H. Hassanpour

• Ph.D.
• Head of Faculty at University of Shahrood

Face recognition methods achieve their highest accuracy when faces are captured in the frontal view. However, the accuracy of these methods decreases when the angle of a person’s face changes relative to the camera. The problem of pose variation in face recognition can be addressed in either the feature space or the image space. While generating a...

Face super-resolution, commonly referred to as face hallucination, is a specific domain of super-resolution that focuses on generating high-resolution face images from their corresponding low-resolution versions. Face hallucination has received evident advances and significant attention with the expansion of deep learning methods. However, the stat...

Face recognition is one of the most important research topics in computer vision. Indeed, the face is an important means of communication with humans and it is highly needed for daily contact. Face recognition technology is applied in many biometric applications such as security, video surveillance, access control systems, and forensics. In this te...

With the expansion of social networks, their utilization in digital advertising has become a key factor in shaping public opinion and driving advertising campaigns —coordinated and targeted series of interactions between users on a specific topic. Properly directing these campaigns can focus many individuals on a particular subject, thereby creatin...

Wireless capsule endoscopy (WCE) is a technology for filming the gastrointestinal (GI) tract to find abnormalities such as tumors, polyps, and bleeding. This paper proposes a new method based on hand-crafted features to detect polyps in WCE frames. A polyp has a convex surface containing pixel values with a specified Gaussian distribution. If a pol...

The small amount of training data for many state-of-the-art deep learning-based Face Recognition (FR) systems causes a marked deterioration in their performance. Although a considerable amount of research has addressed this issue by inventing new data augmentation techniques, using either input space transformations or Generative Adversarial Networ...

The small amount of training data for many state-of-the-art deep learning-based Face Recognition (FR) systems causes a marked deterioration in their performance. Although a considerable amount of research has addressed this issue by inventing new data augmentation techniques, using either input space transformations or Generative Adversarial Networ...

Text clustering is used in various applications of text analysis. In the clustering process, the employed document representation method has a significant impact on the results. Some popular document representation methods cannot effectively maintain the proximity information of the documents or suffer from low interpretability. Although the concep...

Object detection is responsible for categorizing and locating object in an image or video which has been widely used during recent years. This study represents a model based on Feature Pyramid Network (FPN) and new layers of capsule attention, the represented model is based on anchor and has had 79.5 % MAP in the experiments. On one hand, this impr...

In this paper, a computer-aided method is proposed for abnormality detection in Wireless Capsule Endoscopy (WCE) video frames. Common abnormalities in WCE images include ulcers, bleeding, Angiodysplasia, Lymphoid Hyperplasia, and polyp. In this paper, deep features and Hand-crafted features are combined to detect these abnormalities in WCE images....

In this paper, a computer-aided method is proposed for abnormality detection Wireless Capsule Endoscopy (WCE) video frames. Common abnormalities in WCE images include ulcers, bleeding, Angiodysplasia, Lymphoid Hyperplasia, and polyp. In this paper, deep features and Hand-crafted features are combined to detect these abnormalities in WCE images. The...

Event detection using social media analysis has attracted researchers’ attention. Prediction of events especially in the management of social crises can be of particular significance. In this study, events are predicted through analyzing Twitter messages and examining the changes in the rate of Tweets in a specified subject. In the proposed method,...

Image Quality Assessment (IQA) plays a central role in many visual processing algorithms and systems. Most of the existing IQA methods try to detect the image distortions’ type and then evaluate its severity. But each image distortion type has its own characteristics, which can harden up the process of quality evaluation. Here, we propose a novel f...

The performance of video surveillance systems with network cameras depends on their accuracy in people re-identification. Body occlusion, crowded background, and variations in scene illumination and pose are challenging issues in people re-identification. In this paper, a technique is proposed to improve the performance of re-identification approac...

In this paper, a novel method is proposed to detect common abnormalities in Wireless Capsule Endoscopy (WCE) video frames including Lymphoid Hyperplasia, ulcer, and angiodysplasia lesions. Inspecting WCE video frames to detect abnormality is a tedious task for physicians. One important step in the proposed approach is to extract the region of inter...

Face recognition is one of the most common authentication methods. Although much research has been conducted in this area, there are still many challenging issues to be addressed on face recognition, such as a large number of images in a dataset, with only one sample per person. The goal of this paper is to provide a robust face recognition method...

In this paper, an expanded multilayer perceptron (EMLP) neural network is proposed to automatically segment angiodysplasia regions in wireless capsule endoscopy (WCE) images The main idea is to minimize the distance between the input image and the corresponding binary ground truth, i.e., the mask image. After the training phase, when a test image i...

Time-Frequency Signal Analysis and Processing (TFSAP) is a collection of theory and algorithms used for analysis and processing of nonstationary signals, as found in a wide range of applications including telecommunications, radar, and biomedical engineering. This book brings together the main knowledge of TFSAP, from theory to applications, in a u...

Motion blur is a common artifact in image processing, specifically in e-health services, which is caused by the motion of a camera or scene. In linear motion cases, the blur kernel, i.e., the function that simulates the linear motion blur process, depends on the length and direction of blur, called linear motion blur parameters. The estimation of b...

With the huge expansion of user generated content on social networks, event detection has emerged as a major challenge and source of knowledge discovery. This knowledge is employed in different applications such as recommender systems, crisis management systems, and decision support systems. Dynamicity, overlapping, and evolutionary behavior are th...

Vehicle visual tracking is a challenging issue in intelligent transportation systems. The tracking gets more challenging when vehicles change direction at intersections. Undetermined motion flows, occlusion, and congestion are the potential issues of vehicle tracking at intersections. In this study, a new method for tracking multiple vehicles from...

In recent years, image scene classification based on low/high-level features has been considered as one of the most important and challenging problems faced in image processing research. The high-level features based on semantic concepts present a more accurate and closer model to the human perception of the image scene content. This paper presents...

Sesame produces prominent oil whose high-quality emanates from its satisfying combination of fatty acids and antioxidants. Oleic, linoleic, palmitic and stearic acids are the four main fatty acids of sesame oil that are presently measured in laboratories using time-consuming and expensive methods that mainly destruct genetic seeds. The aim of this...

Image processing has many applications in different fields of agriculture. The present study aimed to use image processing techniques and artificial neural networks (ANN) to estimate oil and protein contents of sesame genotypes without the use of time‐consuming and costly laboratory methods. The proposed method accurately estimates the parameters i...

Feature selection can be significantly decisive when analyzing high dimensional data, especially with a small number of samples. Feature extraction methods do not have decent performance in these conditions. With small sample sets and high dimensional data, exploring a large search space and learning from insufficient samples becomes extremely hard...

Grid impedance is an important parameter in most power system applications such as power quality analysis of smart grids. In this study, a new time–frequency distribution is employed for grid-impedance estimation in high-frequency range using a single rectangular pulse injection. There is no compatibility level for harmonics within the frequency ra...

Blind image deblurring, i.e., reconstructing a sharp version of a blurred image, is generally an ill-posed problem, as both the blur kernel and the sharp image are unknown. To solve such problem, one must use effective image and blur kernel priors. In this paper, a blind image deblurring method is proposed, which uses an effective image prior based...

An image may suffer from some degradation such as blurriness. This degradation affects the image contrast. There are various approaches to improve the contrast of the images. Among these approaches, un-sharp masking is a popular method due to its simplicity in implementation and computation. In the un-sharp masking method, the details of the input...

In recurrent neural networks such as the long short-term memory (LSTM), the sigmoid and hyperbolic tangent functions are commonly used as activation functions in the network units. Other activation functions developed for the neural networks are not thoroughly analyzed in LSTMs. While many researchers have adopted LSTM networks for classification t...

The accuracy of multi-class classification problems is improving at a good pace. However, improving the accuracy often leads to slowing down the processing speed. Since employing a large number of classifiers or a combination of them is a time-consuming process, the sluggish behavior is more evident in multiple classifier systems. In this paper, a...

Non-alcoholic fatty liver disease (NAFLD) is one of the most common diseases in the world. Recently the FibroScan device is used as a noninvasive, yet costly method to measure the liver’s elasticity as a NAFLD indicator. Other than the cost, the diagnosis is not widely accessible to all patients. On the other hand, early detection of the disease ca...

Abstract Impulsive noise is one of the imposed defectives degrades the quality of images. Performance of many image processing applications directly depends on the quality of the input image. Hence, it is necessary to de-noise the degraded images without losing their valuable information such as edges. In this paper we propose a method to remove im...

One of the most efficient descriptions of image structure, which has been widely used in image quality assessment (IQA) studies, is the three-components model. Based on this model, the major structural components of an image are edges, textures and flat regions. We found that this model is basically derived from the abstract concept of image region...

Although contrast is a major issue in overall quality assessment of an image, existing contrast evaluators with a reasonable performance are currently scarce. Here, we propose a learning-based blind/no-reference (NR) image quality assessment (IQA) model, dubbed Histogram Eigen-Feature based Contrast Score (HEFCS) for evaluating image contrast. This...

Grid impedance estimation is used in many power system applications such as grid connected renewable energy systems and power quality analysis of smart grids. The grid impedance estimation techniques based on signal injection uses Ohm’s law for the estimation. In these methods, one or several signal(s) is (are) injected to Point of Common Coupling...

This paper presents a novel image zooming method using a neural network. The main issue in any image zooming algorithms is to preserve the main structure of the image. The proposed method uses a multi-layer perceptron for image zooming. For zooming an image, the neural network is initially trained using the same image down-sampled by a factor of 2....

Recommender systems have been developed to assist users in retrieving relevant resources. Collaborative and content-based filtering are two basic approaches that are used in recommender systems. The former employs the feedback of users with similar interests, while the latter is based on the feature of the selected resources by each user. Recommend...

In find-grained recognition, the main category of object is known and the goal is to determine the subcategory or find-grained category. Vehicle make and model recognition (VMMR) is a find-grained classification. It’s a hard classification problem, due to the large number of classes, substantial inner-class and small inter-class distance. In this p...

Blocking is an annoying effect in image compression using JPEG especially at low bit-rates. In this paper, a two-phase method is proposed for reducing JPEG blocking effects. In the first phase, the image is adaptively down-sampled via assessing the DCT coefficients of the image blocks. Since the blocks have a fixed size, independent to the size of...

The existing image quality assessment (IQA) techniques try to estimate image distortions regardless of their destructive effects on image contents. Analyzing the subjective scores of image quality databases shows that the worst opinions belong to distortions which make the images non-recognizable. In this paper, we investigate the effects of image...

Supervised clustering is a data mining technique that assigns a set of data to predefined classes by analyzing dataset attributes. It is considered as an important technique for information retrieval, management, and mining in information systems. Since customer satisfaction is the main goal of organizations in modern society, to meet the requireme...

Super-resolution (SR) is a technique that produces a high resolution (HR) image via employing a number of low resolution (LR) images from the same scene. One of the degradations that attenuates performance of the SR is the blurriness of the input LR images. In many previous works in the SR, the blurriness of the LR images is assumed to be due to th...

In this paper, we propose a new no-reference image quality assessment for JPEG compressed images. In contrast to the most existing approaches, the proposed method considers the compression processes for assessing the blocking effects in the JPEG compressed images. These images have blocking artifacts in high compression ratio. The quantization of t...

Orientation of human body is an important feature that can be used for behavioral analysis in surveillance systems. This cue contains useful information such as the direction of movement or attention. Difficulties such as low quality images, cluttered background and partial occlusion harden orientation estimation. In this paper, we propose a novel...

Vehicle make and model recognition (VMMR) has become an important part of intelligent transportation systems. VMMR can be useful when license plate recognition is not feasible or fake number plates are used. VMMR is a hard, fine-grained classification problem, due to the large number of classes, substantial inner-class and small inter-class distanc...

In the last decade, many researches have been done on fine-grained recognition. The main category of the object is known in this problem and the goal is to determine the subcategory or fine-grained category. Vehicle Make and Model Recognition (VMMR) is a hard fine-grained classification problem, due to the large number of classes, substantial inner...

Technical limitations in image capturing usually impose defect, such as contrast degradation. There are different approaches to improve the contrast of an image. Among the exiting approaches, un-sharp masking is a popular method due to its simplicity in implementation and computation. There is an important parameter in un-sharp masking, named gain...

Recommender systems have been developed to overcome the information overload problem by retrieving the most relevant resources. Constructing an appropriate model to estimate the user interests is the major task of recommender systems. The profile matching and latent factors are two main approaches for user modeling. Although a notion of timestamps...

Local motion deblurring is a highly challenging problem as both the blurred region and the blur kernel are unknown. Most existing methods for local deblurring require a specialized hardware, an alpha matte, or user annotation of the blurred region. In this paper, an automatic method is proposed for local motion deblurring in which a segmentation st...

Fine-grained recognition is a challenge that the computer vision community faces nowadays. The main category of the object is known in this problem and the goal is to determine the subcategory or fine-grained category. Vehicle make and model recognition (VMMR) is a hard fine-grained classification problem, due to the large number of classes, substa...

After vehicle detection and vehicle type recognition, it is vehicle make and model recognition (VMMR) that has attracted researchers attention in the last decade. This problem is known as a hard classification problem due to the large number of classes and small inter-class distance. The present paper proposes a new approach for VMMR. The proposed...

Digital images may contain undesired blurred regions. Automatic detection of such regions and estimation of the amount of blurriness in a given image are important issues in many computer vision applications. This paper presents a simple and effective method to automatically detect blurred regions. The proposed method consists of two main parts. Fi...

The image content detectability and image structure preservation are closely related concepts with undeniable role in image quality assessment. However, the most attention of image quality studies has been paid to image structure evaluation, few of them focused on image content detectability. Examining the image structure was firstly introduced and...

Measuring image blurriness is an important issue in image-quality assessment. The blurriness affects the image quality by degrading the image’s high frequency details in the form of some uniform redundancies in neighboring pixels. Indeed, the blurriness is accompanied with two destructions: corrupted high frequency details, and degraded image struc...

In this paper, a signal processing method is proposed to estimate low and high frequency impedances of power systems using several short-term low power signal injections for a frequency range of 0-150 kHz. This frequency range is very important to be considered to analyze power quality issues of smart grids. The impedance estimation is used in many...

Microarray technology is a powerful genomic tool for simultaneously studying and analyzing the behavior of thousands of genes. The analysis of images obtained from this technology plays a critical role in the detection and treatment of diseases. The aim of the current study is to develop an automated system for analyzing data from microarray images...

In this paper, a method is proposed for passive grid impedance estimation using several short-term low power signal injections. Impedance estimation is used in many applications such as designing filters and stable inverters. In impedance estimation techniques with signal injection, a voltage signal is applied to grid and the division of voltage to...

After vehicle detection and vehicle type recognition, it is vehicle make and model recognition (VMMR) that has attracted researchers attention in the last decade. This problem is known as a hard classification problem due to the large number of classes and small inner-class distance. This paper is proposed a new method for recognition of make and m...

Image deconvolution is an ill-posed problem that requires a regularization term to solve. The most common forms of image priors used as the regularization term in image deconvolution tend to produce smoothed (slightly blurry) images, hence don’t well reconstruct image details. In this paper, a new image prior is introduced. This prior is used as a...

A microarray image is used as an accurate method for diagnosis of cancerous diseases. The aim of this research is to provide an approach for detection of breast cancer type. First, raw data is extracted from microarray images. Determining the exact location of each gene is carried out using image processing techniques. Then, by the sum of the pixel...

Blur is a type of distortion that may happen in digital images. Blur estimation is an important issue in image processing applications such as image deblurring and depth estimation. Several blur metrics exist in the literature, but they are mostly sensitive to the presence of noise. In this paper, a simple yet accurate no-reference blur metric with...

AVO (amplitude variation with offset) analysis is an effective technique to detect hydrocarbon reservoirs especially gas reservoirs. Based on the AVO theory, fluid content of formation cause changes to amplitude versus offset. Unlike common works which AVO analysis is performed in time domain, we want to use AVO in time-frequency domain based on th...

Geological events such as thin beds and channels cannot be easily revealed on seismic sections due to the interference of reflections from the top and bottom of the layer. Buried channel is one of the hydrocarbon traps, which is important in oil and gas exploration. Spectral decomposition can be used to indicate subtle changes in channel thickness....

Gender classification is one of the most challenging problems in computer vision. Facial gender detection of neonates and children is also known as a highly demanding issue for human observers. This study proposes a novel gender classification method using frontal facial images of people. The proposed approach employs principal component analysis (...

In this paper, we propose a method for recognizing English characters in different fonts. The proposed method based on neural network is resistant to font variant.When the samples in new fonts are added to the data base, the accuracy of existing methods rapidly decreases and they are not resistant to font variant but the accuracy of proposed method...

This paper proposes three enhancements to design a qualified active noise control (ANC) system. In common practical ANC systems, an online secondary path modeling method is required to ensure convergence of the system. Existing methods use continues injection of white noise to model the secondary path. As a first novelty, a new online secondary pat...

Medical imaging plays an important role in monitoring the patient's health condition and providing an effective treatment. However, the existence of several objects overlapping in an image and the close proximity of adjacent pixels values in medical images make the diagnostic process a difficult task. To cope with such problems, this paper presents...

One of the most suitable biometric for identifying individuals is finger veins. In this paper we have proposed a new algorithm for finger vein recognition with a high accuracy level. First we extract veins from finger vein images by using entropy based thresholding. The method extracts veins well, but the images are very noisy. It means that the ex...

This paper proposes a new hybrid method based on Homomorphic filtering and anisotropic diffusion equations for image denoising. In this method, the Homomorphic filtering extracts the reflection and illumination components of a noisy image. Then a suitable image denoising method based on anisotropic diffusion is applied to each components with its s...

In many signal processing applications, it is often needed to segment signals into small epochs with similar characteristics such as amplitude and/or frequency that are particularly meaningful to clinicians and for assessment by neurophysiologists. This paper presents a novel adaptive segmentation method based on the time-varying autoregressive (TV...

It is often needed to label electroencephalogram(EEG) signals by segments of similar characteristics that are particularly meaningful to clinicians and for assessment by neurophysiologists. Within each segment, the signals are considered statistically stationary, usually with similar characteristics such as amplitude and/or frequency. In order to d...

In numerous signal processing applications, non-stationary signals should be segmented to piece-wise stationary epochs before being further analyzed. In this article, an enhanced segmentation method based on fractal dimension (FD) and evolutionary algorithms (EAs) for non-stationary signals, like electroencephalogram (EEG), magnetoencephalogram (ME...

Natural fractures study is a complicated and much effective field in oil extraction industry. There have been numerous studies on detection of natural fractures. Moreover, each of these studies is associated with certain shortcoming which negatively affects the usability of different engineering applications in the field. In this study we have trie...

In this paper, a new approach is presented for improving image quality. It provides a new outlook on how to apply the enhancment methods on images. Image enhancement techniques may deal with the illumination, resolution, or distribution of pixels values. Issues such as the illumination of the scene and reflectance of objects affect on image capture...

In this paper, a new approach is presented for improving image quality. It provides a new outlook on how to apply the enhancment methods on images. Image enhancement techniques may deal with the illumination, resolution, or distribution of pixels values. Issues such as the illumination of the scene and reflectance of objects affect on image capture...

Segmentation is one of the most complicated procedures in the image processing that has important role in the image analysis. In this paper, an improved pixon-based method for image segmentation is proposed. In proposed algorithm, complex partial differential equations (PDEs) is used as a kernel function to make pixonal image. Using this kernel fun...

Time-domain based signal enhancement is a widely used and extensively studied areawhichits effectiveness in noise reduction is clear for researchers. The presented chapter is dealing with a novel field of time-domain speech enhancement approaches which are inventively based on an optimized Singular Vector denoising schema. There are plenty of signa...

In this paper we propose a light weight semi-distributed IDS architecture for intrusion detection in mobile ad-hoc network. We consider three modes for nodes in this network as normal, attack-presented, and suspicious which the process of detection is based on them. Suspicious mode is a rough detecting situation which may occur in both normal or at...

Conventional procedures are inadequate for optimizing the concentrations of nutrients to increase the sugar yield. In this study, an artificial neural network (ANN) was used to optimize the Ca, Mg, N, K and Na content of the storage root to increase sugar yield (Y) by increasing both sugar content (SC) and root yield (T). Data from three field expe...

Active Noise Control (ANC) systems are increasingly used to reduce environmental noises. A hybrid ANC system is a combination of feedforward and feedback structures in which the anti-noise signal is generated using both structures. Employing the advantages of feedforward and feedback structures enables a hybrid structure to have a high performance...

Existing meta-search engines return web search results based on the page relevancy to the query, their popularity and content. It is necessary to provide a meta-search engine capable of ranking results considering the user’s field of interest. Social networks can be useful to find the users’ tendencies, favorites, skills, and interests. In this pap...

The aim of this research is to analyze aggregate network traffic for anomaly detection. The accurate and rapid detection of network traffic anomaly is crucial to enhance the effective operation of a network. It is often difficult to detect the time when the faults occur in a network. In this paper, a new algorithm is presented to monitor the aggreg...