Sharif Digital Repository

In this thesis, change detection in hyperspectral images is investigated. In this process, two hyperspectral images captured from the same scene but in different time instances are given and we intend to detect the occurred changes in the scene. A specific change detection algorithm contains four different steps; namely, preprocessing, selection of the criterion, postprocessing, and decision making. Dimension reduction as a critical process is also deeply investigated to be performed before classification (for decision making purposes.) Two new methods are proposed in the thesis. The proposed MCRD method is designed for dimension reduction and the MPR method is related to the change... 

Hyperspectral imaging is one of the remote sensing methods that has been widely applied in different applications. A hyperspectral image is composed of a set of pixels showing the spectral signatures in different frequency bands recorded by sensor cells. The process that detects the proportion of pure elements in the combination of pixels is called hyperspectral unmixing. Noisy and incomplete data, high mutual coherence of spectral libraries and different sensor settings are some challenges of the unmixing problem. In this work, we focus on semi-supervised linear hyperspectral unmixing in which a spectral library is given. The resulting linear equation is an underdetermind problem with... 

In this thesis, we propose a new compressed-sensing-based algorithm for unmixing of hyperspectral data, and show that the reconstruction quality could be significantly improved. In addition, we illustrate that by utilizing this approach, we can achieve an approximate estimation of the Point Spread Function (PSF) of the hyperspectral images. In this way, we first assume that the PSF belongs to a specific family of functions, such as Gaussian, then, by sweeping the parameters of the assumed PSF, we obtain the abundance coefficient matrix of the reconstructed image. Now, by choosing the sparsest coefficient matrix as the best one, we estimate the corresponding PSF. Then, we further investigate... 

Hyperspectral unmixing (HU) is a method used to estimate the fractional abundances corresponding to endmembers in each of the mixed pixels in the hyperspectral remote sensing image. In recent times, deep learning has been recognized as an effective technique for hyperspectral image classification. In this thesis, an end-to-end HU method is proposed based on the convolutional neural network (CNN) and multi-layer perceptron (MLP). which consists of two steps: the first stage extracts features from the input data along with the inverse learning of the spectral library matrix in the hyperspectral image where columns represent the pure spectral of endmembers and The second stage is to estimate... 

Breast cancer is one of the most known types of cancer. About every eight women, one woman will suffer from one of the types of malignant tissues during her life. Diagnosing this type of cancer in the early stages is an important matter and can lead to full recovery. Therefore, one of the challenges in this field is the emergence of a fast method with high sensitivity to diagnose this disease in its early stages. Currently, biopsy is the standard method for breast cancer diagnosis. However, there are some drawbacks to this method. For instance, in order to detect the tumor margin, all breast tissue must be removed, which causes all breast tissue, including healthy tissues, to be removed.... 

Fast, non-destructive and reliable methods for food authentication purposes have been deemed important in recent years. The hyperspectral imaging technique (HSI) is a powerful method in this field, allowing the study of different features such as size, color, texture. Comprehensive interpretation is crucial, and utilizing chemometric methods enhances data interpretation. Rice is a vital and strategic food source for nearly half of the world, with Asia, particularly Iran, being a leading producer and exporter. Various types of rice fraud exist, including the mixing of high-quality and low-quality varieties, sold at a high cost. The present project aims to determine the geographical origin and... 

With the expansion of the pharmaceutical market and the increasing likelihood of distributing substandard medicines, it is necessary to develop methods for rapid, timely, and non-destructive analysis. These methods should enable the assessment of qualitative features such as the amount of active substance and the homogeneous distribution of materials at various stages of drug manufacturing. In this regard, numerous studies have been conducted using spectroscopy and hyperspectral imaging, particularly in the visible and near-infrared regions. The challenge here is that active ingredients in medicine and excipients look very similar in this region. They're usually white powders, and the weak... 

Classification of hyperspectral remote sensing images is a challenging problem, because of the small number of labeled pixels, high dimensionality of the data and large number of pixels. In this context, semisupervised learning can improve the classification accuracy by extracting information form the distribution of all the labeled and unlabeled data. Among semi-supervised methods, manifold-based algorithms have been frequently used in recent years. In most of the previous works, manifolds are constructed according to spectral representation of data, while spatial dependency of pixel labels is an important property of the images in remote sensing applications. In this thesis, after... 

These days, food authenticity has become a major challenge because food health directly affects human health. The importance of authenticity is highlighted when we are faced with foods with higher nutritional and economic value. Saffron is an important example of spices because in addition to having food coloring and flavoring properties, it also has numerous health benefits, but it has limited production and high price. Therefore, with the options available and cheaper to be replaced. Thus, among the various spices, cheating in saffron has the fourth place. Hyperspectral Imaging (HSI) has been developed for food safety industrial applications. This technique combines spectroscopy and... 

The use of hyperspectral images to detect food fraud has become popular and it is necessary to develop chemometrics methods for analyzing the data from these images. Additionally, food authenticity has become a major challenge, and the focus of this thesis is on developing multivariate methods in chemometrics to extract useful information from data obtained from food authenticity verification using hyperspectral imaging (HSI). This thesis consists of six chapters. In the first chapter, a brief introduction to the fundamentals of hyperspectral imaging and food authenticity verification is presented. In the second chapter, the data structure of these images and chemometric methods including...