Saptarshi Chakraborty - Academia.edu (original) (raw)

Uploads

Papers by Saptarshi Chakraborty

Research paper thumbnail of A Study on Eigen Faces for Removing Image Blurredness Through Image Fusion

The International journal of Multimedia & Its Applications, 2012

Advances in technology have brought about extensive research in the field of image fusion. Image ... more Advances in technology have brought about extensive research in the field of image fusion. Image fusion is one of the most researched challenges of Face Recognition. Face Recognition (FR) is the process by which the brain and mind understand, interpret and identify or verify human faces Face recognition is nothing but a biometric application by which we can automatically identify and recognize a person from the visual image of that person stored in the database. Image fusion is the perfect combination of relevant information from two or more images into a single fused image. As a result the final output image will carry more information as compare to the input images. Thus the main aim of an image fusion algorithm is to take redundant and complementary information from the source images and to generate an output image with better visual quality. In this paper we have proposed a novel approach of pixel level image fusion using PCA that will remove the image blurredness in two images and reconstruct a new de-blurred fused image. The proposed approach is based on the calculation of Eigen faces with Principal Component Analysis (PCA). Principal Component Analysis (PCA) has been most widely used method for dimensionality reduction and feature extraction.

Research paper thumbnail of SBD-Duo: a dual stage shot boundary detection technique robust to motion and illumination effect

Multimedia Tools and Applications, 2020

In this paper, we propose a novel shot boundary detection technique using gradient and colour inf... more In this paper, we propose a novel shot boundary detection technique using gradient and colour information. The gradient similarity and luminance distortion are calculated to measure the contrast and structural changes of each frame including luminance changes. In the proposed system, the effects of the changes in luminance and contrast-structure are integrated via an adaptive method to extract the possible transitions using an adaptive threshold across the videos. In the verification part, CIEDE2000 colour-difference values of the possible transition frames are compared for declaration of abrupt and gradual transitions. Our system takes effectively less computational time to detect abrupt and gradual transition for a video as compared with contemporary solutions. Our proposed system also gives dominate the performance as compared with latest techniques in terms of F1 score using TRECVid 2001 and 2007 selected dataset. We have performed a series of rigorous experimentation to validate our claims.

Research paper thumbnail of A novel automatic shot boundary detection algorithm: robust to illumination and motion effect

Signal, Image and Video Processing, 2019

Many researches have been done on shot boundary detection, but the performance of shot boundary d... more Many researches have been done on shot boundary detection, but the performance of shot boundary detection approaches is yet to be addressed for the videos having sudden illumination and object/camera motion effects efficiently. In this paper, a novel dual-stage approach for an abrupt transition detection is proposed which is able to withstand under certain illumination and motion effects. Firstly, an adaptive Wiener filter is applied to the lightness component of the frame to retain some important information on both frequencies and LBP-HF is extracted to reduce the illumination effect. From the experimentation, it is also confirmed that the motion effect is also reduced in the first stage. Secondly, Canny edge difference is used to further remove the illumination and motion effects which are not handled in the first stage. TRECVid 2001 and TRECVid 2007 datasets are applied to analyze and validate our proposed algorithm. Experimental results manifest that the proposed system outperforms the state-of-the-art shot boundary detection techniques.

Research paper thumbnail of A novel shot boundary detection system using hybrid optimization technique

Applied Intelligence, 2019

This paper proposes a novel shot boundary detection method which combines the Advantages of Parti... more This paper proposes a novel shot boundary detection method which combines the Advantages of Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) to optimize the weights of the Feed-Forward Neural Network (FNN). To increase the performance of the system, the output of the hybrid technique is again analyzed by forming a Continuity matrix (ϕ). Then an Outlier along with a Continuity matrix is used for extracting a possible set of transition frames. A set of thresholds δ1 and δ2 is selected for classifying abrupt and gradual transitions from the available set of possible transition frames. Experimental results using TRECVid 2001 depicts that PSOGSA outperforms GSA and PSO in-terms of training the feed forward neural network and generating a higher overall F1 score. The proposed system also gives better performance when compared with other latest techniques in-terms of F1 score.

Research paper thumbnail of Application of Image Fusion for Enhancing the Quality of an Image

Computer Science & Information Technology (CS & IT), 2012

Advances in technology have brought about extensive research in the field of image fusion. Image ... more Advances in technology have brought about extensive research in the field of image fusion. Image fusion is one of the most researched challenges of Face Recognition. Face Recognition (FR) is the process by which the brain and mind understand, interpret and identify or verify human faces.. Image fusion is the combination of two or more source images which vary in resolution, instrument modality, or image capture technique into a single composite representation. Thus, the source images are complementary in many ways, with no one input image being an adequate data representation of the scene. Therefore, the goal of an image fusion algorithm is to integrate the redundant and complementary information obtained from the source images in order to form a new image which provides a better description of the scene for human or machine perception. In this paper we have proposed a novel approach of pixel level image fusion using PCA that will remove the image blurredness in two images and reconstruct a new de-blurred fused image. The proposed approach is based on the calculation of Eigen faces with Principal Component Analysis (PCA). Principal Component Analysis (PCA) has been most widely used method for dimensionality reduction and feature extraction.

Research paper thumbnail of A noble technique for detecting anemia through classification of red blood cells in blood smear

International Conference on Recent Advances and Innovations in Engineering (ICRAIE-2014), 2014

Anemia is responsible for various health hazards. Anemia decreases and also alters the shape of r... more Anemia is responsible for various health hazards. Anemia decreases and also alters the shape of red blood cells (RBCs) present in our blood. Different type of RBC shapes account for different type of anemia. Automated blood cell analyzers can detect anemia and provide RBC, WBC and platelet count but anemia type identification, which requires classification of RBCs is carried out manually. The classification of RBCs provides invaluable information to pathologists for diagnosis and treatment of various types of anemia. The manual visual inspection is tedious, time consuming, repetitive and prone to human error. In this paper we have performed the automated classification of RBCs as falling into one of the anemia type. The segmentation and classification of the RBCs are the most important stages. The proposed system identifies RBCs using intensity ratio transformation followed by centroid contour distance for segmentation of RBC. Due to the large RBC shape variations, a shape independent framework for identification and segmentation is required. The proposed method can successfully separate the agglomerates of RBCs in spite of grouping of non-uniform RBC shapes. Two geometric features are used to distinguish between normal and anemic RBCs: Aspect Ratio and Fourier Descriptors. The Euclidean distance measure is used as a criterion to determine the similarity degree between the templates and testing samples. Also the presence of high number of nucleated RBCs (NRBCs) in severe anemic patients gives erroneous WBC count in automated cell-analyzers and requires correction which is carried out manually. This paper also presents the automated NRBC count and provides automatic solution of WBC count correction obtained from automated hematology analyzers.

Research paper thumbnail of An Overview of Face Liveness Detection

International Journal on Information Theory, 2014

Face recognition is a widely used biometric approach. Face recognition technology has developed r... more Face recognition is a widely used biometric approach. Face recognition technology has developed rapidly in recent years and it is more direct, user friendly and convenient compared to other methods. But face recognition systems are vulnerable to spoof attacks made by non-real faces. It is an easy way to spoof face recognition systems by facial pictures such as portrait photographs. A secure system needs Liveness detection in order to guard against such spoofing. In this work, face liveness detection approaches are categorized based on the various types techniques used for liveness detection. This categorization helps understanding different spoof attacks scenarios and their relation to the developed solutions. A review of the latest works regarding face liveness detection works is presented. The main aim is to provide a simple path for the future development of novel and more secured face liveness detection approach.

Research paper thumbnail of A Study on Eigen Faces for Removing Image Blurredness Through Image Fusion

The International journal of Multimedia & Its Applications, 2012

Advances in technology have brought about extensive research in the field of image fusion. Image ... more Advances in technology have brought about extensive research in the field of image fusion. Image fusion is one of the most researched challenges of Face Recognition. Face Recognition (FR) is the process by which the brain and mind understand, interpret and identify or verify human faces Face recognition is nothing but a biometric application by which we can automatically identify and recognize a person from the visual image of that person stored in the database. Image fusion is the perfect combination of relevant information from two or more images into a single fused image. As a result the final output image will carry more information as compare to the input images. Thus the main aim of an image fusion algorithm is to take redundant and complementary information from the source images and to generate an output image with better visual quality. In this paper we have proposed a novel approach of pixel level image fusion using PCA that will remove the image blurredness in two images and reconstruct a new de-blurred fused image. The proposed approach is based on the calculation of Eigen faces with Principal Component Analysis (PCA). Principal Component Analysis (PCA) has been most widely used method for dimensionality reduction and feature extraction.

Research paper thumbnail of SBD-Duo: a dual stage shot boundary detection technique robust to motion and illumination effect

Multimedia Tools and Applications, 2020

In this paper, we propose a novel shot boundary detection technique using gradient and colour inf... more In this paper, we propose a novel shot boundary detection technique using gradient and colour information. The gradient similarity and luminance distortion are calculated to measure the contrast and structural changes of each frame including luminance changes. In the proposed system, the effects of the changes in luminance and contrast-structure are integrated via an adaptive method to extract the possible transitions using an adaptive threshold across the videos. In the verification part, CIEDE2000 colour-difference values of the possible transition frames are compared for declaration of abrupt and gradual transitions. Our system takes effectively less computational time to detect abrupt and gradual transition for a video as compared with contemporary solutions. Our proposed system also gives dominate the performance as compared with latest techniques in terms of F1 score using TRECVid 2001 and 2007 selected dataset. We have performed a series of rigorous experimentation to validate our claims.

Research paper thumbnail of A novel automatic shot boundary detection algorithm: robust to illumination and motion effect

Signal, Image and Video Processing, 2019

Many researches have been done on shot boundary detection, but the performance of shot boundary d... more Many researches have been done on shot boundary detection, but the performance of shot boundary detection approaches is yet to be addressed for the videos having sudden illumination and object/camera motion effects efficiently. In this paper, a novel dual-stage approach for an abrupt transition detection is proposed which is able to withstand under certain illumination and motion effects. Firstly, an adaptive Wiener filter is applied to the lightness component of the frame to retain some important information on both frequencies and LBP-HF is extracted to reduce the illumination effect. From the experimentation, it is also confirmed that the motion effect is also reduced in the first stage. Secondly, Canny edge difference is used to further remove the illumination and motion effects which are not handled in the first stage. TRECVid 2001 and TRECVid 2007 datasets are applied to analyze and validate our proposed algorithm. Experimental results manifest that the proposed system outperforms the state-of-the-art shot boundary detection techniques.

Research paper thumbnail of A novel shot boundary detection system using hybrid optimization technique

Applied Intelligence, 2019

This paper proposes a novel shot boundary detection method which combines the Advantages of Parti... more This paper proposes a novel shot boundary detection method which combines the Advantages of Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) to optimize the weights of the Feed-Forward Neural Network (FNN). To increase the performance of the system, the output of the hybrid technique is again analyzed by forming a Continuity matrix (ϕ). Then an Outlier along with a Continuity matrix is used for extracting a possible set of transition frames. A set of thresholds δ1 and δ2 is selected for classifying abrupt and gradual transitions from the available set of possible transition frames. Experimental results using TRECVid 2001 depicts that PSOGSA outperforms GSA and PSO in-terms of training the feed forward neural network and generating a higher overall F1 score. The proposed system also gives better performance when compared with other latest techniques in-terms of F1 score.

Research paper thumbnail of Application of Image Fusion for Enhancing the Quality of an Image

Computer Science & Information Technology (CS & IT), 2012

Advances in technology have brought about extensive research in the field of image fusion. Image ... more Advances in technology have brought about extensive research in the field of image fusion. Image fusion is one of the most researched challenges of Face Recognition. Face Recognition (FR) is the process by which the brain and mind understand, interpret and identify or verify human faces.. Image fusion is the combination of two or more source images which vary in resolution, instrument modality, or image capture technique into a single composite representation. Thus, the source images are complementary in many ways, with no one input image being an adequate data representation of the scene. Therefore, the goal of an image fusion algorithm is to integrate the redundant and complementary information obtained from the source images in order to form a new image which provides a better description of the scene for human or machine perception. In this paper we have proposed a novel approach of pixel level image fusion using PCA that will remove the image blurredness in two images and reconstruct a new de-blurred fused image. The proposed approach is based on the calculation of Eigen faces with Principal Component Analysis (PCA). Principal Component Analysis (PCA) has been most widely used method for dimensionality reduction and feature extraction.

Research paper thumbnail of A noble technique for detecting anemia through classification of red blood cells in blood smear

International Conference on Recent Advances and Innovations in Engineering (ICRAIE-2014), 2014

Anemia is responsible for various health hazards. Anemia decreases and also alters the shape of r... more Anemia is responsible for various health hazards. Anemia decreases and also alters the shape of red blood cells (RBCs) present in our blood. Different type of RBC shapes account for different type of anemia. Automated blood cell analyzers can detect anemia and provide RBC, WBC and platelet count but anemia type identification, which requires classification of RBCs is carried out manually. The classification of RBCs provides invaluable information to pathologists for diagnosis and treatment of various types of anemia. The manual visual inspection is tedious, time consuming, repetitive and prone to human error. In this paper we have performed the automated classification of RBCs as falling into one of the anemia type. The segmentation and classification of the RBCs are the most important stages. The proposed system identifies RBCs using intensity ratio transformation followed by centroid contour distance for segmentation of RBC. Due to the large RBC shape variations, a shape independent framework for identification and segmentation is required. The proposed method can successfully separate the agglomerates of RBCs in spite of grouping of non-uniform RBC shapes. Two geometric features are used to distinguish between normal and anemic RBCs: Aspect Ratio and Fourier Descriptors. The Euclidean distance measure is used as a criterion to determine the similarity degree between the templates and testing samples. Also the presence of high number of nucleated RBCs (NRBCs) in severe anemic patients gives erroneous WBC count in automated cell-analyzers and requires correction which is carried out manually. This paper also presents the automated NRBC count and provides automatic solution of WBC count correction obtained from automated hematology analyzers.

Research paper thumbnail of An Overview of Face Liveness Detection

International Journal on Information Theory, 2014

Face recognition is a widely used biometric approach. Face recognition technology has developed r... more Face recognition is a widely used biometric approach. Face recognition technology has developed rapidly in recent years and it is more direct, user friendly and convenient compared to other methods. But face recognition systems are vulnerable to spoof attacks made by non-real faces. It is an easy way to spoof face recognition systems by facial pictures such as portrait photographs. A secure system needs Liveness detection in order to guard against such spoofing. In this work, face liveness detection approaches are categorized based on the various types techniques used for liveness detection. This categorization helps understanding different spoof attacks scenarios and their relation to the developed solutions. A review of the latest works regarding face liveness detection works is presented. The main aim is to provide a simple path for the future development of novel and more secured face liveness detection approach.