Over the past three decades, significant developments have been made in hyperspectral imaging due to which it has emerged as an effective tool in numerous civil, environmental, and military applications. Modern sensor technologies are capable of covering large surfaces of earth with exceptional spatial, spectral, and temporal resolutions. Due to these features, hyperspectral imaging has been effectively used in numerous remote sensing applications requiring estimation of physical parameters of many complex surfaces and identification of visually similar materials having fine spectral signatures. In the recent years, ground based hyperspectral imaging has gained immense interest in the research on electronic imaging for food inspection, forensic science, medical surgery and diagnosis, and military applications. This review focuses on the fundamentals of hyperspectral image analysis and its modern applications such as food quality and safety assessment, medical diagnosis and image guided surgery, forensic document examination, defense and homeland security, remote sensing applications such as precision agriculture and water resource management and material identification and mapping of artworks. Moreover, recent research on the use of hyperspectral imaging for examination of forgery detection in questioned documents, aided by deep learning, is also presented. This review can be a useful baseline for future research in hyperspectral image analysis.

Breast cancer is among world's second most occurring cancer in all types of cancer. Most common cancer among women worldwide is breast cancer. There is always need of advancement when it comes to medical imaging. Early detection of cancer followed by the proper treatment can reduce the risk of deaths. Machine learning can help medical professionals to diagnose the disease with more accuracy. Where deep learning or neural networks is one of the techniques which can be used for the classification of normal and abnormal breast detection. CNN can be used for this detection. Mammograms-MIAS dataset is used for this purpose, having 322 mammograms in which almost 189 images are of normal and 133 are of abnormal breasts. Promising experimental results have been obtained which depict the efficacy of deep learning for breast cancer detection in mammogram images and further encourage the use of deep learning based modern feature extraction and classification methods in various medical imaging applications especially in breast cancer detection. It is an ongoing research and further developments are being made by optimizing the CNN architecture and also employing pre-trained networks which will hopefully lead to higher accuracy measures. Proper segmentation is mandatory for efficient feature extraction and classification.

Shared spectrum usage is inevitable due to the ongoing increase in wireless services and bandwidth requirements. Spectrum monitoring is a key enabler for efficient spectrum sharing by multiple radio access technologies (RATs). In this paper, we present signal classification using deep neural networks to identify various radio technologies and their associated interferences. We use Convolutional Neural Networks (CNN) to perform signal classification and employ six well-known CNN models to train for ten signal classes. These classes include LTE, Radar, WiFi and FBMC (Filter Bank Multicarrier) and their interference combinations, which include, LTE + Radar, LTE + WiFi, FBMC + Radar, FBMC + WiFi, WiFi + Radar and Noise. The CNN models include, AlexNet, VGG16, ResNet18, SqueezeNet, InceptionV3 and ResNet50. The radio signal data sets for training and testing of CNN-based classifiers are acquired using a USRP-based experimental setup. Extensive measurements of these radio technologies (LTE, WiFi, Radar and FBMC) are done over different locations and times to generate a robust dataset. We propose a novel (spectrogram) representation called the Quarter-spectrogram (Q-spectrogram) that squeezes temporal and frequency information for input to CNN models. While considering classification accuracy, model complexity and prediction time for a single input Q-spectrogram (image), ResNet18 (CNN model) gives the best overall performance with 98% classification accuracy. While SqueezeNet (CNN model) offers the lowest model complexity which makes it very suitable for resource-constrained radio monitoring devices and also offers the least prediction time of 110 msec. Moreover, we also propose a simple WiFi classification scheme that buffers several WiFi Q-spectrograms and then makes a decision about WiFi’s presence and also gives a quantified measure of WiFi traffic density.

Face is one of the most widely used biometrics for human identity authentication. Facial recognition has remained an interesting and active research area in the past several decades due to its ever growing applications in biometric authentication, content based data retrieval, video surveillance, access control and social media. Unlike other biometric systems, facial recognition based systems work independently without involving the individual, due to which it does not add unnecessary delay. Its ability of recognizing multiple persons at a time further adds to its speed. There are many face recognition methods based on traditional machine learning that are available in the literature. Improvements are being made with the constant developments in computer vision and machine learning. However, most of the traditional methods lack robustness against varying illumination, facial expression, scale, occlusions and pose. With the advent of big data and graphical computing, deep learning has impressively advanced the traditional computer vision systems over the past decade. In this paper, we present a convolutional neural network based face recognition system which detects faces in an input image using Viola Jones face detector and automatically extracts facial features from detected faces using a pre-trained CNN for recognition. A large database of facial images of subjects is created, which is augmented in order to increase the number of images per subject and to incorporate different illumination and noise conditions for optimal training of the convolutional neural network. Moreover, an optimal pretrained CNN model along with a set of hyperparameters is experimentally selected for deep face recognition. Promising experimental results, with an overall accuracy of 98.76 ^% , are obtained which depict the effectiveness of deep face recognition in automated biometric authentication systems.

Deep learning is revolutionizing the already rapidly developing field of computer vision. The convolutional neural network (CNN) is a state-of-the-art deep learning tool that learns high level features directly from a huge dataset of labeled images. In document image processing, ink analysis allows for determination of ink age and forgery and identification of pen or writer. The spectral information of inks in hyperspectral document images provides valuable information about the underlying material and thus helps in identification and discrimination of inks based on their unique spectral signatures even if they have the same color. Ink mismatch detection is a key step in document forgery detection. Although various ink mismatch detection techniques are available in the recent literature, there is a constant need for development of more accurate and effective methods to empower automated document forgery detection. A state-of-the-art deep learning method for ink mismatch detection in hyperspectral document images is proposed. The spectral responses of ink pixels are extracted from a hyperspectral document image, reshaped to a CNN-friendly image format and fed to the CNN for classification. The proposed method effectively identifies different ink types in a hyperspectral document image for forgery detection and achieves an overall accuracy of 98.2% for blue and 88% for black inks, which is the highest accuracy among the latest techniques of ink mismatch detection on the UWA Writing Ink Hyperspectral Images (WIHSI) database and differentiates between the highest number of inks mixed in unbalanced proportions in a hyperspectral document image. Furthermore, a detailed discussion on selection of appropriate CNN architecture and classification results are presented in this paper along with comparison with the former methods of ink mismatch detection. This research opens a new window for research on automated forgery detection in hyperspectral document images using deep learning.

Vegetation includes a significant class of terrestrial ecosystem. Information on tree species categorization is important for environmentalists, foresters, agriculturist, urban managers, landscape architects and biodiversity conservationist. The traditional methods of measuring and identifying tree species (i.e., through field-based survey) are time taking, laborious and costly. Remote sensing data provides an opportunity to identify and classify vegetation species over a large spatial extent. Hyperspectral remote sensing can detect the sublet spectral details among species classes and thus make it possible to differentiate vegetation species based on these subtle variations. This research examines the thermal infrared (2.5 to 14.0 μm) hyperspectral emissivity spectra (comprised of 3456 spectral bands) for the classification of thirteen different plant species. The use of thermal infrared hyperspectral emissivity spectra for the identification of vegetation species is very rare. Three different machine learning methods including support vector machine (SVM), artificial neural network (ANN) and convolutional neural network (CNN) are used to classify thirteen vegetation species and their performance is assessed based on their overall accuracy. The accuracy obtained by CNN, ANN and SVM is 99%, 94% and 91%, respectively. Each classifier was also tested for the advantage associated with increase in training samples or object segmentation size. Increase in the training samples improved the performance of SVM. In a nutshell, all comparative machine learning methods provide very high classification accuracy and CNN outperformed the comparative methods. This study concludes that thermal infrared hyperspectral emissivity data has the potential to discern vegetation species using state of the art machine learning and deep learning methods.