No abstract

No abstract

Deep learning has recently been used to study blind image quality assessment (BIQA) in great detail. Yet, the scarcity of high-quality algorithms prevents from developing them further and being used in a real-time scenario. Patch-based techniques have been used to forecast the quality of an image, but they typically award the picture quality score to an individual patch of the image. As a result, there would be a lot of misleading scores coming from patches. Some regions of the image are important and can contribute highly toward the right prediction of its quality. To prevent outlier regions, we suggest a technique with a visual saliency module which allows the only important region to bypass to the neural network and allows the network to only learn the important information required to predict the quality. The neural network architecture used in this study is Inception-ResNet-v2. We assess the proposed strategy using a benchmark database (KADID-10k) to show its efficacy. The outcome demonstrates better performance compared with certain popular no-reference IQA (NR-IQA) and full-reference IQA (FR-IQA) approaches. This technique is intended to be utilized to estimate the quality of an image being acquired in real time from drone imagery.

In the fields of image processing and computer vision, evaluating blind image quality (BIQA) is still a difficult task. In this paper, a unique BIQA framework is presented that integrates feature extraction, feature selection, and regression using a support vector machine (SVM). Various image characteristics are included in the framework, such as wavelet transform, prewitt and gaussian, log and gaussian, and prewitt, sobel, and gaussian. An SVM regression model is trained using these features to predict the quality ratings of photographs. The proposed model uses the Information Gain attribute approach for feature selection to improve the performance of the regression model and decrease the size of the feature space. Three commonly used benchmark datasets, TID2013, CSIQ, and LIVE, are utilized to assess the performance of the proposed methodology. The study examines how various feature types and feature selection strategies affect the functionality of the framework through thorough experiments. The experimental findings demonstrate that our suggested framework reaches the highest levels of accuracy and robustness. This suggests that it has a lot of potential to improve the accuracy and dependability of BIQA approaches. Additionally, its use is broadened to include image transmission, compression, and restoration. Overall, the results demonstrate our framework’s promise and ability to advance studies into image quality assessment.

The purpose of the no-reference image quality assessment (NR-IQA) is to measure perceived image quality based on subjective judgments; however, due to the lack of a clean reference image, this is a complicated and unresolved challenge. Massive new IQA datasets have facilitated the creation of deep learning-based image quality measurements. We present a unique model to handle the NR-IQA challenge in this research by employing a hybrid strategy that leverages from pre-trained CNN model and the unified learning mechanism that extracts both local and non-local characteristics from the input patch. The deep analysis of the proposed framework shows that the model uses features and a mechanism that improves the monotonicity relationship between objective and subjective ratings. The intermediary goal was mapped to a quality score using a regression architecture. To extract various feature maps, a deep architecture with an adaptive receptive field was used. Analyses of this biggest NR-IQA benchmark datasets demonstrate that the suggested technique outperforms current state-of-the-art NR-IQA measures.