In this paper, an abnormal object detection method in X-ray images is proposed under the framework of YOLO. ResNeXt-50 is adopted as the backbone network to extract the deep features. And a self-normalizing channel attention mechanism (SCAM) is proposed and introduced into the high layer of ResNeXt-50 to enhance the semantic representative ability of the features. According to the characteristics of X-ray images, an efficient data augmentation method is also proposed to enlarge the amount of the training data samples, which facilitates to improve the training performance of the network. The experimental results on the public SIX-ray and OPIX-ray datasets show that, compared with the methods of YOLO series, the proposed method can obtain a higher detection accuracy.
In airports, railway stations and other public places, security inspectors generally use the way of viewing x-ray images for security inspection, so false detection and missed detection often occur. In this paper, an automatic anomaly object detection method in x-ray images is proposed under a two-stage framework. At the first stage, a learnable Gabor convolution layer is introduced into ResNeXt to facilitate the network to capture the edge information of objects. Then, region proposal network (RPN) is used to determine the candidate regions of objects as well as perform coarse classification. At the second stage, bigger discriminative RoI pooling (BDRP) is proposed to classify the candidate boxes to improve the classification accuracy of objects. Furthermore, dense local regression (DLR) is applied to predict the offset of multiple dense boxes in region proposals to locate the objects accurately. Experimental results on the SIXray and OPIXray datasets show that, compared with the state-of-the-art methods, the proposed method can achieve a competitive detection performance.
With the rapid development of remote-sensing earth observation technology, hyperspectral imagery has shown exponential growth. The quick and accurate retrieval of hyperspectral images has become a practical challenge in applications. Moreover, open network sharing has rendered network information security increasingly important. It is necessary to prevent breach of confidentiality events during retrieval, particularly for hyperspectral images containing crucial information. Therefore, a method for hyperspectral image secure retrieval based on encrypted deep spectral–spatial features is proposed. In principle, our method includes the following steps: (1) Considering the powerful feature learning capability of deep networks, deep spectral–spatial features of hyperspectral image are extracted with a deep convolutional generative adversarial network. (2) For high-dimensional deep features, t-distributed Stochastic neighbor embedding based nonlinear manifold hashing is utilized to reduce the dimensionality of deep spectral–spatial features. (3) To ensure data security during retrieval, deep spectral–spatial features are encrypted with feature randomization encryption. (4) Multi-index hashing is utilized to measure similarities among the deep spatial–spectral features of hyperspectral images. (5) Relevance feedback based on feature reweighting is introduced to further improve retrieval accuracy. Four experiments are conducted to prove the effectiveness of the proposed method based on retrieval and security performance. Our experimental results on two hyperspectral datasets show that our method can effectively protect the security of image content with sufficient image retrieval accuracy.
Vehicle classification is vital to an intelligent transport system. To obtain a high accuracy, it is the most crucial process to extract reliable and distinguishable features of vehicles. A feature extraction method using a lightweight convolutional network for vehicle classification is proposed. The main contributions are threefold: (1) a lightweight network named LWNet with two convolution layers is proposed to extract the features of the vehicles; (2) Hu moment is integrated with spatial location information to improve its own describing and distinguishing ability; and (3) histogram of oriented gradient (HOG) feature is extracted from the complete image, and then the above two kinds of features are combined with HOG to form the vector. And then, a support vector machine is trained to obtain the classification model. Vehicles are classified into six categories, i.e., large bus, car, motorcycle, minibus, truck, and van. The experimental results have demonstrated that the classification accuracy can achieve 97.39%, which is 3.81% higher than that obtained from the conventional methods. In addition, for this vehicle classification task, the proposed lightweight convolutional network can achieve comparable or even higher performance compared to the deep convolutional neural networks, while the proposed method does not need the support of a graphics processing unit and has much lower complexity without the training process.
Vehicle color recognition is easily affected by subtle environmental changes. The existing recognition methods cannot achieve an accurate result. A high-accuracy vehicle color recognition method using a hierarchical fine-tuning strategy for urban surveillance videos is proposed. Different from the conventional convolutional neural networks-based methods, which usually obtain a single classification model, the proposed method combines pretraining and hierarchical fine-tunings to obtain different classification models that can adapt to the change of illumination conditions. First, the GoogLeNet is pretrained using the ILSVRC-2012 dataset to obtain the initial weight parameters of the network. During the first stage of fine-tuning, the whole vehicle color dataset is used to fine-tune the pretrained results to get the initial classification model. Then, an image quality assessment method is proposed to evaluate the illumination conditions of the image. The whole vehicle color dataset is divided into some subdatasets according to the evaluation results. The second stage of fine-tuning is performed on the initial classification model using each subdataset. Thus, the final classification models for the subdatasets are obtained. The experimental results on different databases demonstrate that the recognition accuracy of the proposed method can achieve superior performance over the state-of-the-art methods.
For large-scale hyperspectral image data, how to retrieve the satisfied information quickly and accurately is critical. As hyperspectral images are one of the important fundamental and strategic information resources, it is necessary to ensure data security during the retrieval process. A secure retrieval method of hyperspectral images in an encrypted domain is proposed. The main contributions are fourfold: (1) for accurately describing the hyperspectral image content, spectral words are created to represent the spectral feature of hyperspectral image and the gray level cooccurrence matrix is computed as the texture feature; (2) the hyperspectral images are protected using a hybrid domain encryption method; (3) an order preserving encryption method is utilized to encrypt the spectral words and texture feature for secure retrieval; and (4) the retrieval results are obtained by matching Jaccard distance in the encrypted domain and then further optimized by the user’s relevance feedback. The experimental results show that our secure retrieval method can effectively improve the retrieval accuracy of a hyperspectral image as well as guarantee the security of the image content.
With the rapid development and popularity of the network, the openness, anonymity, and interactivity of networks have led to the spread and proliferation of pornographic images on the Internet, which have done great harm to adolescents’ physical and mental health. With the establishment of image compression standards, pornographic images are mainly stored with compressed formats. Therefore, how to efficiently filter pornographic images is one of the challenging issues for information security. A pornographic image recognition and filtering method in the compressed domain is proposed by using incremental learning, which includes the following steps: (1) low-resolution (LR) images are first reconstructed from the compressed stream of pornographic images, (2) visual words are created from the LR image to represent the pornographic image, and (3) incremental learning is adopted to continuously adjust the classification rules to recognize the new pornographic image samples after the covering algorithm is utilized to train and recognize the visual words in order to build the initial classification model of pornographic images. The experimental results show that the proposed pornographic image recognition method using incremental learning has a higher recognition rate as well as costing less recognition time in the compressed domain.
KEYWORDS: Target detection, Hyperspectral imaging, Detection and tracking algorithms, Sensors, Image processing, Data processing, Hyperspectral target detection, Signal to noise ratio, Signal processing, Receivers
The high dimensionality of hyperspectral imagery is a huge challenge for remote sensing data processing. Band selection utilizes the most distinctive and informative band subset to reduce data dimensions. Although band selection can significantly alleviate the computational burden, the process itself may be time consuming because it needs to take all pixels into consideration, especially when the image spatial size is larger. An improved band similarity-based band selection method is proposed for hyperspectral imagery target detection, which includes four steps: (1) bad bands are removed by data preprocessing; (2) several selected pixels are used for band selection instead of using all the pixels to reduce the computational complexity; (3) hyperspectral imagery is analyzed for target detection; and (4) the number of selected bands is determined by adjusting the threshold of similarity metric, to ensure target detection operators have the best performance with selected bands. In the example, the well-known adaptive coherence estimator detector was used to evaluate the effectiveness of the proposed band selection method. The receiver operating characteristics curves were plotted to prove the proposed algorithm quantitatively. The experimental results show that our method can yield a better result in target detection than other band selection methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.