Papers by Anterpreet bedi
2017 International Conference on Computing, Communication and Automation (ICCCA)
Ultrasound imaging is an indisputable image modality for clinical purposes. Unfortunately, it com... more Ultrasound imaging is an indisputable image modality for clinical purposes. Unfortunately, it comes with the inherent speckle noise which results in the degradation of the texture information in these images, thus making the diagnosis harder. This paper proposes a new approach for despeckling the ultrasound images combining the multiscale anisotropic diffusion model with the non-subsampled shearlet transform (NSST). The method involves the decomposition of images using the Non-Subsampled Laplacian pyramid, resulting in a low and high frequency sub images. Modified anisotropic diffusion method is further applied to the coarser component, whereas, the finer component is subjected to shearlet function, resulting in noisy coefficients, which are further subjected to thresholding. This multidimensional and multidirectional method enhances the visual characteristics of the ultrasound images with not just the removal of speckle noise, but also with the preservation of more edges, thus enhancing the images effectively. The performance of the proposed algorithm is assessed for real ultrasound images. Results show that the method excels over the earlier proposed techniques in terms of preservation of edges and structural similarities. Moreover, when analysed qualitatively, it is observed that there is a substantial removal of speckle noise, thus making the diagnosis easier for the radiologists.
Multimedia anomaly datasets play a crucial role in automated surveillance. They have a wide range... more Multimedia anomaly datasets play a crucial role in automated surveillance. They have a wide range of applications expanding from outlier objects/ situation detection to the detection of life-threatening events. For more than 1.5 decades, this field has attracted a lot of research attention, and as a result, more and more datasets dedicated to anomalous actions and object detection have been developed. Tapping these public anomaly datasets enable researchers to generate and compare various anomaly detection frameworks with the same input data. This paper presents a comprehensive survey on a variety of video, audio, as well as audiovisual datasets based on the application of anomaly detection. This survey aims to address the lack of a comprehensive comparison and analysis of multimedia public datasets based on anomaly detection. Also, it can assist researchers in selecting the best available dataset for benchmarking frameworks. Additionally, we discuss gaps in the existing dataset and insights for future direction towards developing multimodal anomaly detection datasets.
2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC), 2018
Liver diseases are one of the significant public health issues in present scenario. Liver cirrhos... more Liver diseases are one of the significant public health issues in present scenario. Liver cirrhosis is one of the leading causes of deaths due to liver related diseases. In this work, classification of normal and cirrhotic liver is done using texture analysis. Various texture features are extracted for classification. Out of all the extracted features, seven best features are identified using fisher discriminant ratio. Further, weighted fisher discriminant ratio algorithm is designed using the selected features, such that maximum accuracy and sensitivity is achieved.
2020 4th International Conference on Electronics, Communication and Aerospace Technology (ICECA), 2020
Angiography is a way towards picturing the retina of eye. Unfortunately, a specialist has to spen... more Angiography is a way towards picturing the retina of eye. Unfortunately, a specialist has to spend a lot of time to examine the picture. Segmentation is one of the processes to identify eye problems and decrease the specialist time. This paper proposes the performance comparison of vessel segmentation methodologies. Firstly, the fundus image is taken from the openly accessible datahise and pre-processing is done to adjust the contrast of input image so that the vessels are segmented Segmentation is the second step of algorithm that segments the image and post processing is done to enhance the segmented binary image. The methods are involved with ISODATA, adaptive thresholding and vessel location map. The results declare that the method dominates over the prior proposed strategies like segmentation of vessels and recovering edges. Additionally, the evaluated algorithms achieving 94% accuracy of extracting normal fundus vessels.
Multimedia Tools and Applications, 2021
A rapid growth in medical ultrasound database makes it difficult for medical practitioners to man... more A rapid growth in medical ultrasound database makes it difficult for medical practitioners to manage and search relevant data with good efficiency. Hence, a novel image retrieval technique using Mean Distance Local Binary Pattern (Mean Distance LBP) has been proposed for content-based image retrieval. The conventional local binary pattern (LBP) converts every pixel of image into a binary pattern based on their relationship with neighbourhood pixels. The proposed feature descriptor differs from local binary pattern as it transforms the mutual relationship of all neighbouring pixels in a binary pattern based on their standard deviation templates as well as Euclidean distance from the center pixel. Color feature and Gray Level Co-occurrence Matrix have also been used in this work. To prove the excellence of the proposed method, experiments have been conducted on two different databases of natural images and face images. Further, the method is applied on real time ultrasound database for retrieval of liver images from a set of ultrasound images of various organs. The performance has been observed using well-known evaluation measures, precision and recall, and compared with some state-of-art local patterns. Comparison shows a significant improvement in the proposed method over existing methods.
The Computer Journal, 2019
Ultrasound imaging is undoubtedly the most used imaging modality for diagnostic purposes. Unfortu... more Ultrasound imaging is undoubtedly the most used imaging modality for diagnostic purposes. Unfortunately, it is accompanied by speckle which can degrade texture information by obscuring fine details like boundaries and edges. This work presents a method for despeckling ultrasound images by treating them with multiscale modified speckle reduction anisotropic diffusion model and Non-Subsampled shearlet transform (NSST). The method involves division of images using a non-subsampled Laplacian pyramid. This results in low and high frequency image components. Modified anisotropic diffusion is used on the low frequency part. The high frequency component, as subjected to shearlet function, generates noisy coefficients in various directions. These coefficients are further subjected to NSST thresholding. The denoised low and high frequency image components are then recombined to obtain the enhanced image. This multidimensional and multidirectional method improves the qualitative characteristic...
ArXiv, 2021
Audio or video anomaly datasets play a crucial role in automated surveillance. The range of appli... more Audio or video anomaly datasets play a crucial role in automated surveillance. The range of applications expand from outlier object/ situation detection to the detection of lifethreatening events. This research area has been active for more than 1.5 decades, and consequently, more and more datasets dedicated to anomalous actions and object detection have been created. Making use of these public anomaly datasets enable researchers to compare various anomaly detection frameworks with the same input data. This survey aims to address the lack of a comprehensive comparison and analysis of public datasets for audio, video, and audio-visual based anomaly detection. It also assists in selecting the best dataset for bench-marking frameworks. Additionally, we discuss gaps in the existing dataset and future direction insights toward developing multimodal anomaly detection datasets.
Multimedia Tools and Applications
2018 First International Conference on Secure Cyber Computing and Communication (ICSCCC), 2018
Local Binary Pattern (LBP) is a non-parametric descriptor that is used to study various local str... more Local Binary Pattern (LBP) is a non-parametric descriptor that is used to study various local structures of an image. It is considered as simple and efficient texture operator for image analysis in challenging real-time situations. It has been applied successfully for various applications of computer vision and image processing, like pattern recognition, texture analysis, face detection, image retrieval etc. This paper covers different LBP variants in spatial domain, which were created in order to improve its robustness and efficiency.
2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)
Multidimensional Systems and Signal Processing
Proceedings of International Conference on Women Researchers in Electronics and Computing
Ultrasound imaging is considered as one of the most widely used imaging modalities owing to its s... more Ultrasound imaging is considered as one of the most widely used imaging modalities owing to its simple and non-invasive nature. However, ultrasound images are usually manifested with speckle noise, that acts as a hindrance in carrying out any further analysis or disease detection by the radiologists. Despeckling of these images is thus a very important phenomenon to carry out further studies by medical experts. It is of utmost importance that ultrasound images be despeckled, keeping in consideration that no information is lost from the images. This paper covers various despeckling techniques that have been designed for ultrasound images, making sure that no information is lost.
Proceedings of International Conference on Women Researchers in Electronics and Computing
In Obstetrics, Ultrasound is used to access fetus growth which can be measured by Head Circumfere... more In Obstetrics, Ultrasound is used to access fetus growth which can be measured by Head Circumference. Accurate segmentation of fetal head is important for calculating Head Circumference. As Deep Learning is gaining popularity because of its state of the art performance, the various Deep Learning techniques for the segmentation of fetal skull are discussed in this article.
Proceedings of International Conference on Women Researchers in Electronics and Computing
In everyday life, image data, such as information, processing and computer vision, play a signifi... more In everyday life, image data, such as information, processing and computer vision, play a significant role in many applications; such as image classification, image segmentation and image retrieval. A preferred attributes that has been applied in a lots of picture applications is texture. This was forming an image using an array of pixels. Texture played a significant part in image segmentation and image detection and retrieval. In addition ranked the classifications of the texture then local binary pattern are coming. The LBP method seemed to work very effectively in real time. In the LBP method, comparing the values of the central pixels with the values of the neighbouring pixels and to attribute the binary values on these values. In this paper providing an overview for the local binary model and their benefits.
Pattern Recognition and Image Analysis
Ultrasound imaging is an indisputable image modality for clinical purposes. Unfortunately, it com... more Ultrasound imaging is an indisputable image modality for clinical purposes. Unfortunately, it comes with the inherent speckle noise which results in the degradation of the texture information in these images, thus making the diagnosis harder. This paper proposes a new approach for despeckling the ultrasound images combining the multiscale anisotropic diffusion model with the non-subsampled shearlet transform (NSST). The method involves the decomposition of images using the Non-Subsampled Laplacian pyramid, resulting in a low and high frequency sub images. Modified anisotropic diffusion method is further applied to the coarser component, whereas, the finer component is subjected to shearlet function, resulting in noisy coefficients, which are further subjected to thresholding. This multidimensional and multidirectional method enhances the visual characteristics of the ultrasound images with not just the removal of speckle noise, but also with the preservation of more edges, thus enhancing the images effectively. The performance of the proposed algorithm is assessed for real ultrasound images. Results show that the method excels over the earlier proposed techniques in terms of preservation of edges and structural similarities. Moreover, when analysed qualitatively, it is observed that there is a substantial removal of speckle noise, thus making the diagnosis easier for the radiologists.
Local Binary Pattern (LBP) is a non-parametric descriptor that is used to study various local str... more Local Binary Pattern (LBP) is a non-parametric descriptor that is used to study various local structures of an image. It is considered as simple and efficient texture operator for image analysis in challenging real-time situations. It has been applied successfully for various applications of computer vision and image processing, like pattern recognition, texture analysis, face detection, image retrieval etc. This paper covers different LBP variants in spatial domain, which were created in order to improve its robustness and efficiency.
Liver diseases are one of the significant public health issues in present scenario. Liver cirrhos... more Liver diseases are one of the significant public health issues in present scenario. Liver cirrhosis is one of the leading causes of deaths due to liver related diseases. In this work, classification of normal and cirrhotic liver is done using texture analysis. Various texture features are extracted for classification. Out of all the extracted features, seven best features are identified using fisher discriminant ratio. Further, weighted fisher discriminant ratio algorithm is designed using the selected features, such that maximum accuracy and sensitivity is achieved.
The applicability of contemporary deep learning techniques have seen considerable improvements in... more The applicability of contemporary deep learning techniques have seen considerable improvements in the field of biomedical signal analysis. Emotion analysis using EEG signals is one such problem that has been studied and worked upon extensively in recent times. In this paper we have proposed a novel methodology to classify emotions using signal processing techniques such as wavelet transform and statistical measures for feature extraction and dimensionality reduction followed by developing state of the art neural architecture for the classification task. A merged LSTM model has been proposed for binary classification of emotions. The model's applicability and accuracy has been validated using DEAP dataset which is the benchmark dataset for emotion recognition.
Angiography is a way towards picturing the retina of eye. Unfortunately, a specialist has to spen... more Angiography is a way towards picturing the retina of eye. Unfortunately, a specialist has to spend a lot of time to examine the picture. Segmentation is one of the processes to identify eye problems and decrease the specialist time. This paper proposes the performance comparison of vessel segmentation methodologies. Firstly, the fundus image is taken from the openly accessible database and pre-processing is done to adjust the contrast of input image so that the vessels are segmented. Segmentation is the second step of algorithm that segments the image and post processing is done to enhance the segmented binary image. The methods are involved with ISODATA, adaptive thresholding and vessel location map. The results declare that the method dominates over the prior proposed strategies like segmentation of vessels and recovering edges. Additionally, the evaluated algorithms achieving 94% accuracy of extracting normal fundus vessels.
Uploads
Papers by Anterpreet bedi