Search

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on two 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being partially unable to reach the accuracies reported in the original papers, we compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) point cloud classification methods based on deep learning have good classification performance; however, they adapt poorly to diverse datasets and their classification accuracy must be improved. Therefore, FSDCNet, a neural network model based on the fusion of static and dynamic convolution, is proposed and applied for multiview 3D point cloud classification in this paper. FSDCNet devises a view selection method with fixed and random viewpoints, which effectively avoids the overfitting caused by the traditional fixed viewpoint. A local feature extraction operator of dynamic and static convolution adaptive weight fusion was designed to improve the model's adaptability to different types of datasets. To address the problems of large parameters and high computational complexity associated with the current methods of dynamic convolution, a lightweight and adaptive dynamic convolution operator was developed. In addition, FSDCNet builds a global attention pooling, integrating the most crucial information on different view features to the greatest extent. Due to these characteristics, FSDCNet is more adaptable, can extract more fine-grained detailed information, and can improve the classification accuracy of point cloud data. The proposed method was applied to the ModelNet40 and Sydney Urban Objects datasets. In these experiments, FSDCNet outperformed its counterparts, achieving state-of-the-art point cloud classification accuracy. For the ModelNet40 dataset, the overall accuracy (OA) and average accuracy (AA) of FSDCNet in a single view reached 93.8% and 91.2%, respectively, which were superior to those values for many other methods using 6 and 12 views. FSDCNet obtained the best results for 6 and 12 views, achieving 94.6%, 93.3%, 95.3%, and 93.6% in OA and AA metrics, respectively. For the Sydney Urban Objects dataset, FSDCNet achieved an OA and F1 score of 81.2% and 80.1% in a single view, respectively, which were higher than most of the compared methods. In 6 and 12 views, FSDCNet reached an OA of 85.3% and 83.6% and an F1 score of 85.5% and 83.7%, respectively. [ABSTRACT FROM AUTHOR]

Image classification, which aims at assigning a semantic category to images, has been extensively studied during the past few years. More recently, convolution neural network arises and has achieved very promising achievement. Compared with traditional feature extraction techniques (e.g., SIFT, HOG, GIST), the convolutional neural network can extract features from image automatically and does not need hand designed features. However, how to further improve the classification algorithm is still challenging in academic research. The latest research on CNN shows that the features extracted from middle layers is representative, which shows a possible way to improve the classification accuracy. Based on the observation, in this paper, we propose a method to fuse the latent features extracted from the middle layers in a CNN to train a more robust classifier. First, we utilize the pretrained CNN models to extract visual features from middle layer. Then, we use supervised learning method to train classifiers for each feature respectively. Finally, we use the late fusion strategy to combine the prediction of these classifiers. We evaluate the proposal with different classification methods under some several images benchmarks, and the results demonstrate that the proposed method can improve the performance effectively. [ABSTRACT FROM AUTHOR]

Convolutional neural networks are special types of artificial neural networks that can solve various tasks in computer vision, such as image classification, object detection, and general recognition. The paper presents the basic building blocks of convolutional neural networks and their architecture, and compares their recognition accuracy with other character recognition techniques using the example of character recognition from vehicle registration plates. The purpose of the experiments was to determine the optimal configuration of the convolutional neural network and the influence of the size and design method of the training set on the recognition rate. The study shows that although convolutional neural networks have recently gained attention, traditional recognition methods are still relevant, and the choice of the right classifier and its configuration depends on the type of recognition task. [ABSTRACT FROM AUTHOR]

In semiconductor manufacturing, a wafer bin map (WBM) represents the results of wafer testing for dies using a binary pass or fail value. For WBMs, defective dies are often clustered into groups of local systematic defects. Determining their specific patterns is important, because different patterns are related to different root causes of failure. Recently, because wafer sizes have increased and the process technology has become more complicated, the probability of observing mixed-type defect patterns, i.e., two or more defect patterns in a single wafer, has increased. In this paper, we propose the use of convolutional neural networks (CNNs) to classify mixed-type defect patterns in WBMs in the framework of an individual classification model for each defect pattern. Through simulated and real data examples, we show that the CNN is robust to random noise and performs effectively, even if there are many random defects in WBMs. [ABSTRACT FROM AUTHOR]

Fingerprint pattern recognition and classification can be of assistance in the research on human personality. In some previous studies, fingerprints were classified into four categories to speed up recognition, but the method of that classification is not suitable for researching the diversity of human personalities. Therefore, in this paper, fingerprint patterns were classified into six types and the accuracy of the recognition was improved to facilitate the research on human personality characteristics. Based on this idea, a six-category fingerprint database is annotated manually and a convolutional neural network (CNN) is proposed for identifying real fingerprint patterns. The new CNN consists of four convolutional layers, three max-pooling layers, two norm layers, and three fully connected layers. The best accuracy the model achieved was 94.87% for a six-category fingerprint database and 92.9% accuracy for a four-category fingerprint database. The results of experimental tests show that the proposed model can recognize the pattern features from a large fingerprint database using the automatic learning and feature extraction abilities of the CNN to get a greater accuracy than in previous experiments. [ABSTRACT FROM AUTHOR]

To improve the correct rate of image classification by convolutional neural network, this paper proposed a multimodel fusion convolutional neural network after research on the network structure. By extracting the output feature vectors of a single model and then fusing them, it obtained the new output feature vectors, and then set up a single classifier to classify the images, and improved the accuracy of the classification. By comparing the classification accuracy of single model and multimodel fusion, the class ification accuracy of multi-model fu sion convolutional neural network was improved. This paper analyzed the weight distribution of the last layer of the convolutional neural network, and found that the weight distribution curve of the same model on different data sets was similar and the weight distribution curve of the network model with better classification effect was more gentle. [ABSTRACT FROM AUTHOR]

Cell classification, especially that of white blood cells, plays a very important role in the field of diagnosis and control of major diseases. Compared to traditional optical microscopic imaging, hyperspectral imagery, combined with both spatial and spectral information, provides more wealthy information for recognizing cells. In this paper, a novel blood cell classification framework, which combines a modulated Gabor wavelet and deep convolutional neural network (CNN) kernels, named as MGCNN, is proposed based on medical hyperspectral imaging. For each convolutional layer, multi-scale and orientation Gabor operators are taken dot product with initial CNN kernels. The essence is to transform the convolutional kernels into the frequency domain to learn features. By combining characteristics of Gabor wavelets, the features learned by modulated kernels at different frequencies and orientations are more representative and discriminative. Experimental results demonstrate that the proposed model can achieve better classification performance than traditional CNNs and widely used support vector machine approaches, especially as training small-sample-size situations. [ABSTRACT FROM AUTHOR]

Highlights • The hand-crafted features and the deep features were combined into a deep network. • The importance of different body parts were revealed by the gait descriptor. • The body parts were described in more details after updating data with weights. Gait recognition is an important issue currently. In this paper, we propose to combine deep features and hand-crafted representations into a globally trainable deep model. Specifically, a set of deep feature vectors are firstly extracted by a pre-trained CNN model from the input sequences. Then, a kernel function with respect to the fully connected vector is trained as the guiding weight of the respective receptive fields of the input sequences. Therefore, the hand-crafted features are extracted based on the guiding weight. Finally, the hand-crafted features and the deep features are combined into a unified deep network to complete classification. The optimized gait descriptor, termed as deep convolutional location weight descriptor (DLWD), is capable of effectively revealing the importance of different body parts to gait recognition accuracy. Experiments on two gait data sets (i.e., CASIA-B, OU-ISIR) show that our method outperforms the other existing methods for gait recognition. [ABSTRACT FROM AUTHOR]

In the recent time, enviromental sound classification has received much popularity. This area of research comes under domain of non-speech audio classification. In this work, we have proposed a dilated Convolutional Neural Network approch to classify urban sound. We have carried out feature extraction, data augmentation techniques to carry out our experimental strategy smoothly. We also found out the activation maps of each layers of dilated convolution neural network. An increamental dilation rate has exploited Overall we achieved 84.16% of accuracy from the proposed dilated convolutional method. The gradual increaments of dilation rate has exploited the worse effect of grindding and has lowered down the computational cost. Also, overall classification performance, precision, recall,overall truth and kappa value have been obtained from our proposed method. We have considered 10 fold cross validation for the implementation of the dilated CNN model. [ABSTRACT FROM AUTHOR]

The identification of DNA sequences as exon and intron is a common problem in genome analysis. The methods used for feature extraction and mapping techniques for the digitization of sequences affect directly the solution of this problem. The existing mapping techniques are not enough to detect coding and noncoding regions in some genomes because the digital representation of each base in a DNA sequence with an integer does not fully reflect the structure of an original DNA sequence. In the entropy-based mapping technique, we could overcome this problem because the technique deepens distinction rates of exon regions, and better reflects the complexity of DNA sequences. Moreover, in the literature, features are extracted by using various statistical techniques. The statistical features to be extracted are chosen by a system designer's experience. The other proposed approach in this study is to carry out the feature extraction using the transfer learning method. Transfer learning and feature extraction are performed automatically by convolutional neural network models as independent of the data set. In this study, we propose a new method to classify DNA sequences as exon and intron using two approaches. In the first approach, the entropy-based numerical technique was used for the numerical representation of DNA sequences. In the second approach, transfer learning was used to extract features. Then, the obtained features were classified by support vector machine and k -nearest neighbors algorithm. As a result of the classification, accurate performance with 97.8% was achieved. The performance of the current method was compared with the other numerical mapping techniques and feature extraction methods. The results showed that the developed method was much more successful than other methods. [ABSTRACT FROM AUTHOR]

Huge amount of time series data over several domains such as engineering, biomedical and finance, demands the development of efficient methods for the problem of time series classification. The classification of univariate and multivariate time series together using a single architecture is a very difficult task. In this work, a bio-inspired convolutional spiking neural network (CSNN) is proposed for both univariate and multivariate time series. For this, first we develop a simple transformation to convert raw time series sequences into matrices. The CSNN is a three staged framework which include convolutional feature extraction, spike encoding using soft leaky integrate and fire (Soft-LIf) and classification. As spikes generated are differentiable, thus the learning algorithm for CSNN uses error-backpropagation with cyclical learning rates (CLR) and RMSprop optimizer. Additionally, validation based stopping rules are employed to overcome the overfitting which also provides a set of parameters associated with low validation set loss. Thereafter, to demonstrate the accuracy and robustness of proposed CSNN model, we have used University of California (UCR) univariate as well as University of East Anglia (UEA) multivariate datasets to perform the experiments. Moreover, we conduct comparative empirical performance evaluation with benchmark methods and also with recent deep networks proposed for time series classification. Our results reveal that proposed CSNN advances the baseline methods by achieving higher performance accuracy for both univariate and multivariate datasets. It is shown that the CLR with RMSprop optimizer is able to achieve faster convergence, however CLR and adaptive rates are considered competitive to each other. In addition, we also address the optimal model selection and study the effects of different factors on the performance of proposed CSNN. [ABSTRACT FROM AUTHOR]

This study aims to propose a vision-based method to classify mosquito species. To investigate the efficiency of the method, we compared two different classification methods: The handcraft feature-based conventional method and the convolutional neural network-based deep learning method. For the conventional method, 12 types of features were adopted for handcraft feature extraction, while a support vector machine method was adopted for classification. For the deep learning method, three types of architectures were adopted for classification. We built a mosquito image dataset, which included 14,400 images with three types of mosquito species. The dataset comprised 12,000 images for training, 1500 images for testing, and 900 images for validating. Experimental results revealed that the accuracy of the conventional method using the scale-invariant feature transform algorithm was 82.4% at maximum, whereas the accuracy of the deep learning method was 95.5% in a residual network using data augmentation. From the experimental results, deep learning can be considered to be effective for classifying the mosquito species of the proposed dataset. Furthermore, data augmentation improves the accuracy of mosquito species' classification. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNN) are increasingly being used in hyperspectral image (HSI) classification. However, most pooling methods are non-overlap pooling and ignore the influence of neighboring pixels on image characteristics, thereby limiting network classification accuracy. This work presents a deep CNN that is based on overlap pooling; in this model, non-overlap pooling is replaced with overlap pooling to improve the accuracy of feature extraction. However, overlap pooling introduces additional noise while improving feature accuracy. We have found that different combinations of max pooling and mean pooling can effectively solve the problem and significantly improve classification performance. The best pooling combination (max–mean–mean) for HSI classification is obtained after verification through experiments. A rectified linear unit activation function layer and the softmax loss classification model are combined to improve overall classification accuracy. Experiments on three HSI data sets, namely, Indian Pines, Salinas and Pavia University, show that the CNN model can increase overall accuracy to 95.66, 97.8 and 97.48%, respectively. Compared with deep network models such as deep belief network and non-overlap CNN, the proposed model has significantly improved the classification accuracy, and thus verifying the high accuracy of feature extraction of overlap pooling in CNN. [ABSTRACT FROM AUTHOR]

Variation in the format and classification requirements for remote sensing data makes establishing a standard remote sensing sample dataset difficult. As a result, few remote sensing deep neural network models have been widely accepted. We propose a hybrid deep neural network model based on a convolutional auto-encoder and a complementary convolutional neural network to solve this problem. The convolutional auto-encoder supports feature extraction and data dimension reduction of remote sensing data. The extracted features are input into the convolutional neural network and subsequently classified. Experimental results show that in the proposed model, the classification accuracy increases from 0.916 to 0.944, compared to a traditional convolutional neural network model; furthermore, the number of training runs is reduced from 40,000 to 22,000, and the number of labelled samples can be reduced by more than half, all while ensuring a classification accuracy of no less than 0.9, which suggests the effectiveness and feasibility of the proposed model. [ABSTRACT FROM AUTHOR]

Every pixel in a hyperspectral image contains detailed spectral information in hundreds of narrow bands captured by hyperspectral sensors. Pixel-wise classification of a hyperspectral image is the cornerstone of various hyperspectral applications. Nowadays, deep learning models represented by the convolutional neural network (CNN) provides an ideal solution for feature extraction, and has made remarkable achievements in supervised hyperspectral classification. However, hyperspectral image annotation is time-consuming and laborious, and available training data is usually limited. Due to the "small-sample problem", CNN-based hyperspectral classification is still challenging. Focused on the limited sample-based hyperspectral classification, we designed an 11-layer CNN model called R-HybridSN (Residual-HybridSN) from the perspective of network optimization. With an organic combination of 3D-2D-CNN, residual learning, and depth-separable convolutions, R-HybridSN can better learn deep hierarchical spatial–spectral features with very few training data. The performance of R-HybridSN is evaluated over three public available hyperspectral datasets on different amounts of training samples. Using only 5%, 1%, and 1% labeled data for training in Indian Pines, Salinas, and University of Pavia, respectively, the classification accuracy of R-HybridSN is 96.46%, 98.25%, 96.59%, respectively, which is far better than the contrast models. [ABSTRACT FROM AUTHOR]