Small-Footprint Magic Word Detection Method Using Convolutional LSTM Neural Network
7
Citation
10
Reference
10
Related Paper
Citation Trend
Keywords:
Footprint
Surface damage on concrete is important as the damage can affect the structural integrity of the structure. This paper proposes a two-step surface damage detection scheme using Convolutional Neural Network (CNN) and Artificial Neural Network (ANN). The CNN classifies given input images into two categories: positive and negative. The positive category is where the surface damage is present within the image, otherwise the image is classified as negative. This is an image-based classification. The ANN accepts image inputs that have been classified as positive by the ANN. This reduces the number of images that are further processed by the ANN. The ANN performs feature-based classification, in which the features are extracted from the detected edges within the image. The edges are detected using Canny edge detection. A total of 19 features are extracted from the detected edges. These features are inputs into the ANN. The purpose of the ANN is to highlight only the positive damaged edges within the image. The CNN achieves an accuracy of 80.7% for image classification and the ANN achieves an accuracy of 98.1% for surface detection. The decreased accuracy in the CNN is due to the false positive detection, however false positives are tolerated whereas false negatives are not. The false negative detection for both CNN and ANN in the two-step scheme are 0%.
Feature (linguistics)
Canny edge detector
Cite
Citations (1)
Unconstrained Face Verification is still an important problem worth researching. The major challenges such as illumination, pose, occlusion and expression can produce more complex variations in both shape and texture of the face. In this paper, we propose a method based on Monogenic Binary Pattern and Convolutional Neural Network (MBP-CNN) to improve the performance of face recognition system. For each facial image, the proposed method firstly extracts local features using Monogenic Binary Pattern (MBP) which is an excellent and powerful local descriptor compared to the well-recognized Gabor filtering-based LBP models. Then, we use Convolutional Neural Networks which is one of the best representative network architectures of deep learning in the literature, in order to extract more deep features. Thus, the developed MBP-CNN has robustness to variations of illumination, occlusion, pose, expression, texture and shape by combining Monogenic Binary Pattern and convolutional neural network. Moreover, MBP-CNN was more accurately represented by combining global and local information of facial images. Experiments demonstrate that our method provided competitive performance on the LFW database, compared to the others described in the state-of-the-art.
Local Binary Patterns
Robustness
Cite
Citations (5)
This paper proposes a new face verification method that uses multiple deep convolutional neural networks (DCNNs) and a deep ensemble, that extracts two types of low dimensional but discriminative and high-level abstracted features from each DCNN, then combines them as a descriptor for face verification. Our DCNNs are built from stacked multi-scale convolutional layer blocks to present multi-scale abstraction. To train our DCNNs, we use different resolutions of triplets that consist of reference images, positive images, and negative images, and triplet-based loss function that maximize the ratio of distances between negative pairs and positive pairs and minimize the absolute distances between positive face images. A deep ensemble is generated from features extracted by each DCNN, and used as a descriptor to train the joint Bayesian learning and its transfer learning method. On the LFW, although we use only 198,018 images and only four different types of networks, the proposed method with the joint Bayesian learning and its transfer learning method achieved 98.33% accuracy. In addition to further increase the accuracy, we combine the proposed method and high dimensional LBP based joint Bayesian method, and achieved 99.08% accuracy on the LFW. Therefore, the proposed method helps to improve the accuracy of face verification when training data is insufficient to train DCNNs.
Discriminative model
Transfer of learning
Abstraction
Cite
Citations (16)
In this work, we compare the performance of three local-feature-based texture classifiers and a Convolutional Neural Network (CNN) at face recognition with sparse training data. The texture-based classifiers use Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), and Scale Invariant Feature Transform (SIFT), respectively. The CNN uses six convolutional layers, two pooling layers, two fully connected layers, and outputs a softmax probability distribution over the classes. The dataset contains 100 classes with five samples each, and is partitioned so there is only one training sample per class. Under these conditions, we find that all three feature-based approaches significantly outperform the CNN, with the HOG-based approach showing especially strong performance.
Softmax function
Local Binary Patterns
Pooling
Scale-invariant feature transform
Discriminative model
Feature (linguistics)
Cite
Citations (2)
Deep learning methods have been effectively used to provide great improvement in various research fields such as machine learning, image processing and computer vision. One of the most frequently used deep learning methods in image processing is the convolutional neural networks. Compared to the traditional artificial neural networks, convolutional neural networks do not use the predefined kernels, but instead they learn data specific kernels. This property makes them to be used as feature extractors as well. In this study, we used a convolutional neural network including 60 million parameters and 650 thousand neurons to extract features to be used for image retrieval. The architecture of the network consists of five convolutional layers and three fully-connected layers. Extracted features, in comparison with Fisher vectors - which are one of the most widely used representation types - are tested on UCMerced Land Use dataset in terms of retrieval accuracies by using different hashing methods. Experimental results demonstrate the superiority of the CNN features.
Feature (linguistics)
Contextual image classification
Cite
Citations (7)
In order to extract effective image features in different areas of an image, a method of deep convolutional neural networks with adaptive spatial characteristics for person re-identification is proposed. Firstly, each pedestrian image is divided into multiple blocks according to the characteristics of spatial distribution. Secondly, multi-branch of convolutional neural networks is used to extract deep features of individual pedestrian image block adaptively. Finally, the images are discriminated whether belong to the same person by calculating the deep feature's similarity. Different from traditional methods which extracts whole pedestrian's feature and feedback adjusted, the proposed method extract deep features from various areas of an image, and improved results are obtained on VIPeR dataset.
Feature (linguistics)
Similarity (geometry)
Identification
Contextual image classification
Cite
Citations (5)
Convolutional neural network extracts features from input data and classify them with end to end learning. In this paper we test the performance of the cooperation between texture features which undertakes effective role for SAR image classification and convolutional neural network. For this purpose we create local images for each pixel in the image taking into consideration neighbor pixels and pixel-based classification is performed with convolutional neural network after being extracted histogram and texture features from these images. Experimental results show that the network trained with feature vectors gives high classification accuracy.
Contextual image classification
Feature (linguistics)
Cite
Citations (1)
Robustness
Feature (linguistics)
Cite
Citations (67)
Feature (linguistics)
Identification
Contextual image classification
Cite
Citations (9)
Single label image classification has been promisingly demonstrated using Convolutional Neural Network (CNN). However, how this CNN will fit for multi-label images is still difficult to solve. It is mainly difficult due to lack of multi-label training image data and high complexity of latent obj ect layouts. This paper proposes an approach for classifying multi-label image by a trained single label classifier using CNN with objectness measure and selective search. We have taken two established image segmentation techniques for segmenting a multi-label image into some segmented images. Then we have forwarded the images to our trained CNN and predicted the labels of the segmented images by generalizing the result. Our single-label image classifier gives 87% accuracy on CIFAR-10 dataset. Using objectness measure with CNN gives us 51 % accuracy on a multi-label dataset and gives up to 57% accuracy using selective search both considering top-4 labels that is significantly good for a simple approach rather than a complex approach for multi-label classification using CNN.
Multi-label classification
Contextual image classification
Cite
Citations (10)