A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks

We propose a simple but effective convolutional neural network to learn the similarities between closely related raw pixel images for feature representation extraction and classification through the initialization of convolutional kernels from learned filter kernels of the network. The binary-class classification of sigmoid and discriminative feature vectors are simultaneously learned together contrasting the handcrafted traditional method of feature extractions, which split feature-extraction and classification tasks into two different processes during training. Relying on the high-quality feature representation learned by the network, the classification tasks can be efficiently conducted. We evaluated the classification performance of our proposed method using a collection of tile surface images consisting of cracked surfaces and no-cracked surfaces. We tried to classify the tiny-cracked surfaces from non-crack normal tile demarcations, which could be useful for automated visual inspections that are labor intensive, risky in high altitudes, and time consuming with manual inspection methods. We performed a series of comparisons on the results obtained by varying the optimization, activation functions, and deployment of different data augmentation methods in our network architecture. By doing this, the effectiveness of the presented model for smooth surface defect classification was explored and determined. Through extensive experimentation, we obtained a promising validation accuracy and minimal loss.

Download Full-text

UAV Image Multi-Labeling with Data-Efficient Transformers

Applied Sciences ◽

10.3390/app11093974 ◽

2021 ◽

Vol 11 (9) ◽

pp. 3974

Author(s):

Laila Bashmal ◽

Yakoub Bazi ◽

Mohamad Mahmoud Al Rahhal ◽

Haikel Alhichri ◽

Naif Al Ajlan

Keyword(s):

Data Augmentation ◽

Feature Representation ◽

Aerial Image ◽

Remote Sensing Images ◽

Training Set ◽

Proposed Model ◽

Class Labels ◽

Using Data ◽

Uav Image

In this paper, we present an approach for the multi-label classification of remote sensing images based on data-efficient transformers. During the training phase, we generated a second view for each image from the training set using data augmentation. Then, both the image and its augmented version were reshaped into a sequence of flattened patches and then fed to the transformer encoder. The latter extracts a compact feature representation from each image with the help of a self-attention mechanism, which can handle the global dependencies between different regions of the high-resolution aerial image. On the top of the encoder, we mounted two classifiers, a token and a distiller classifier. During training, we minimized a global loss consisting of two terms, each corresponding to one of the two classifiers. In the test phase, we considered the average of the two classifiers as the final class labels. Experiments on two datasets acquired over the cities of Trento and Civezzano with a ground resolution of two-centimeter demonstrated the effectiveness of the proposed model.

Download Full-text

Large-Scale Whale-Call Classification by Transfer Learning on Multi-Scale Waveforms and Time-Frequency Features

Applied Sciences ◽

10.3390/app9051020 ◽

2019 ◽

Vol 9 (5) ◽

pp. 1020 ◽

Cited By ~ 6

Author(s):

Lilun Zhang ◽

Dezhi Wang ◽

Changchun Bao ◽

Yongxian Wang ◽

Kele Xu

Keyword(s):

Transfer Learning ◽

Large Scale ◽

Data Augmentation ◽

Feature Representation ◽

Biological Research ◽

Time Frequency ◽

Feature Representations ◽

Multi Scale ◽

Data Driven Approach

Whale vocal calls contain valuable information and abundant characteristics that are important for classification of whale sub-populations and related biological research. In this study, an effective data-driven approach based on pre-trained Convolutional Neural Networks (CNN) using multi-scale waveforms and time-frequency feature representations is developed in order to perform the classification of whale calls from a large open-source dataset recorded by sensors carried by whales. Specifically, the classification is carried out through a transfer learning approach by using pre-trained state-of-the-art CNN models in the field of computer vision. 1D raw waveforms and 2D log-mel features of the whale-call data are respectively used as the input of CNN models. For raw waveform input, windows are applied to capture multiple sketches of a whale-call clip at different time scales and stack the features from different sketches for classification. When using the log-mel features, the delta and delta-delta features are also calculated to produce a 3-channel feature representation for analysis. In the training, a 4-fold cross-validation technique is employed to reduce the overfitting effect, while the Mix-up technique is also applied to implement data augmentation in order to further improve the system performance. The results show that the proposed method can improve the accuracies by more than 20% in percentage for the classification into 16 whale pods compared with the baseline method using groups of 2D shape descriptors of spectrograms and the Fisher discriminant scores on the same dataset. Moreover, it is shown that classifications based on log-mel features have higher accuracies than those based directly on raw waveforms. The phylogeny graph is also produced to significantly illustrate the relationships among the whale sub-populations.

Download Full-text

Gastrointestinal Disease Classification in Endoscopic Images Using Attention-Guided Convolutional Neural Networks

Applied Sciences ◽

10.3390/app112311136 ◽

2021 ◽

Vol 11 (23) ◽

pp. 11136

Author(s):

Zenebe Markos Lonseko ◽

Prince Ebenezer Adjei ◽

Wenju Du ◽

Chengsi Luo ◽

Dingcan Hu ◽

...

Keyword(s):

Data Augmentation ◽

Spatial Information ◽

Gastrointestinal Disease ◽

Confusion Matrix ◽

Automatic Classification ◽

Classification Performance ◽

Attention Mechanism ◽

Disease Classification ◽

Matrix Analysis

Gastrointestinal (GI) diseases constitute a leading problem in the human digestive system. Consequently, several studies have explored automatic classification of GI diseases as a means of minimizing the burden on clinicians and improving patient outcomes, for both diagnostic and treatment purposes. The challenge in using deep learning-based (DL) approaches, specifically a convolutional neural network (CNN), is that spatial information is not fully utilized due to the inherent mechanism of CNNs. This paper proposes the application of spatial factors in improving classification performance. Specifically, we propose a deep CNN-based spatial attention mechanism for the classification of GI diseases, implemented with encoder–decoder layers. To overcome the data imbalance problem, we adapt data-augmentation techniques. A total of 12,147 multi-sited, multi-diseased GI images, drawn from publicly available and private sources, were used to validate the proposed approach. Furthermore, a five-fold cross-validation approach was adopted to minimize inconsistencies in intra- and inter-class variability and to ensure that results were robustly assessed. Our results, compared with other state-of-the-art models in terms of mean accuracy (ResNet50 = 90.28, GoogLeNet = 91.38, DenseNets = 91.60, and baseline = 92.84), demonstrated better outcomes (Precision = 92.8, Recall = 92.7, F1-score = 92.8, and Accuracy = 93.19). We also implemented t-distributed stochastic neighbor embedding (t–SNE) and confusion matrix analysis techniques for better visualization and performance validation. Overall, the results showed that the attention mechanism improved the automatic classification of multi-sited GI disease images. We validated clinical tests based on the proposed method by overcoming previous limitations, with the goal of improving automatic classification accuracy in future work.

Download Full-text

An Efficient Lightweight Neural Network for Remote Sensing Image Change Detection

Remote Sensing ◽

10.3390/rs13245152 ◽

2021 ◽

Vol 13 (24) ◽

pp. 5152

Author(s):

Kaiqiang Song ◽

Fengzhi Cui ◽

Jie Jiang

Keyword(s):

Remote Sensing ◽

Change Detection ◽

Land Surface ◽

Network Architecture ◽

Data Augmentation ◽

Feature Fusion ◽

Feature Representation ◽

Geometric Transformation ◽

Computation Efficiency ◽

Image Change Detection

Remote sensing (RS) image change detection (CD) is a critical technique of detecting land surface changes in earth observation. Deep learning (DL)-based approaches have gained popularity and have made remarkable progress in change detection. The recent advances in DL-based methods mainly focus on enhancing the feature representation ability for performance improvement. However, deeper networks incorporated with attention-based or multiscale context-based modules involve a large number of network parameters and require more inference time. In this paper, we first proposed an effective network called 3M-CDNet that requires about 3.12 M parameters for accuracy improvement. Furthermore, a lightweight variant called 1M-CDNet, which only requires about 1.26 M parameters, was proposed for computation efficiency with the limitation of computing power. 3M-CDNet and 1M-CDNet have the same backbone network architecture but different classifiers. Specifically, the application of deformable convolutions (DConv) in the lightweight backbone made the model gain a good geometric transformation modeling capacity for change detection. The two-level feature fusion strategy was applied to improve the feature representation. In addition, the classifier that has a plain design to facilitate the inference speed applied dropout regularization to improve generalization ability. Online data augmentation (DA) was also applied to alleviate overfitting during model training. Extensive experiments have been conducted on several public datasets for performance evaluation. Ablation studies have proved the effectiveness of the core components. Experiment results demonstrate that the proposed networks achieved performance improvements compared with the state-of-the-art methods. Specifically, 3M-CDNet achieved the best F1-score on two datasets, i.e., LEVIR-CD (0.9161) and Season-Varying (0.9749). Compared with existing methods, 1M-CDNet achieved a higher F1-score, i.e., LEVIR-CD (0.9118) and Season-Varying (0.9680). In addition, the runtime of 1M-CDNet is superior to most, which exhibits a better trade-off between accuracy and efficiency.

Download Full-text

Transparent Classification with Multilayer Logical Perceptrons and Random Binarization

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.6102 ◽

2020 ◽

Vol 34 (04) ◽

pp. 6331-6339

Author(s):

Zhuo Wang ◽

Wei Zhang ◽

Ning LIU ◽

Jianyong Wang

Keyword(s):

Network Architecture ◽

Gradient Descent ◽

Classification Performance ◽

Data Sets ◽

Neural Network Architecture ◽

Continuous Version ◽

Continuous Space ◽

Public Data ◽

Rule Sets ◽

Classification Tasks

Models with transparent inner structure and high classification performance are required to reduce potential risk and provide trust for users in domains like health care, finance, security, etc. However, existing models are hard to simultaneously satisfy the above two properties. In this paper, we propose a new hierarchical rule-based model for classification tasks, named Concept Rule Sets (CRS), which has both a strong expressive ability and a transparent inner structure. To address the challenge of efficiently learning the non-differentiable CRS model, we propose a novel neural network architecture, Multilayer Logical Perceptron (MLLP), which is a continuous version of CRS. Using MLLP and the Random Binarization (RB) method we proposed, we can search the discrete solution of CRS in continuous space using gradient descent and ensure the discrete CRS acts almost the same as the corresponding continuous MLLP. Experiments on 12 public data sets show that CRS outperforms the state-of-the-art approaches and the complexity of the learned CRS is close to the simple decision tree.

Download Full-text

Automatic detection and classification of the ceramic tiles’ surface defects

Pattern Recognition ◽

10.1016/j.patcog.2016.11.021 ◽

2017 ◽

Vol 66 ◽

pp. 174-189 ◽

Cited By ~ 34

Author(s):

Saeed Hosseinzadeh Hanzaei ◽

Ahmad Afshar ◽

Farshad Barazandeh

Keyword(s):

Surface Defects ◽

Automatic Detection ◽

Ceramic Tiles

Download Full-text

Recognition of Scratches and Abrasions on Metal Surfaces Using a Classifier Based on a Convolutional Neural Network

Metals ◽

10.3390/met11040549 ◽

2021 ◽

Vol 11 (4) ◽

pp. 549

Author(s):

Ihor Konovalenko ◽

Pavlo Maruschak ◽

Vitaly Brevus ◽

Olegas Prentkovskis

Keyword(s):

Neural Network ◽

Steel Industry ◽

Network Architecture ◽

Metal Surfaces ◽

Surface Defects ◽

High Accuracy ◽

Feature Maps ◽

Neural Network Architecture ◽

Neuron Activation

Classification of steel surface defects in steel industry is essential for their detection and also fundamental for the analysis of causes that lead to damages. Timely detection of defects allows to reduce the frequency of their appearance in the final product. This paper considers the classifiers for the recognition of scratches, scrapes and abrasions on metal surfaces. Classifiers are based on the ResNet50 and ResNet152 deep residual neural network architecture. The proposed technique supports the recognition of defects in images and does this with high accuracy. The binary accuracy of the classification based on the test data is 97.14%. The influence of a number of training conditions on the accuracy metrics of the model have been studied. The augmentation conditions have been figured out to make the greatest contribution to improving the accuracy during training. The peculiarities of damages that cause difficulties in their recognition have been studied. The fields of neuron activation have been investigated in the convolutional layers of the model. Feature maps which developed in this case have been found to correspond to the location of the objects of interest. Erroneous cases of the classifier application have been considered. The peculiarities of damages that cause difficulties in their recognition have been studied.

Download Full-text

Klasifikasi Kualitas Mutu Daun Gambir Ladang Rakyat Menggunakan Metode Convolutional Neural Network

Jurnal Sistim Informasi dan Teknologi ◽

10.37034/jsisfotek.v3i3.156 ◽

2021 ◽

pp. 102-107

Author(s):

Teddy Winanda ◽

Yuhandri Yunus ◽

H Hendrick

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Data Augmentation ◽

Poor Quality ◽

Leaf Quality ◽

Manual Inspection ◽

West Sumatra ◽

Python Programming

Indonesia is one of the countries which have the best Gambier quality in the world. Those are a few areas in Indonesia which have best gambier quality such as Aceh, Riau, North Sumatera, Bengkulu, South Sumatera and West Sumatra. Kabupaten 50 Kota is one of the regencies in west Sumatra that supplies gambier in Indonesia. The gambier leaf selection is mostly done by manual inspection or conventional method. The leaf color, thickness and structure are the important parameters in selecting gambier leaf quality. Farmers usually classify the quality of gambier leaves into good and bad. Computer Vision can help farmers to classify gambier leaves automatically. To realize this proposed method, gambier leaves are collected to create a dataset for training and testing processes. The gambier image leaves is captured by using DLSR camera at Kabupaten 50 Koto manually. 60 images were collected in this research which separated into 30 images with good and 30 images with bad quality. Furthermore, the gambier leaves image is processed by using digital image processing and coded by using python programming language. Both TensorFlow and Keras were implemented as frameworks in this research. To get a faster processing time, Ubuntu 18.04 Linux is selected as an operating system. Convolutional Neural Network (CNN) is the basis of image classification and object detection. In this research, the miniVGGNet architecture was used to perform the model creation. A quantity of dataset images was increased by applying data augmentation methods. The result of image augmentation for good quality gambier produced 3000 images. The same method was applied to poor quality images, the same results were obtained as many as 3000 images, with a total of 6000 images. The classification of gambier leaves produced by the Convolutional Neural Network method using miniVGGNet architecture obtained an accuracy rate of 0.979 or 98%. This method can be used to classify the quality of Gambier leaves very well.

Download Full-text

Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting

Remote Sensing ◽

10.3390/rs10071156 ◽

2018 ◽

Vol 10 (7) ◽

pp. 1156 ◽

Cited By ~ 12

Author(s):

Jacopo Acquarelli ◽

Elena Marchiori ◽

Lutgarde Buydens ◽

Thanh Tran ◽

Twan Laarhoven

Keyword(s):

Network Architecture ◽

Data Augmentation ◽

Hyperspectral Image ◽

State Of The Art ◽

Hyperspectral Images ◽

Class Label ◽

Spatial Classification ◽

Increased Risk ◽

New Learning

Spectral-spatial classification of hyperspectral images has been the subject of many studies in recent years. When there are only a few labeled pixels for training and a skewed class label distribution, this task becomes very challenging because of the increased risk of overfitting when training a classifier. In this paper, we show that in this setting, a convolutional neural network with a single hidden layer can achieve state-of-the-art performance when three tricks are used: a spectral-locality-aware regularization term and smoothing- and label-based data augmentation. The shallow network architecture prevents overfitting in the presence of many features and few training samples. The locality-aware regularization forces neighboring wavelengths to have similar contributions to the features generated during training. The new data augmentation procedure favors the selection of pixels in smaller classes, which is beneficial for skewed class label distributions. The accuracy of the proposed method is assessed on five publicly available hyperspectral images, where it achieves state-of-the-art results. As other spectral-spatial classification methods, we use the entire image (labeled and unlabeled pixels) to infer the class of its unlabeled pixels. To investigate the positive bias induced by the use of the entire image, we propose a new learning setting where unlabeled pixels are not used for building the classifier. Results show the beneficial effect of the proposed tricks also in this setting and substantiate the advantages of using labeled and unlabeled pixels from the image for hyperspectral image classification.

Download Full-text

Computer tomographic differential diagnosis of ameloblastoma and odontogenic keratocyst: classification using a convolutional neural network

Dentomaxillofacial Radiology ◽

10.1259/dmfr.20210002 ◽

2021 ◽

pp. 20210002

Author(s):

Mayara Simões Bispo ◽

Mário Lúcio Gomes de Queiroz Pierre Júnior ◽

Antônio Lopes Apolinário Jr ◽

Jean Nunes dos Santos ◽

Braulio Carneiro Junior ◽

...

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Error Rate ◽

Cross Validation ◽

Data Augmentation ◽

Multidetector Ct ◽

Classification Performance ◽

Tomographic Images ◽

High Classification Accuracy

Objective: To analyse the automatic classification performance of a convolutional neural network (CNN), Google Inception v3, using tomographic images of odontogenic keratocysts (OKCs) and ameloblastomas (AMs). Methods: For construction of the database, we selected axial multidetector CT images from patients with confirmed AM (n = 22) and OKC (n = 18) based on a conclusive histopathological report. The images (n = 350) were segmented manually and data augmentation algorithms were applied, totalling 2500 images. The k-fold × five cross-validation method (k = 2) was used to estimate the accuracy of the CNN model. Results: The accuracy and standard deviation (%) of cross-validation for the five iterations performed were 90.16 ± 0.95, 91.37 ± 0.57, 91.62 ± 0.19, 92.48 ± 0.16 and 91.21 ± 0.87, respectively. A higher error rate was observed for the classification of AM images. Conclusion: This study demonstrated a high classification accuracy of Google Inception v3 for tomographic images of OKCs and AMs. However, AMs images presented the higher error rate.

Download Full-text