancer using deep learning

Colorectal cancer (CRC) is a type of cancer that occurs in the colon or rectum, caused by cells dividing uncontrollably. Deep learning has proven to perform image recognition accurately that rivals human capabilities. This method became popular and can handle various complex image data. This paper presents a multiclass classification of histology on colorectal cancer using a Convolutional Neural Network (CNN). We propose the usage of EfficientNet with transfer learning to create high-performance learners and combine the model with the attention Squeeze and Excitation layer (SE layer). In several studies, the SE layer can improve the model by extracting essential features of the images. We compare EfficientNet with other architectures such as ResNet-101, AlexNet, and VGG16. Our experiment result achieves 97% testing accuracy, whereas NN-Ensemble-CNNs as the baseline model achieves 96.16%. The combined EfficientNet model and SE layer performed better than regular EfficientNet and other models.

Textual Backdoor Attack for the Text Classification System

Deep neural networks provide good performance for image recognition, speech recognition, text recognition, and pattern recognition. However, such networks are vulnerable to backdoor attacks. In a backdoor attack, normal data that do not include a specific trigger are correctly classified by the target model, but backdoor data that include the trigger are incorrectly classified by the target model. One advantage of a backdoor attack is that the attacker can use a specific trigger to attack at a desired time. In this study, we propose a backdoor attack targeting the BERT model, which is a classification system designed for use in the text domain. Under the proposed method, the model is additionally trained on a backdoor sentence that includes a specific trigger, and afterward, if the trigger is attached before or after an original sentence, it will be misclassified by the model. In our experimental evaluation, we used two movie review datasets (MR and IMDB). The results show that using the trigger word “ATTACK” at the beginning of an original sentence, the proposed backdoor method had a 100% attack success rate when approximately 1.0% and 0.9% of the training data consisted of backdoor samples, and it allowed the model to maintain an accuracy of 86.88% and 90.80% on the original samples in the MR and IMDB datasets, respectively.

Integrated Transfer Learning Method for Image Recognition Based on Neural Network

As recognition technology advances in various fields, the problem of requiring a large number of correct image recognition is also accompanied. So as to promote the correctness of image recognition, we adopted two Convolutional Neural Network (CNN) integrated migration learning network models VGG-16 CNN and LeNet-5 CNN. Experimental results prove that the performance of image recognition in various models are improved. Also, the migration learning and convolutional neural network are used to construct a K-selection migration learning algorithm and a migration framework model whose parameters are migrated to the image data set. The use of a label data set with a large sample size, the selection of a pre-trained convolutional neural network model with a deep layer of complex network structure and the selection of an appropriate network fine-tuning depth can optimize the migration adaptation effect of the migration network. The image recognition precision of the algorithm is improved by about 3%, which further improves the migration adaptation effect.

Research on fan vibration fault diagnosis based on image recognition

The conventional methods for vibration fault detection and diagnosis relies on feature extraction from the waveforms of the vibration signals. This article exploits the scope of image recognition application for the detection and diagnosis of fan vibration faults. In this paper, a novel image recognition technique is proposed for vibration-based fault diagnosis using the spectrum images of the vibration signals. 1D vibration signal spectrum is initially computed using Fast Fourier Transform (FFT) and the FFT frequencies are adjusted such that it captures a vibration spectrum diagram as 2D image representation. FFT based vibration analysis is done and the image recognition concept is utilized for feature extraction and a machine learning classification module is used for fault analysis and diagnosis. Effective feature generation is done using Principal Component Analysis (PCA) by removing the redundancy from the feature vectors and machine learning classifiers are used to obtain improved image recognition and classification performance. Artificial Neural Network (ANN) classifier yields better performance in terms of various performance parameters and percentage improvement in terms of accuracy for ANN classification methods over Support Vector Machine (SVM), k-Nearest Neighbours (kNN) and Random Forest Ensemble (RFE) methods are 10.01 %, 4.51 % and 2.01 % respectively. Comparative scenarios are considered in this work for fan vibration fault detection as well as diagnosis based on the image features for various realistic vibration fault conditions. Effectiveness of the proposed image recognition-based technique is compared with the state-of-the-art methods, justifying its outperformance for fan fault detection and diagnosis using the combination of spectrum adjustment, PCA and ANN classification method.

Few-shot contrastive learning for image classification and its application to insulator identification.

This paper presents a novel discriminative Few-shot learning architecture based on batch compact loss. Currently, Convolutional Neural Network (CNN) has achieved reasonably good performance in image recognition. Most existing CNN methods facilitate classifiers to learn discriminating patterns to identify existing categories trained with large samples. However, learning to recognize novel categories from a few examples is a challenging task. To address this, we propose the Residual Compact Network to train a deep neural network to learn hierarchical nonlinear transformations to project image pairs into the same latent feature space, under which the distance of each positive pair is reduced. To better use the commonality of class-level features for category recognition, we develop a batch compact loss to form robust feature representations relevant to a category. The proposed methods are evaluated on several datasets. Experimental evaluations show that our proposed method achieves acceptable results in Few-shot learning.

Brain hierarchy score: Which deep neural networks are hierarchically brain-like?

SummaryAchievement of human-level image recognition by deep neural networks (DNNs) has spurred interest in whether and how DNNs are brain-like. Both DNNs and the visual cortex perform hierarchical processing, and correspondence has been shown between hierarchical visual areas and DNN layers in representing visual features. Here, we propose the brain hierarchy (BH) score as a metric to quantify the degree of hierarchical correspondence based on neural decoding and encoding analyses where DNN unit activations and human brain activity are predicted from each other. We find that BH scores for 29 pre-trained DNNs with various architectures are negatively correlated with image recognition performance, thus indicating that recently developed high-performance DNNs are not necessarily brain-like. Experimental manipulations of DNN models suggest that single-path sequential feedforward architecture with broad spatial integration is critical to brain-like hierarchy. Our method may provide new ways to design DNNs in light of their representational homology to the brain.