scholarly journals Fabric defect recognition using optimized neural networks

2019 ◽  
Vol 14 ◽  
pp. 155892501989739 ◽  
Author(s):  
Zhoufeng Liu ◽  
Chi Zhang ◽  
Chunlei Li ◽  
Shumin Ding ◽  
Yan Dong ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Recognition Task ◽  
Deep Convolutional Neural Network ◽  
Image Feature ◽  
Feature Maps ◽  
Convolutional Network ◽  
Fabric Defect ◽  
Defect Recognition

Fabric defect recognition is an important measure for quality control in a textile factory. This article utilizes a deep convolutional neural network to recognize defects in fabrics that have complicated textures. Although convolutional neural networks are very powerful, a large number of parameters consume considerable computation time and memory bandwidth. In real-world applications, however, the fabric defect recognition task needs to be carried out in a timely fashion on a computation-limited platform. To optimize a deep convolutional neural network, a novel method is introduced to reveal the input pattern that originally caused a specific activation in the network feature maps. Using this visualization technique, this study visualizes the features in a fully trained convolutional model and attempts to change the architecture of original neural network to reduce computational load. After a series of improvements, a new convolutional network is acquired that is more efficient to the fabric image feature extraction, and the computation load and the total number of parameters in the new network is 23% and 8.9%, respectively, of the original model. The proposed neural network is specifically tailored for fabric defect recognition in resource-constrained environments. All of the source code and pretrained models are available online at https://github.com/ZCmeteor .

scholarly journals Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Pei Yang ◽  
Yong Pi ◽  
Tao He ◽  
Jiangming Sun ◽  
Jianan Wei ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Predictive Value ◽  
Automatic Differentiation ◽  
External Validation ◽  
Deep Convolutional Neural Network ◽  
Image Feature ◽  
Training Dataset ◽  
Internal Validation

Abstract Background 99mTc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop an artificial intelligence (AI) system to automatically classify the four patterns of thyroid scintigram. Methods We collected 3087 thyroid scintigrams from center 1 to construct the training dataset (n = 2468) and internal validating dataset (n = 619), and another 302 cases from center 2 as external validating datasets. Four pre-trained neural networks that included ResNet50, DenseNet169, InceptionV3, and InceptionResNetV2 were implemented to construct AI models. The models were trained separately with transfer learning. We evaluated each model’s performance with metrics as following: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), recall, precision, and F1-score. Results The overall accuracy of four pre-trained neural networks in classifying four common uptake patterns of thyroid scintigrams all exceeded 90%, and the InceptionV3 stands out from others. It reached the highest performance with an overall accuracy of 92.73% for internal validation and 87.75% for external validation, respectively. As for each category of thyroid scintigrams, the area under the receiver operator characteristic curve (AUC) was 0.986 for ‘diffusely increased,’ 0.997 for ‘diffusely decreased,’ 0.998 for ‘focal increased,’ and 0.945 for ‘heterogeneous uptake’ in internal validation, respectively. Accordingly, the corresponding performances also obtained an ideal result of 0.939, 1.000, 0.974, and 0.915 in external validation, respectively. Conclusions Deep convolutional neural network-based AI model represented considerable performance in the classification of thyroid scintigrams, which may help physicians improve the interpretation of thyroid scintigrams more consistently and efficiently.

scholarly journals Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

2020 ◽  
Vol 10 (6) ◽  
pp. 2104
Author(s):  
Michał Tomaszewski ◽  
Paweł Michalski ◽  
Jakub Osuchowski
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Detection Efficiency ◽  
Training Data ◽  
Training Dataset ◽  
Training Set ◽  
Convolutional Network

This article presents an analysis of the effectiveness of object detection in digital images with the application of a limited quantity of input. The possibility of using a limited set of learning data was achieved by developing a detailed scenario of the task, which strictly defined the conditions of detector operation in the considered case of a convolutional neural network. The described solution utilizes known architectures of deep neural networks in the process of learning and object detection. The article presents comparisons of results from detecting the most popular deep neural networks while maintaining a limited training set composed of a specific number of selected images from diagnostic video. The analyzed input material was recorded during an inspection flight conducted along high-voltage lines. The object detector was built for a power insulator. The main contribution of the presented papier is the evidence that a limited training set (in our case, just 60 training frames) could be used for object detection, assuming an outdoor scenario with low variability of environmental conditions. The decision of which network will generate the best result for such a limited training set is not a trivial task. Conducted research suggests that the deep neural networks will achieve different levels of effectiveness depending on the amount of training data. The most beneficial results were obtained for two convolutional neural networks: the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN). Faster R-CNN reached the highest AP (average precision) at a level of 0.8 for 60 frames. The R-FCN model gained a worse AP result; however, it can be noted that the relationship between the number of input samples and the obtained results has a significantly lower influence than in the case of other CNN models, which, in the authors’ assessment, is a desired feature in the case of a limited training set.

Deep Convolutional Neural Network for Object Classification

2021 ◽  
pp. 317-343
Author(s):  
Amira Ahmad Al-Sharkawy ◽  
Gehan A. Bahgat ◽  
Elsayed E. Hemayed ◽  
Samia Abdel-Razik Mashali
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Computational Models ◽  
Human Performance ◽  
Deep Neural Networks ◽  
Object Classification ◽  
Classification Problem ◽  
Deep Convolutional Neural Network ◽  
Object Appearance

Object classification problem is essential in many applications nowadays. Human can easily classify objects in unconstrained environments easily. Classical classification techniques were far away from human performance. Thus, researchers try to mimic the human visual system till they reached the deep neural networks. This chapter gives a review and analysis in the field of the deep convolutional neural network usage in object classification under constrained and unconstrained environment. The chapter gives a brief review on the classical techniques of object classification and the development of bio-inspired computational models from neuroscience till the creation of deep neural networks. A review is given on the constrained environment issues: the hardware computing resources and memory, the object appearance and background, and the training and processing time. Datasets that are used to test the performance are analyzed according to the images environmental conditions, besides the dataset biasing is discussed.

scholarly journals A Deep Convolutional Neural Network for Oil Spill Detection from Spaceborne SAR Images

2020 ◽  
Vol 12 (6) ◽  
pp. 1015 ◽  
Author(s):  
Kan Zeng ◽  
Yixiao Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Oil Spill ◽  
Data Augmentation ◽  
Classification Performance ◽  
Deep Convolutional Neural Network ◽  
Convolutional Network ◽  
Data Set ◽  
Oil Spill Detection ◽  
Processing Framework

Classification algorithms for automatically detecting sea surface oil spills from spaceborne Synthetic Aperture Radars (SARs) can usually be regarded as part of a three-step processing framework, which briefly includes image segmentation, feature extraction, and target classification. A Deep Convolutional Neural Network (DCNN), named the Oil Spill Convolutional Network (OSCNet), is proposed in this paper for SAR oil spill detection, which can do the latter two steps of the three-step processing framework. Based on VGG-16, the OSCNet is obtained by designing the architecture and adjusting hyperparameters with the data set of SAR dark patches. With the help of the big data set containing more than 20,000 SAR dark patches and data augmentation, the OSCNet can have as many as 12 weight layers. It is a relatively deep Deep Learning (DL) network for SAR oil spill detection. It is shown by the experiments based on the same data set that the classification performance of OSCNet has been significantly improved compared to that of traditional machine learning (ML). The accuracy, recall, and precision are improved from 92.50%, 81.40%, and 80.95% to 94.01%, 83.51%, and 85.70%, respectively. An important reason for this improvement is that the distinguishability of the features learned by OSCNet itself from the data set is significantly higher than that of the hand-crafted features needed by traditional ML algorithms. In addition, experiments show that data augmentation plays an important role in avoiding over-fitting and hence improves the classification performance. OSCNet has also been compared with other DL classifiers for SAR oil spill detection. Due to the huge differences in the data sets, only their similarities and differences are discussed at the principle level.

scholarly journals Research and Application of Ancient Chinese Pattern Restoration Based on Deep Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Xuhui Fu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Restoration ◽  
Deep Convolutional Neural Network ◽  
Deep Convolutional Neural Networks ◽  
Multilayer Network ◽  
Restoration Method ◽  
Restoration Effect

In recent years, deep learning, as a very popular artificial intelligence method, can be said to be a small area in the field of image recognition. It is a type of machine learning, actually derived from artificial neural networks, and is a method used to learn the characteristics of sample data. It is a multilayer network, which can learn the information from the bottom to the top of the image through the multilayer network, so as to extract the characteristics of the sample, and then perform identification and classification. The purpose of deep learning is to make the machine have the same analytical and learning capabilities as the human brain. The ability of deep learning in data processing (including images) is unmatched by other methods, and its achievements in recent years have left other methods behind. This article comprehensively reviews the application research progress of deep convolutional neural networks in ancient Chinese pattern restoration and mainly focuses on the research based on deep convolutional neural networks. The main tasks are as follows: (1) a detailed and comprehensive introduction to the basic knowledge of deep convolutional neural and a summary of related algorithms along the three directions of text preprocessing, learning, and neural networks are provided. This article focuses on the related mechanism of traditional pattern repair based on deep convolutional neural network and analyzes the key structure and principle. (2) Research on image restoration models based on deep convolutional networks and adversarial neural networks is carried out. The model is mainly composed of four parts, namely, information masking, feature extraction, generating network, and discriminant network. The main functions of each part are independent and interdependent. (3) The method based on the deep convolutional neural network and the other two methods are tested on the same part of the Qinghai traditional embroidery image data set. From the final evaluation index of the experiment, the method in this paper has better evaluation index than the traditional image restoration method based on samples and the image restoration method based on deep learning. In addition, from the actual image restoration effect, the method in this paper has a better image restoration effect than the other two methods, and the restoration results produced are more in line with the habit of human observation with the naked eye.

scholarly journals Prediction of protein function using a deep convolutional neural network ensemble

2017 ◽  
Author(s):  
Evangelia I Zacharaki
Keyword(s):  
Neural Network ◽  
Amino Acid ◽  
Convolutional Neural Network ◽  
Protein Function ◽  
Protein Structures ◽  
Function Prediction ◽  
Deep Convolutional Neural Network ◽  
Supervised Machine Learning ◽  
Support Vector ◽  
Feature Maps

Background. The availability of large databases containing high resolution three-dimensional (3D) models of proteins in conjunction with functional annotation allows the exploitation of advanced supervised machine learning techniques for automatic protein function prediction. Methods. In this work, novel shape features are extracted representing protein structure in the form of local (per amino acid) distribution of angles and amino acid distances, respectively. Each of the multi-channel feature maps is introduced into a deep convolutional neural network (CNN) for function prediction and the outputs are fused through Support Vector Machines (SVM) or a correlation-based k-nearest neighbor classifier. Two different architectures are investigated employing either one CNN per multi-channel feature set, or one CNN per image channel. Results. Cross validation experiments on enzymes (n = 44,661) from the PDB database achieved 90.1% correct classification demonstrating the effectiveness of the proposed method for automatic function annotation of protein structures. Discussion. The automatic prediction of protein function can provide quick annotations on extensive datasets opening the path for relevant applications, such as pharmacological target identification.

scholarly journals Visual Analytics for Network Events Classification in LAN With Deep Convolutional Neural Network

2020 ◽  
Author(s):  
Yuwei Sun ◽  
Hideya Ochiai ◽  
Hiroshi Esaki
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Traffic ◽  
Visual Analytics ◽  
Deep Convolutional Neural Network ◽  
Training Dataset ◽  
Validation Dataset ◽  
Hilbert Curve ◽  
Feature Maps ◽  
F Measure

Abstract This article illustrates a method of visualizing network traffic in LAN based on the Hilbert Curve structure and the array exchange and projection, with nine types of protocols’ communication frequency information as the discriminators, the results of which we call them feature maps of network events. Several known scan cases are simulated in LANs and network traffic is collected for generating feature maps under each case. In order to solve this multi-label classification task, we adopt and train a deep convolutional neural network (DCNN), in two different network environments with feature maps as the input data, and different scan cases as the labels. We separate datasets with a ratio of 4:1 into the training dataset and the validation dataset. Then, based on the micro scores and the macro scores of the validation, we evaluate performance of the scheme, achieving macro-F-measure scores of 0.982 and 0.975, and micro-F-measure scores of 0.976 and 0.965 separately in these two LANs.

Burnt Human Skin Segmentation and Depth Classification Using Deep Convolutional Neural Network (DCNN)

2020 ◽  
Vol 10 (10) ◽  
pp. 2421-2429
Author(s):  
Fakhri Alam Khan ◽  
Ateeq Ur Rehman Butt ◽  
Muhammad Asif ◽  
Hanan Aljuaid ◽  
Awais Adnan ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Human Skin ◽  
Low Income ◽  
Deep Convolutional Neural Network ◽  
Image Feature ◽  
World Health ◽  
Skin Segmentation ◽  
Average Accuracy ◽  
Research Task

World Health Organization (WHO) manage health-related statistics all around the world by taking the necessary measures. What could be better for health and what may be the leading causes of deaths, all these statistics are well organized by WHO. Burn Injuries are mostly viewed in middle and low-income countries due to lack of resources, the result may come in the form of deaths by serious injuries caused by burning. Due to the non-accessibility of specialists and burn surgeons, simple and basic health care units situated at tribble areas as well as in small cities are facing the problem to diagnose the burn depths accurately. The primary goals and objectives of this research task are to segment the burnt region of skin from the normal skin and to diagnose the burn depths as per the level of burn. The dataset contains the 600 images of burnt patients and has been taken in a real-time environment from the Allied Burn and Reconstructive Surgery Unit (ABRSU) Faisalabad, Pakistan. Burnt human skin segmentation was carried by the use of Otsu's method and the image feature vector was obtained by using statistical calculations such as mean and median. A classifier Deep Convolutional Neural Network based on deep learning was used to classify the burnt human skin as per the level of burn into different depths. Almost 60 percent of images have been taken to train the classifier and the rest of the 40 percent burnt skin images were used to estimate the average accuracy of the classifier. The average accuracy of the DCNN classifier was noted as 83.4 percent and these are the best results yet. By the obtained results of this research task, young physicians and practitioners may be able to diagnose the burn depths and start the proper medication.

scholarly journals Mitigation of Effects of Occlusion on Object Recognition with Deep Neural Networks through Low-Level Image Completion

2016 ◽  
Vol 2016 ◽  
pp. 1-15 ◽  
Author(s):  
Benjamin Chandler ◽  
Ennio Mingolla
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Object Recognition ◽  
Convolutional Neural Network ◽  
Deep Neural Networks ◽  
Poor Performance ◽  
Classification Algorithms ◽  
Image Completion ◽  
Convolutional Network ◽  
Occluded Objects

Heavily occluded objects are more difficult for classification algorithms to identify correctly than unoccluded objects. This effect is rare and thus hard to measure with datasets like ImageNet and PASCAL VOC, however, owing to biases in human-generated image pose selection. We introduce a dataset that emphasizes occlusion and additions to a standard convolutional neural network aimed at increasing invariance to occlusion. An unmodified convolutional neural network trained and tested on the new dataset rapidly degrades to chance-level accuracy as occlusion increases. Training with occluded data slows this decline but still yields poor performance with high occlusion. Integrating novel preprocessing stages to segment the input and inpaint occlusions is an effective mitigation. A convolutional network so modified is nearly as effective with more than 81% of pixels occluded as it is with no occlusion. Such a network is also more accurate on unoccluded images than an otherwise identical network that has been trained with only unoccluded images. These results depend on successful segmentation. The occlusions in our dataset are deliberately easy to segment from the figure and background. Achieving similar results on a more challenging dataset would require finding a method to split figure, background, and occluding pixels in the input.

scholarly journals ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget

IoT ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 222-235
Author(s):  
Guillaume Coiffier ◽  
Ghouthi Boukli Hacene ◽  
Vincent Gripon
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Feature Maps ◽  
Neural Network Architecture

Deep Neural Networks are state-of-the-art in a large number of challenges in machine learning. However, to reach the best performance they require a huge pool of parameters. Indeed, typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations. This means that most of the parameters lay in the final layers, while a large portion of the computations are performed by a small fraction of the total parameters in the first layers. In an effort to use every parameter of a network at its maximum, we propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. In complement, normalization, non-linearities, downsamplings and shortcut ensure sufficient expressivity of the model. ThriftyNet achieves competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40 k parameters in total, 74.3% on CIFAR-100 with less than 600 k parameters, and 67.1% On ImageNet ILSVRC 2012 with no more than 4.15 M parameters. However, the proposed method typically requires more computations than existing counterparts.

Sign in / Sign up

Export Citation Format

Share Document