Mamoona Jabbar - Academia.edu (original) (raw)

Papers by Mamoona Jabbar

Research paper thumbnail of Evaluation of PSNR Value for Image Super-Resolution Using Deep Learning

Lahore Garrison University research journal of computer science and information technology, Dec 19, 2023

Deep learning, inspired by the human brain, is adept at deciphering extensive data sets. In recen... more Deep learning, inspired by the human brain, is adept at deciphering extensive data sets. In recent years, its methodologies have gained prominence across diverse domains, notably in image processing. These methods shine in tasks such as object detection, image augmentation, and especially in super-resolution-a technique that transforms low-resolution images into high-definition versions. Prominent models like the Convolutional Neural Network for Super Resolution, Super Resolution Residual Network, Generative Adversarial Network for Super Resolution, and its enhanced version, are pivotal in this transformation process. Each layer in these models is tailored to refine low-quality images into their high-resolution analogues. This means multiple clear images can emerge from a single blurry counterpart. For our research, we compiled a dataset of assorted images. We then compared the original low-quality versions to their deep learning-enhanced equivalents. To ensure a rigorous comparison, we employed metrics like the Peak Signal-to-Noise Ratio and the Structural Similarity Index. Our evaluation also incorporated calculating the 'ground truth' value, ensuring a comprehensive assessment. Among the models tested, VGG54 was a standout, boasting an impressive 96% similarity index. This underscores deep learning's potential in revolutionizing image processing and enhancement.

Research paper thumbnail of Content-based image retrieval via transfer learning

Journal of Intelligent and Fuzzy Systems, May 4, 2023

In the past few years, due to the increased usage of internet, smartphones, sensors and digital c... more In the past few years, due to the increased usage of internet, smartphones, sensors and digital cameras, more than a million images are generated and uploaded daily on social media platforms. The massive generation of such multimedia contents has resulted in an exponential growth in the stored and shared data. Certain ever-growing image repositories, consisting of medical images, satellites images, surveillance footages, military reconnaissance, fingerprints and scientific data etc., has increased the motivation for developing robust and efficient search methods for image retrieval as per user requirements. Hence, it is need of the hour to search and retrieve relevant images efficiently and with good accuracy. The current research focuses on Content-based Image Retrieval (CBIR) and explores well-known transfer learning-based classifiers such as VGG16, VGG19, EfficientNetB0, ResNet50 and their variants. These deep transfer leaners are trained on three benchmark image datasets i.e., CIFAR-10, CIFAR-100 and CINIC-10 containing 10, 100, and 10 classes respectively. In total 16 customized models are evaluated on these benchmark datasets and 96% accuracy is achieved for CIFAR-10 while 83% accuracy is achieved for CIFAR-100.

Research paper thumbnail of Content-based image retrieval via transfer learning

Journal of Intelligent & Fuzzy Systems

In the past few years, due to the increased usage of internet, smartphones, sensors and digital c... more In the past few years, due to the increased usage of internet, smartphones, sensors and digital cameras, more than a million images are generated and uploaded daily on social media platforms. The massive generation of such multimedia contents has resulted in an exponential growth in the stored and shared data. Certain ever-growing image repositories, consisting of medical images, satellites images, surveillance footages, military reconnaissance, fingerprints and scientific data etc., has increased the motivation for developing robust and efficient search methods for image retrieval as per user requirements. Hence, it is need of the hour to search and retrieve relevant images efficiently and with good accuracy. The current research focuses on Content-based Image Retrieval (CBIR) and explores well-known transfer learning-based classifiers such as VGG16, VGG19, EfficientNetB0, ResNet50 and their variants. These deep transfer leaners are trained on three benchmark image datasets i.e., C...

Research paper thumbnail of Evaluation of PSNR Value for Image Super-Resolution Using Deep Learning

Lahore Garrison University research journal of computer science and information technology, Dec 19, 2023

Deep learning, inspired by the human brain, is adept at deciphering extensive data sets. In recen... more Deep learning, inspired by the human brain, is adept at deciphering extensive data sets. In recent years, its methodologies have gained prominence across diverse domains, notably in image processing. These methods shine in tasks such as object detection, image augmentation, and especially in super-resolution-a technique that transforms low-resolution images into high-definition versions. Prominent models like the Convolutional Neural Network for Super Resolution, Super Resolution Residual Network, Generative Adversarial Network for Super Resolution, and its enhanced version, are pivotal in this transformation process. Each layer in these models is tailored to refine low-quality images into their high-resolution analogues. This means multiple clear images can emerge from a single blurry counterpart. For our research, we compiled a dataset of assorted images. We then compared the original low-quality versions to their deep learning-enhanced equivalents. To ensure a rigorous comparison, we employed metrics like the Peak Signal-to-Noise Ratio and the Structural Similarity Index. Our evaluation also incorporated calculating the 'ground truth' value, ensuring a comprehensive assessment. Among the models tested, VGG54 was a standout, boasting an impressive 96% similarity index. This underscores deep learning's potential in revolutionizing image processing and enhancement.

Research paper thumbnail of Content-based image retrieval via transfer learning

Journal of Intelligent and Fuzzy Systems, May 4, 2023

In the past few years, due to the increased usage of internet, smartphones, sensors and digital c... more In the past few years, due to the increased usage of internet, smartphones, sensors and digital cameras, more than a million images are generated and uploaded daily on social media platforms. The massive generation of such multimedia contents has resulted in an exponential growth in the stored and shared data. Certain ever-growing image repositories, consisting of medical images, satellites images, surveillance footages, military reconnaissance, fingerprints and scientific data etc., has increased the motivation for developing robust and efficient search methods for image retrieval as per user requirements. Hence, it is need of the hour to search and retrieve relevant images efficiently and with good accuracy. The current research focuses on Content-based Image Retrieval (CBIR) and explores well-known transfer learning-based classifiers such as VGG16, VGG19, EfficientNetB0, ResNet50 and their variants. These deep transfer leaners are trained on three benchmark image datasets i.e., CIFAR-10, CIFAR-100 and CINIC-10 containing 10, 100, and 10 classes respectively. In total 16 customized models are evaluated on these benchmark datasets and 96% accuracy is achieved for CIFAR-10 while 83% accuracy is achieved for CIFAR-100.

Research paper thumbnail of Content-based image retrieval via transfer learning

Journal of Intelligent & Fuzzy Systems

In the past few years, due to the increased usage of internet, smartphones, sensors and digital c... more In the past few years, due to the increased usage of internet, smartphones, sensors and digital cameras, more than a million images are generated and uploaded daily on social media platforms. The massive generation of such multimedia contents has resulted in an exponential growth in the stored and shared data. Certain ever-growing image repositories, consisting of medical images, satellites images, surveillance footages, military reconnaissance, fingerprints and scientific data etc., has increased the motivation for developing robust and efficient search methods for image retrieval as per user requirements. Hence, it is need of the hour to search and retrieve relevant images efficiently and with good accuracy. The current research focuses on Content-based Image Retrieval (CBIR) and explores well-known transfer learning-based classifiers such as VGG16, VGG19, EfficientNetB0, ResNet50 and their variants. These deep transfer leaners are trained on three benchmark image datasets i.e., C...